% Encoding: UTF-8
@COMMENT{BibTeX export based on data in FAU CRIS: https://cris.fau.de/}
@COMMENT{For any questions please write to cris-support@fau.de}
@book{faucris.121946484,
address = {Dagstuhl},
editor = {Denzler, Joachim and Hornegger, Joachim and Kittler, Jürgen and Maurer Jr., Calvin R.},
faupublication = {yes},
keywords = {multi-sensor fusion; multi-modal perception; multiple expert fusion; fusion paradigms; multi-modal and intra-modal experts; non-rigid registration},
note = {UnivIS-Import:2015-07-08:Pub.2007.tech.IMMD.IMMD5.06311a},
publisher = {Internationales Begegnungs- und Forschungszentrum fuer Informatik (IBFI), Schloss Dagstuhl},
series = {Dagstuhl Seminar Proceedings},
title = {06311 {Abstracts} {Collection} -- {Sensor} {Data} and {Information} {Fusion} in {Computer} {Vision} and {Medicine}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Denzler07-ACS.pdf},
volume = {06311},
year = {2007}
}
@inproceedings{faucris.120333224,
address = {Erlangen},
author = {Prümmer, Marcus and Han, Jingfeng and Hornegger, Joachim},
booktitle = {Vision Modeling and Visualization},
date = {2005-11-16/2005-11-18},
editor = {Greiner Günther, Hornegger Joachim, Niemann Heinrich, Stamminger Marc},
faupublication = {yes},
pages = {187-194},
peerreviewed = {unknown},
publisher = {Akademische Verlagsgesellschaft Aka GmbH, Berlin},
title = {{2D}-{3D} {Non}-rigid {Registration} using {Iterative} {Reconstruction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Pruemmer05-2NR.pdf},
venue = {Erlangen},
year = {2005}
}
@inproceedings{faucris.110628804,
author = {Berger, Martin and Müller, Kerstin and Choi, Jang-Hwan and Aichert, André and Maier, Andreas and Fahrig, Rebecca},
booktitle = {IFMBE Proceedings},
doi = {10.1007/978-3-319-19387-8},
edition = {51},
faupublication = {yes},
isbn = {978-3-319-19387-8},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.2d3dre{\_}8},
pages = {54-57},
peerreviewed = {Yes},
title = {{2D}/{3D} {Registration} for {Motion} {Compensated} {Reconstruction} in {Cone}-{Beam} {CT} of {Knees} {Under} {Weight}-{Bearing} {Condition}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Berger15-2RF.pdf},
venue = {Toronto, Canada},
year = {2015}
}
@inproceedings{faucris.111364704,
author = {Kurzendorfer, Tanja and Reiml, Sabrina and Brost, Alexander and Toth, Daniel and Panayiotou, Maria and Mountney, Peter and Steidl, Stefan and Maier, Andreas},
booktitle = {IGIC 2017 - Abstract Book},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.2dinte},
pages = {13-14},
peerreviewed = {unknown},
title = {2-{D} {Interactive} {Scar} {Layer} {Visualization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Kurzendorfer17-2IS.pdf},
venue = {Magdeburg},
year = {2017}
}
@inproceedings{faucris.255675526,
author = {Hoppe, Elisabeth and Wetzl, Jens and Roser, Philipp and Felsner, Lina and Preuhs, Alexander and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}38},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-19},
pages = {158-163},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{2D} {Respiration} {Navigation} {Framework} for {3D} {Continuous} {Cardiac} {Magnetic} {Resonance} {Imaging}},
venue = {Regensburg},
year = {2021}
}
@inproceedings{faucris.121370304,
address = {Berlin},
author = {Schuldhaus, Dominik and Spiegel, Martin and Redel, Thomas and Polyanskaya, Maria and Struffert, Tobias and Hornegger, Joachim and Dörfler, Arnd},
booktitle = {Bildverarbeitung für die Medizin},
date = {2011-03-22},
editor = {H. Handels, J. Ehrhardt, T. Deserno, H. Meinzer, T. Tolxdorff},
faupublication = {yes},
pages = {109-113},
peerreviewed = {unknown},
publisher = {Springer},
title = {{2D} {Vessel} {Segmentation} {Using} {Local} {Adaptive} {Contrast} {Enhancement}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Schuldhaus11-2VS.pdf},
venue = {Luebeck},
year = {2011}
}
@phdthesis{faucris.233911807,
abstract = {Atrial fibrillation is one of the most common cardiac arrhythmias. It can be treated minimally invasive by catheter ablation. For guidance during the intervention, augmented fluoroscopy systems gain more and more popularity. These systems allow to fuse data which was pre-operatively acquired, e.g., using computed tomography, and intra-operative patient data. This facilitates navigation during the procedure by overlaying a 3-D model of the patient's left atrium to the fluoroscopic images. Moreover, if X-ray images are acquired from two views, 2-D image annotations can be displayed with respect to the 3-D patient model. Image fusion and annotation requires an accurate registration of pre-operative and intra-operative data which is mostly performed manually. This thesis is primarily concerned with methods for automatizing both the registration process and also steps which are required for registration. Thus, we propose also methods for reconstructing the 3-D shape of catheters from 2-D X-ray images as this is needed later for registration.
In the first part of this thesis, we present methods for fast 3-D annotation of catheters. The first method is able to annotate whole line-shaped catheters in 2-D X-ray images based on a single seed point. To this end, catheter-like image regions are transformed into a graph like structure which serves as reduced search space for the catheter detection method. Resulting annotations in two X-ray images from different views can then be used to compute a 3-D reconstruction of the catheters. Our proposed method establishes point correspondences based on epipolar geometry. We define an optimality criterion that makes this approach robust with respect to spurious and missing point correspondences. Both methods are then used to establish a method for automatic cryoballoon catheter reconstruction.
The second part investigates registration methods based on devices placed at certain anatomical structures. We present two different methods, one for thermal ablation and one for cryoablation. The first method relies on line-shaped devices placed outside the left atrium in the oesophagus and the coronary sinus. Their 3-D shape can be reconstructed using the algorithms presented in the first part and can then be aligned to their corresponding 3-D structures segmented from the preoperative data. The second method uses the pulmonary vein ostium which is a structure inside the left atrium in which cryoballoons are placed. A registration is established by relating the ostium position to a reconstruction of the cryoballoon computed using the approach presented in the first part. We use a skeletonization of the 3-D left atrium model to extract potential ostia from the model.
In the last part we consider an automatic registration method based on injected contrast agent. In this context we present a method for classification of contrasted frames. Moreover, we present a novel similarity measure for 3-D/2-D registration that takes into account how plausible a registration is. Plausibility is determined with respect to a reconstructed contrast agent distribution within the 3-D left atrium and the contrast agent in the 2-D images. We show that a combination of this similarity measure and a measure that relates edge information from the contrast agent in 2-D images to edges of the 3-D model increases accuracy substantially. As a final step, the frame-wise registration results are postprocessed by means of a Markov chain model of the cardiac motion. This method of temporal filtering reduces outliers and improves registration quality significantly.
Cardiovascular disease has become the number one cause of death worldwide. Its prevention, diagnosis and therapy are therefore highly important topics in today’s clinical practice and research. For the diagnosis and therapy of coronary artery disease, interventional C-arm-based fluoroscopy is an imaging method of choice. It delivers 2-D X-ray images from almost arbitrary directions, but a 2-D projection image is naturally limited in its depiction of complex spatial relations. While the C- arm systems are capable of rotating around the patient and thus allow a CT-like 3-D image reconstruction, their long rotation time of about five seconds leads to strong motion artefacts in 3-D coronary artery imaging. Several methods to estimate the coronary motion and compensate for it during 3-D image reconstruction can be found in the literature. All have their specific properties, advantages and disadvantages, which are discussed in the first part of this thesis.
Then, a novel method is introduced that is based on a 2-D–2-D image registra- tion algorithm, henceforth called rmc (Registration-based Motion Compensation). It is embedded in an iterative algorithm for motion estimation and compensation. rmc does not require any complex segmentation or user interaction and is thus fully automatic, which is a very desirable feature for interventional applications. Motion estimation and compensation becomes more difficult when projection data from the whole heart cycle is used from the beginning. rmc overcomes this by successively increasing the utilised amount of projections in a bootstrapping process.
Throughout the remainder of this thesis, rmc is first evaluated in a simulation study using a simple numerical phantom, then on the publicly available Cavarev platform (employing an anthropomorphic phantom), and finally in a study using 58 human clinical datasets. Through the simulation study, approximations for the inherent error of the investigated algorithms were established. In addition, evidence that the missing depth information of a 2-D motion model is not a limiting factor for coronary artery imaging was found. The Cavarev experiments investigated the effect of different filter kernel choices during the execution of rmc. For the quantitative evaluation on human clinical data, a new software called CoroEval was introduced to the scientific community.
Overall, it could be shown from both the quantitative results as well as the human observer ratings that rmc can be successfully applied to a large set of clinical data without user interaction or parameter changes, and with a high robustness against initial 3-D image quality, while delivering results that are at least up to the current state of the art, and better in many cases.
},
address = {Erlangen},
author = {Schwemmer, Chris},
edition = {1},
faupublication = {yes},
isbn = {978-3-8325-4937-4},
keywords = {Cardiac imaging; C-arm CT; Coronary imaging; Motion estimation; Reconstruction},
note = {UnivIS-Import:2019-08-15:Pub.2019.tech.IMMD.IMMD5.3dimag},
peerreviewed = {unknown},
publisher = {Logos Verlag Berlin},
series = {Studien zur Mustererkennung},
title = {3-{D} {Imaging} of {Coronary} {Vessels} {Using} {C}-arm {CT}},
url = {https://www5.cs.fau.de/Forschung/Publikationen/2019/Schwemmer19-IOC.pdf},
volume = {48},
year = {2019}
}
@phdthesis{faucris.296579125,
abstract = {Cardiovascular disease has become the number one cause of death worldwide. Its prevention, diagnosis and therapy are therefore highly important topics in today’s clinical practice and research. For the diagnosis and therapy of coronary artery disease, interventional C-arm-based fluoroscopy is an imaging method of choice. It delivers 2-D X-ray images from almost arbitrary directions, but a 2-D projection image is naturally limited in its depiction of complex spatial relations. While the C- arm systems are capable of rotating around the patient and thus allow a CT-like 3-D image reconstruction, their long rotation time of about five seconds leads to strong motion artefacts in 3-D coronary artery imaging. Several methods to estimate the coronary motion and compensate for it during 3-D image reconstruction can be found in the literature. All have their specific properties, advantages and disadvantages, which are discussed in the first part of this thesis.Then, a novel method is introduced that is based on a 2-D–2-D image registra- tion algorithm, henceforth called rmc (Registration-based Motion Compensation). It is embedded in an iterative algorithm for motion estimation and compensation. rmc does not require any complex segmentation or user interaction and is thus fully automatic, which is a very desirable feature for interventional applications. Motion estimation and compensation becomes more difficult when projection data from the whole heart cycle is used from the beginning. rmc overcomes this by successively increasing the utilised amount of projections in a bootstrapping process.
Throughout the remainder of this thesis, rmc is first evaluated in a simulation study using a simple numerical phantom, then on the publicly available Cavarev platform (employing an anthropomorphic phantom), and finally in a study using 58 human clinical datasets. Through the simulation study, approximations for the inherent error of the investigated algorithms were established. In addition, evidence that the missing depth information of a 2-D motion model is not a limiting factor for coronary artery imaging was found. The Cavarev experiments investigated the effect of different filter kernel choices during the execution of rmc. For the quantitative evaluation on human clinical data, a new software called CoroEval was introduced to the scientific community.
Overall, it could be shown from both the quantitative results as well as the human observer ratings that rmc can be successfully applied to a large set of clinical data without user interaction or parameter changes, and with a high robustness against initial 3-D image quality, while delivering results that are at least up to the current state of the art, and better in many case},
author = {Schwemmer, Chris},
faupublication = {yes},
peerreviewed = {automatic},
school = {Friedrich-Alexander-Universität Erlangen-Nürnberg},
title = {3-{D} {Imaging} of {Coronary} {Vessels} {Using} {C}-arm {CT}},
url = {https://www5.cs.fau.de/Forschung/Publikationen/2019/Schwemmer19-IOC.pdf},
year = {2019}
}
@inproceedings{faucris.121178684,
abstract = {Diagnosis and treatment of coronary heart disease are performed in the catheter laboratory using an angiographic X-ray C-arm system. The morphology of the coronary tree and potentially ischemic lesions are determined in 2D projection views. The hemodynamic impact of the lesion would be valuable information for treatment decision. Using other modalities for functional imaging is disrupting the clinical workflow since the patient has to be transferred from the catheter laboratory to another scanner, and back to the catheter laboratory for performing the treatment. In this work a novel technology is used for simultaneous 3D imaging of first pass perfusion and the morphology of the coronary tree from a single rotational angiogram. A selective, single shot of contrast agent of less than 20ml directly into the coronaries is sufficient for a proper contrast resolution. Due to the long acquisition time cardiac motion has to be considered. A novel reconstruction technique for estimation and compensation of cardiac motion from the acquired projection data is used. The overlay of the 3D structure of the coronary tree and the perfusion image shows the correlation of myocardial areas and the associated coronary sections supporting that region. In a case example scar lesions caused by a former myocardial infarct are investigated. A first pass perfusion defect is found which is validated by a late enhancement magnetic resonance image. No ischemic defects are found. The non vital regions are still supported by the coronary vasculature. © 2011 SPIE.},
author = {Lauritsch, Günter and Rohkohl, Christopher and Hornegger, Joachim and Sinha, Anil-Martin and Rittger, Harald and Brachmann, Johannes and Rieber, Johannes and Rittger, Harald},
booktitle = {Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling},
doi = {10.1117/12.877931},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{3D} imaging of myocardial perfusion and coronary tree morphology from a single rotational angiogram},
venue = {Lake Buena Vista, FL},
volume = {7964},
year = {2011}
}
@phdthesis{faucris.116854364,
abstract = {Nowadays, angiography is the gold standard for the visualization of the morphology of the cardiac vasculature and cardiac chambers in the interventional suite. Up to now, high resolution 2-D X-ray images are acquired with a C-arm system in standard
views and the diagnosis of the cardiologist is based on the observations in the planar X-ray images. No dynamic analysis of the cardiac chambers can be performed in 3-D. In the last years, cardiac imaging in 3-D using a C-arm system becomes of more and
more interest in the interventional catheter laboratory. Furthermore, the analysis of the 3-D motion would provide valuable information with respect to functional cardiac imaging. However, cardiac motion is a challenging problem in 3-D imaging, which
leads to severe imaging artifacts in the 3-D image. Therefore, the main research goal of this thesis was the visualization and extraction of dynamic and functional parameters of the cardiac chambers in 3-D using an interventional angiographic C-arm
system.
In this thesis, two different approaches for cardiac chamber motion-compensated reconstruction have been developed and evaluated. The first technique addresses the visualization of the left ventricle. Therefore, a whole framework for left ventricular
tomographic reconstruction and wall motion analysis has been developed. Dynamic surface models are generated from the 2-D X-ray images acquired during a short scan of a C-arm scanner using the 2-D bloodpool information. The acquisition time is about 5 s and the patients have normal sinus rhythm. Due to the acquisition time of about 5 s of the C-arm, no valuable retrospective ECG-gated reconstructions are possible. The dynamic surface LV model comprises a sparse motion vector field on the surface, which can be used for functional wall motion analysis. Furthermore, applying various interpolation schemes, dense motion vector fields can be generated
for a tomographic motion-compensated reconstruction. In this thesis, linear interpolation methods and spline-based methods have been compared. The combination of the wall motion analysis and the motion-compensated reconstruction is of great value to the diagnostic of pathological regions in cardiac interventions.
The second motion-compensated reconstruction approach uses volume-based motion estimation algorithms for the reconstruction of two - left atrium and left ventricle - to four heart chambers. A longer C-arm acquisition and contrast protocol allows for the generation of initial images at various heart phases. However, the initial image quality is not sufficient for motion estimation. Therefore, different pre-processing techniques, e.g., bilateral filtering or iterative reconstruction techniques, to improve the image quality were tested in combination with different motion estimation techniques.
Overall, the results of this thesis highly demonstrate the feasibility of dynamic and
functional cardiac chamber imaging using data from an interventional angiographic
C-arm system for clinical applications.
30% SUVpeak increase; regressive, <30% SUVpeak decrease; or stable, all others). RESULTS: Quantitative analysis of PSMA-positive lesions yielded significantly higher interobserver agreement (90.6%; 95% confidence interval [CI], 0.83%-0.96%) than visual assessments by either SPECT/CT (76.0%; 95% CI, 0.66%-0.84%) or planar scintigraphy (56.3%; 95% CI, 0.46%-0.66%). Intermethod comparison of aggregated results yielded significantly higher agreement between quantitative and visual SPECT/CT (85.1%; 95% CI, 0.80%-0.89%), as opposed to quantitative SPECT/CT and planar scintigraphy (53.1%; 95% CI, 0.47%-0.59%) or visual SPECT/CT and planar scintigraphy (54.9%; 95% CI, 0.49%-0.61%). In visual and quantitative analysis of 96 PSMA-positive lesions, the number of discrepancies ranged from 9 (9.4%) for quantitative SPECT/CT to 42 (43.8%) for planar scintigraphy. Overall reader confidence was higher for SPECT/CT than for planar scintigraphy (P < 0.001). Intraobserver agreement was near-perfect for all methods, whether SPECT/CT (visual, all κ = 0.94-0.97; quantitative κ = 0.94-0.98) or planar scintigraphy (all κ = 0.90-0.94). CONCLUSIONS: Quantitative evaluation of longitudinal change in tracer uptake by PSMA-positive lesions measured via SPECT/CT is superior to visual interpretation of images by planar scintigraphy or SPECT/CT. Compared with visual evaluation, quantitative SPECT/CT is highly reproducible, showing near-perfect agreement among observers and higher reader confidence.},
author = {Schmidkonz, Christian and Atzinger, Armin and Götz, Theresa and Beck, Michael and Ritt, Philipp and Prante, Olaf and Kuwert, Torsten and Bäuerle, Tobias and Cordes, Michael},
doi = {10.1097/RLU.0000000000002880},
faupublication = {yes},
journal = {Clinical Nuclear Medicine},
note = {CRIS-Team Scopus Importer:2020-01-14},
pages = {105-112},
peerreviewed = {Yes},
title = {{99mTc}-{MIP}-1404 {SPECT}/{CT} for {Patients} {With} {Metastatic} {Prostate} {Cancer}: {Interobserver} and {Intraobserver} {Variability} in {Treatment}-{Related} {Longitudinal} {Tracer} {Uptake} {Assessments} of {Prostate}-{Specific} {Membrane} {Antigen}-{Positive} {Lesions}},
volume = {45},
year = {2020}
}
@article{faucris.119825904,
abstract = {99m Tc-MIP-1404 (Progenics Pharmaceuticals, Inc., New York, NY) is a novel, SPECT-compatible 99m Tc-labeled PSMA inhibitor for the detection of prostate cancer. We present results of its clinical use in a cohort of 225 men with histologically confirmed prostate cancer referred for workup of biochemical relapse.From April 2013 to April 2017, 99m Tc-MIP1404-scintigraphy was performed in 225 patients for workup of PSA biochemical relapse of prostate cancer. Whole-body planar and SPECT/CT images of the lower abdomen and thorax were obtained 3-4 h p.i. of 710 ± 64 MBq 99m Tc-MIP-1404. Images were visually analyzed for presence and location of abnormal uptake. In addition, quantitative analysis of the SPECT/CT data was carried out on a subset of 125 patients. Follow-up reports of subsequent therapeutic interventions were available for 59% (139) of all patients.Tracer-positive lesions were detected in 77% (174/225) of all patients. Detections occurred at the area of local recurrence in the prostate in 25% of patients (or a total of 56), with metastases in lymph nodes in 47% (105), bone in 27% (60), lung in 5% (12), and other locations in 2% (4) of patients. Detection rates were 90% at PSA levels >=2 ng/mL and 54% below that threshold. Lesional SUVmax values were, on average, 32.2 ± 29.6 (0.8-142.2), and tumor-to-normal ratios 146.6 ± 160.5 (1.9-1482.4). The PSA level correlated significantly with total uptake of MIP-1404 in tumors (P < 0.001). Furthermore, total tumor uptake was significantly higher in patients with Gleason scores >=8 compared to those with Gleason scores <=7 (P < 0.05). In patients with androgen deprivation therapy, the detection rate was significantly higher compared to patients without androgen deprivation therapy (86% vs 71%, P < 0.001). Based on 99m Tc-MIP-1404-imaging and other information, an interdisciplinary tumor board review recommended changes to treatment plans in 74% (104/139) of those patients for whom the necessary documentation was available.SPECT/CT with 99m Tc-labeled MIP-1404 has a high probability in detecting PSMA-positive lesions in patients with elevated PSA. Statistical analysis disclosed significant relationship between quantitative 99m Tc-MIP-1404 uptake, PSA level, and Gleason score.},
author = {Schmidkonz, Christian and Hollweg, Claudia and Beck, Michael and Reinfelder, Julia and Götz, Theresa and Sanders, James Chester and Schmidt, Daniela and Prante, Olaf and Bäuerle, Tobias and Uder, Michael and Wullich, Bernd and Goebell, Peter and Kuwert, Torsten and Ritt, Philipp and Cavallaro, Alexander Josef},
doi = {10.1002/pros.23444},
faupublication = {yes},
journal = {Prostate},
note = {EVALuna2:13874},
pages = {54-63},
peerreviewed = {Yes},
title = {99m {Tc}-{MIP}-1404-{SPECT}/{CT} for the detection of {PSMA}-positive lesions in 225 patients with biochemical recurrence of prostate cancer},
volume = {78},
year = {2018}
}
@inproceedings{faucris.216892130,
abstract = {Automatic segmentation of organs-at-risk (OAR) in computed tomography (CT) is an essential part of planning effective treatment strategies to combat lung and esophageal cancer. Accurate segmentation of organs surrounding tumours helps account for the variation in position and morphology inherent across patients, thereby facilitating adaptive and computer-assisted radiotherapy. Although manual delineation of OARs is still highly prevalent, it is prone to errors due to complex variations in the shape and position of organs across patients, and low soft tissue contrast between neigh-bouring organs in CT images. Recently, deep convolutional neural networks (CNNs) have gained tremendous traction and achieved state-of-the-art results in medical image segmentation. In this paper, we propose a deep learning framework to segment OARs in thoracic CT images, specifically for the: heart, esophagus, trachea and aorta. Our approach employs dilated convolutions and aggregated residual connections in the bottleneck of a U-Net styled network, which incorporates global context and dense information. Our method achieved an overall Dice score of 91.57% on 20 unseen test samples from the ISBI 2019 SegTHOR challenge.},
author = {Vesal, Sulaiman and Ravikumar, Nishant and Maier, Andreas},
booktitle = {CEUR Workshop Proceedings},
date = {2019-04-10},
editor = {Su Ruan, Caroline Petitjean, Bernard Dubray, Bernard Dubray, Zoe Lambert},
faupublication = {yes},
note = {CRIS-Team Scopus Importer:2019-05-03},
peerreviewed = {unknown},
publisher = {CEUR-WS},
title = {{A} {2D} dilated residual {U}-net for multi-organ segmentation in thoracic {CT}},
venue = {Venice},
volume = {2349},
year = {2019}
}
@article{faucris.121173844,
abstract = {Cerebrovascular disease is among the leading causes of death in western industrial nations. 3D rotational angiography delivers indispensable information on vessel morphology and pathology. Physicians make use of this to analyze vessel geometry in detail, i.e. vessel diameters, location and size of aneurysms, to come up with a clinical decision. 3D segmentation is a crucial step in this pipeline. Although a lot of different methods are available nowadays, all of them lack a method to validate the results for the individual patient. Therefore, we propose a novel 2D digital subtraction angiography (DSA)-driven 3D vessel segmentation and validation framework. 2D DSA projections are clinically considered as gold standard when it comes to measurements of vessel diameter or the neck size of aneurysms. An ellipsoid vessel model is applied to deliver the initial 3D segmentation. To assess the accuracy of the 3D vessel segmentation, its forward projections are iteratively overlaid with the corresponding 2D DSA projections. Local vessel discrepancies are modeled by a global 2D/3D optimization function to adjust the 3D vessel segmentation toward the 2D vessel contours. Our framework has been evaluated on phantom data as well as on ten patient datasets. Three 2D DSA projections from varying viewing angles have been used for each dataset. The novel 2D driven 3D vessel segmentation approach shows superior results against state-of-the-art segmentations like region growing, i.e. an improvement of 7.2% points in precision and 5.8% points for the Dice coefficient. This method opens up future clinical applications requiring the greatest vessel accuracy, e.g. computational fluid dynamic modeling. © 2011 Institute of Physics and Engineering in Medicine.},
author = {Spiegel, Martin and Redel, T. and Struffert, Tobias and Hornegger, Joachim and Dörfler, Arnd},
doi = {10.1088/0031-9155/56/19/015},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {6401-6419},
peerreviewed = {Yes},
title = {{A} {2D} driven {3D} vessel segmentation algorithm for {3D} digital subtraction angiography data},
volume = {56},
year = {2011}
}
@article{faucris.221535426,
author = {Felsner, Lina and Hu, Shiyang and Maier, Andreas and Bopp, Johannes and Ludwig, Veronika and Anton, Gisela and Riess, Christian},
doi = {10.1038/s41598-019-45708-9},
faupublication = {yes},
journal = {Scientific Reports},
peerreviewed = {Yes},
title = {{A} 3-{D} {Projection} {Model} for {X}-ray {Dark}-field {Imaging}},
volume = {9},
year = {2019}
}
@misc{faucris.208871928,
author = {Hu, Shiyang and Felsner, Lina and Maier, Andreas and Ludwig, Veronika and Anton, Gisela and Riess, Christian},
doi = {10.1038/s41598-019-45708-9},
faupublication = {yes},
peerreviewed = {automatic},
title = {{A} 3-{D} {Projection} {Model} for {X}-ray {Dark}-field {Imaging}},
url = {https://arxiv.org/pdf/1811.04457},
year = {2018}
}
@inproceedings{faucris.208855099,
author = {Hu, Shiyang and Maier, Andreas and Hornegger, Joachim and Bayer, Florian and Weber, Thomas and Anton, Gisela and Riess, Christian},
booktitle = {Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {yes},
pages = {220-223},
peerreviewed = {Yes},
title = {{A} 3-{D} {Scattering} {Model} for {Orientation}-dependent {X}-ray {Dark}-field {Imaging}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Hu15-A3S.pdf},
year = {2015}
}
@inproceedings{faucris.108247524,
address = {-},
author = {Hornegger, Joachim and Niemann, Heinrich},
booktitle = {Proceedings of the 12th International Conference on Pattern Recognition (ICPR)},
date = {1994-10-09/1994-10-13},
doi = {10.1109/ICPR.1994.577035},
editor = {IEEE},
faupublication = {yes},
pages = {557-559},
peerreviewed = {unknown},
publisher = {IEEE Computer Society Press},
title = {{A} {Bayesian} approach to learn and classify 3-{D} objects from intensity images},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1994/Hornegger94-BAL.pdf},
venue = {Jerusalem},
year = {1994}
}
@inproceedings{faucris.234083576,
abstract = {In this paper a dataset consisting of 2,426 solar cells extracted from high-resolution electroluminescence (EL) images is used for automated defect probability recognition. The collected images contain both functional and defective solar cells with varying degrees of degradation both in monocrystalline and polycrystalline solar modules. The images were labeled by expert who categorized the solar cells by the likelihood of a defect within each image. The labeled images can be used for development of computer vision and machine learning methods for automatic detection of different defects, like cracks, fracture interconnects, PID, and cell quality and for the purpose of predicting the power efficiency los},
author = {Buerhop-Lutz, Claudia and Deitsch, Sergiu and Maier, Andreas and Gallwitz, Florian and Berger, Stephan and Doll, Bernd and Hauch, Jens and Camus, Christian and Brabec, Christoph},
booktitle = {35th European Photovoltaic Solar Energy Conference and Exhibition},
date = {2018-09-24/2018-09-28},
doi = {10.4229/35thEUPVSEC20182018-5CV.3.15},
faupublication = {yes},
isbn = {3-936338-50-7},
keywords = {EL Imaging; Machine Learning; Visual Inspection;},
pages = {1287-1289},
peerreviewed = {Yes},
title = {{A} {Benchmark} for {Visual} {Identification} of {Defective} {Solar} {Cells} in {Electroluminescence} {Imagery}},
venue = {Brussels},
year = {2018}
}
@article{faucris.117766044,
abstract = {Wireless capsule endoscopy (WCE) represents a significant technical breakthrough for the investigation of intestines. It can be used to examine entire section of the intestines, including the blind section that is not reachable with a traditional endoscope. However, one problem with this new technology is that too many images need to be examined by eyes to detect the normal and/or abnormal images and it becomes a burden to physicians. This paper presents some potential methods for an automatic detection system to identify suspected capsule endoscope images containing either chyme blocked, suspected blood indicator, or white spot abnormality in order to reduce this burden. These methods use color and texture of images as recognition features for the classifiers such as support vector machines (SVM), imbalanced SVM, and total margin-based adaptive fuzzy SVM. For comparison, the nearest neighbor (NN) classifier is also considered. Experimental results, carried out on 10-runs of 5-fold cross validation, show that the combination of hue-saturation (HS) histogram using relevant features (64 bins), image downsampling factor by 1, and TAF-SVM performs the best. The resulting accuracy obtained is 98.13% and the computational time during the testing phase is below 0.5 seconds per image, which is useful for practical applications.},
author = {Timotius, Ivanna and Miaou, Shaou-Gang and Valdeavilla, Edreen Bryan and Liu, Yi-Hung},
doi = {10.4015/S1016237212002962},
faupublication = {no},
journal = {Biomedical Engineering-Applications Basis Communications},
keywords = {Color histogram; Texture; Chyme blocked; Suspected blood indicator; White spot abnormality},
pages = {71 - 83},
peerreviewed = {Yes},
title = {{Abnormality} {Detection} for {Capsule} {Endoscope} {Images} {Based} on {Support} {Vector} {Machines}},
url = {http://www.worldscientific.com/doi/abs/10.4015/S1016237212002962},
volume = {24},
year = {2012}
}
@inproceedings{faucris.121390764,
address = {Erlangen},
author = {Wels, Michael and Huber, Martin and Hornegger, Joachim},
booktitle = {3rd Russian-Bavarian Conference on Biomedical Engineering},
date = {2007-07-02/2007-07-03},
editor = {Hornegger Joachim, Mayr Ernst W., Schookin Sergey, Feußner Hubertus, Navab Nassir, Gulyaev Yuri V., Höller Kurt, Ganzha Victor},
faupublication = {yes},
pages = {116-120},
peerreviewed = {unknown},
publisher = {Union aktuell},
title = {{A} {Boosting} {Approach} for {Multiple} {Sclerosis} {Lesion} {Segmentation} in {Multi}-{Spectral} {3D} {MRI}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Wels07-ABA.pdf},
venue = {Erlangen},
year = {2007}
}
@misc{faucris.111006764,
author = {Wilke, Peter and et al.},
author_hint = {Wilke Peter, et al.},
faupublication = {yes},
keywords = {Risiko-management-system},
note = {UnivIS-Import:2016-06-30:Pub.2002.tech.IMMD.IMMD2.{\_}absch},
peerreviewed = {automatic},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Abschlussbericht} {Software} für ein {Risiko}-{Management}-{System}},
year = {2002}
}
@article{faucris.120191104,
abstract = {Single-photon emission computed tomography (SPECT) allows the three-dimensional visualization of radioactivity within the human body and is widely used for clinical purposes. In SPECT, image quality is compromised by several factors including photon attenuation, photon scatter, the partial volume effect, and motion artefacts. These variables also confound the capacity of SPECT to quantify the concentration of radioactivity within given volumes of interest in absolute units, e.g. as kilobecquerels per cubic centimetre. In the last decade, considerable technical progress has been achieved in SPECT image reconstruction, involving, in particular, the development of iterative image reconstruction techniques. Furthermore, hybrid cameras integrating a SPECT camera with an X-ray CT scanner have become commercially available. These systems allow the acquisition of SPECT and CT datasets registered to each other with a high anatomical accuracy. First studies have shown that iterative SPECT image reconstruction techniques incorporating information from SPECT/CT image datasets greatly increase the accuracy of SPECT in quantifying radioactivity concentrations in phantoms and also in humans. This new potential of SPECT may improve not only diagnostic accuracy, but also dosimetry for internal radiotherapy. © 2011 Springer-Verlag.},
author = {Ritt, Philipp and Vija, Hans and Hornegger, Joachim and Kuwert, Torsten},
doi = {10.1007/s00259-011-1770-8},
faupublication = {yes},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
pages = {S69-S77},
peerreviewed = {Yes},
title = {{Absolute} quantification in {SPECT}},
volume = {38},
year = {2011}
}
@article{faucris.121402204,
abstract = {It was reported from planar imaging studies that the cerebral uptake of injected 99mTc-HMPAO activity is about 4-7% in humans. Recent work has shown that modern SPECT/CT devices are able to quantify the tissue concentration of radioactivity in vivo in absolute units (Bq/ml), while avoiding the limitations of planar techniques. The aims of this study were (a) to determine the cerebral uptake of 99mTc-HMPAO in absolute units in SPECT/CT, (b) to investigate potential differences in absolute tracer uptake for patients suspected of dementia.We performed 99mTc-HMPAO SPECT/CT in 65 patients with suspected dementia. 99mTc-HMPAO uptake was determined using a previously published quantitative SPECT/CT protocol. The absolute HMPAO uptake and the results of a regionalized analysis were compared for MMSE and NINCDS-ADRDA based patient groups.The mean absolute uptake of 99mTc-HMPAO for our patient population was 4.3 ± 0.8% of the injected dose. The uptake, as well as the regionalized analysis yielded significantly different results for low (<=23) and high (>23) MMSE groups and also for some of the NINCDS-ADRDA groups.Our results show that the absolute cerebral uptake of 99mTc-HMPAO is in the range of previously reported results, obtained by planar techniques. Absolute uptake is significantly different between the patient groups.},
author = {Welz, Friedrich and Sanders, James Chester and Kuwert, Torsten and Maler, Juan and Kornhuber, Johannes and Ritt, Philipp},
doi = {10.3413/Nukmed-0765-15-09},
faupublication = {yes},
journal = {Nuklearmedizin-Nuclear Medicine},
note = {EVALuna2:13833},
pages = {158-65},
peerreviewed = {Yes},
title = {{Absolute} {SPECT}/{CT} quantification of cerebral uptake of {99mTc}-{HMPAO} for patients with neurocognitive disorders},
volume = {55},
year = {2016}
}
@inproceedings{faucris.255681868,
author = {Marzahl, Christian and Bertram, Christof A. and Aubreville, Marc and Petrick, Anne and Weiler, Kristina and Gläsel, Agnes C. and Fragoso, Marco and Merz, Sophie and Bartenschlager, Florian and Hoppe, Judith and Langenhagen, Alina and Jasensky, Anne Katherine and Voigt, Jörn and Klopfleisch, Robert and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}71},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-19},
pages = {296-},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Abstract}: {Are} {Fast} {Labeling} {Methods} {Reliable}?: {A} {Case} {Study} of {Computer}-aided {Expert} {Annotations} on {Microscopy} {Slides}},
venue = {Regensburg},
year = {2021}
}
@inproceedings{faucris.254742382,
author = {Denzinger, Felix and Wels, Michael and Breininger, Katharina and Gülsün, Mehmet A. and Schöbinger, Max and André, Florian and Buß, Sebastian and Görich, Johannes and Sühling, Michael and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}24},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-09},
pages = {104-},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Abstract}: {Automatic} {CAD}-{RADS} {Scoring} using {Deep} {Learning}},
venue = {Regensburg, DEU},
year = {2021}
}
@inproceedings{faucris.254739128,
author = {Chen, Shuqing and Stromer, Daniel and Alnasser Alabdalrahim, Harb and Schwab, Stefan and Weih, Markus and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}69},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-09},
pages = {289-},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Abstract}: {Automatic} {Dementia} {Screening} and {Scoring} by {Applying} {Deep} {Learning} on {Clock}-drawing {Tests}},
venue = {Regensburg},
year = {2021}
}
@inproceedings{faucris.203716019,
author = {Mentl, Katrin and Saffoury, Rimon and Maier, Andreas},
booktitle = {Informatik Aktuell},
doi = {10.1007/978-3-662-56537-7{\_}12},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.abstra{\_}7},
pages = {13-13},
peerreviewed = {unknown},
title = {{Abstract}: {Automatic} {Malignancy} {Estimation} for {Pulmonary} {Nodules} from {CT} {Images}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Mentl18-AAM.pdf},
venue = {Erlangen},
year = {2018}
}
@inproceedings{faucris.243490397,
abstract = {Assessing coronary artery plaque segments in coronary CT angiography scans is an important task to improve patient management and clinical outcomes, as it can help to decide whether invasive investigation and treatment are necessary. In this work, we present three machine learning approaches capable of performing this task. The first approach is based on radiomics, where a plaque segmentation is used to calculate various shape-, intensity- and texture-based features under different image transformations. A second approach is based on deep learning and relies on centerline extraction as sole prerequisite. In the third approach, we fuse the deep learning approach with radiomic features. On our data the methods reached similar scores as simulated fractional flow reserve (FFR) measurements, which - in contrast to our methods - requires an exact segmentation of the whole coronary tree and often time-consuming manual interaction. In literature, the performance of simulated FFR reaches an AUC between 0.79–0.93 predicting an abnormal invasive FFR that demands revascularization. The radiomics approach achieves an AUC of 0.84, the deep learning approach 0.86 and the combined method 0.88 for predicting the revascularization decision directly. While all three proposed methods can be determined within seconds, the FFR simulation typically takes several minutes. Provided representative training data in sufficient quantities, we believe that the presented methods can be used to create systems for fully automatic non-invasive risk assessment for a variety of adverse cardiac events.
Computed Tomography Angiography (CTA) is one of the most commonly used modalities in the diagnosis of cerebrovascular diseases like ischemic strokes. Usually, the anatomy of interest in ischemic stroke cases is the Circle of Willis and its peripherals, the cerebral arteries, as these vessels are the most prominent candidates for occlusions. The diagnosis of occlusions in these vessels remains challenging, not only because of the large amount of surrounding vessels but also due to the large number of anatomical variants. We propose a fully automated image processing and visualization pipeline, which provides a full segmentation and modelling of the cerebral arterial tree for CTA data. The model itself enables the interactive masking of unimportant vessel structures e.g. veins like the Sinus Sagittalis, and the interactive planning of shortest paths meant to be used to prepare further treatments like a mechanical thrombectomy. Additionally, the algorithm automatically labels the cerebral arteries (Middle Cerebral Artery left and right, Anterior Cerebral Artery short, Posterior Cerebral Artery left and right) detects occlusions or interruptions in these vessels. The proposed pipeline does not require a prior non-contrast CT scan and achieves a comparable segmentation appearance as in a Digital Subtraction Angiography (DSA).
},
author = {Thamm, Florian and Jürgens, Markus and Ditt, Hendrik and Maier, Andreas},
booktitle = {BVM Workshop},
date = {2021-03-08/2021-03-09},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Abstract}: {VirtualDSA}++: {Automated} {Segmentation}, {Vessel} {Labeling}, {Occlusion} {Detection} and {Graph} {Search} on {CT}-{Angiography} {Data}},
venue = {OTH Regensburg},
year = {2021}
}
@inproceedings{faucris.120326844,
address = {Berlin},
author = {Hofmann, Hannes and Keck, Benjamin and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2010},
date = {2010-03-14/2010-03-16},
editor = {Deserno Thomas Martin, Handels Heinz, Meinzer Hans-Peter, Tolxdorff Thomas},
faupublication = {yes},
pages = {380-384},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Accelerated} {C}-arm {Reconstruction} by {Out}-of-{Projection} {Prediction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Hofmann10-ACR.pdf},
venue = {Aachen},
year = {2010}
}
@phdthesis{faucris.111917124,
abstract = {Cardiovascular diseases such as stroke, stenosis, peripheral or renal artery disease require accurate angiographic visualization techniques both for diagnosis and treatment planning. Beside the morphological imaging, the in-vivo acquisition of blood flow information gained increasing clinical importance in recent years.
Non-contrast-enhanced Magnetic Resonance Angiography (nceMRA) provides techniques for both fields. For morphological imaging, Time of Flight (TOF) and magnetization-prepared balanced Steady State Free Precession (mp-bSSFP) offer non-invasive, ionizing-radiation free and user independent alternatives to clinically established methods such as Digital Subtraction Angiography, Computed Tomography or Ultrasound. In the field of functional imaging, unique novel possibilities are given with three-directional velocity fields, acquired simultaneously to the morphological information using Phase Contrast Imaging (PCI). But the wider clinical use of nceMRA is still hampered by long acquisition times. Thus, accelerating nceMRA is a problem of high relevance and with great potential clinical impact. In this thesis, acceleration strategies based on k-sampling below the Nyquist limit and adapted reconstruction techniques, combining parallel MRI (pMRI) methods with Compressed Sensing (CS), are developed for both types of nceMRA methods. This includes contributions to all relevant parts of the reconstruction algorithms, the sampling strategy, the regularization technique and the optimization method.
For morphological imaging, a novel analytical pattern combining aspects of pMRI and CS, called the MICCS pattern, is proposed in combination with an adapted Split Bregman algorithm. This allows for a reduction in the acquisition time for peripheral TOF imaging of the entire lower vasculature from over 30 minutes to less than 8 minutes. Further acceleration is achieved for 3-D free-breathing renal angiography using mp-bSSFP, where the entire volume can be acquired in less than 1 minute instead of over 8 minutes. In addition, organ based evaluations including the vessel sharpness at important positions show the diagnostic usability and the increased accuracy over clinically established acceleration methods.
For PCI, advances are achieved with a dedicated novel sampling strategy, called I-VT sampling, including interleaved variations for all dimensions. Furthermore, two novel regularization techniques for PCI are developed in this thesis. First, a novel temporally masked and weighted strategy focusing on enhanced temporal fidelity, referred to as TMW is developed. This fully automatic approach uses dynamic and static vessel masks to guide the influence specifically to the static areas. Second, the low rank and sparse decomposition model, is extended to PCI, combined with adapted sparsity assumptions and the unconstrained Split Bregman algorithm. These methods are successfully applied to the carotid bifurcation, a region with a huge demand of significant acceleration as well high spatial and temporal accuracy of the flow values. But all algorithmic contributions exploit inherent properties of the acquisition technique, and thus can be applied for further applications.
In summary, the main contribution of this thesis is significant acceleration of nceMRA achieved with novel sampling, regularization and optimization elements.
177Lu radionuclide therapies, dosimetry is used for determining patient-individual dose burden. Standard approaches provide whole organ doses only. For assessing dose heterogeneity inside organs, voxel-wise dosimetry based on 3D SPECT/CT imaging could be applied. Often, this is achieved by convolving voxel-wise time-activity-curves with appropriate dose-voxel-kernels (DVK). The DVKs are meant to model dose deposition, and can be more accurate if modelled for the specific tissue type under consideration. In literature, DVKs are often not adapted to these inhomogeneities, or simple approximation schemes are applied. For 26 patients, which had previously undergone a 177Lu-PSMA or -DOTATOC therapy, decay maps, mass-density maps as well as tissue-type maps were derived from SPECT/CT acquisitions. These were used for a voxel-based dosimetry based on convolution with DVKs (each of size (4.8mm)3) obtained by four different DVK methods proposed in literature. The simplest only considers a spatially constant soft-tissue DVK (herein named 'constant'), while others either take into account only the local density of the center voxel of the DVK (herein named 'center-voxel') or scale each voxel linearly according to the proper mass density deduced from the CT image (herein named 'density') or considered both the local mass density as well as the direct path between the center voxel and any voxel in its surrounding (herein named 'percentage'). Deviations between resulting dose values and those from full Monte-Carlo simulations (MC simulations) were compared for selected organs and tissue-types. For each DVK method, inter-patient variability was considerable showing both under- and over-estimation of energy dose compared to the MC result for all tissue densities higher than soft tissue. In kidneys and spleen, 'constant' and 'density'-scaled DVKs achieved estimated doses with smallest deviations to the full MC gold standard (∼5%-8% underestimation). For low and high density tissue types such as lung and adipose or bone tissue, alternative DVK methods like 'center-voxel'- and 'percentage'- scaled achieved superior results, respectively. Concerning computational load, dose estimation with the DVK method 'constant' needs about 1.1 s per patient, center-voxel scaling amounts to 1.2 s, density scaling needs 1.4 s while percentage scaling consumes 860.3 s per patient. In this study encompassing a large patient cohort and four different DVK estimation methods, no single DVK-adaption method was consistently better than any other in case of soft tissue kernels. Hence in such cases the simplest DVK method, labeled 'constant', suffices. In case of tumors, often located in tissues of low (lung) or high (bone) density, more sophisticated DVK methods excel. The high inter-patient variability indicates that for evaluating new algorithms, a sufficiently large patient cohort needs to be involved.},
author = {Götz, Theresa and Schmidkonz, Christian and Lang, E. W. and Maier, Andreas and Kuwert, Torsten and Ritt, Philipp},
doi = {10.1088/1361-6560/ab5b81},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
keywords = {; dose-voxel-kernel; dosimetry; SPECT/CT},
note = {CRIS-Team Scopus Importer:2020-02-21},
peerreviewed = {Yes},
title = {{A} comparison of methods for adapting {177Lu} dose-voxel-kernels to tissue inhomogeneities},
volume = {64},
year = {2019}
}
@article{faucris.246367960,
abstract = {Canine mammary carcinoma (CMC) has been used as a model to investigate the pathogenesis of human breast cancer and the same grading scheme is commonly used to assess tumor malignancy in both. One key component of this grading scheme is the density of mitotic figures (MF). Current publicly available datasets on human breast cancer only provide annotations for small subsets of whole slide images (WSIs). We present a novel dataset of 21 WSIs of CMC completely annotated for MF. For this, a pathologist screened all WSIs for potential MF and structures with a similar appearance. A second expert blindly assigned labels, and for non-matching labels, a third expert assigned the final labels. Additionally, we used machine learning to identify previously undetected MF. Finally, we performed representation learning and two-dimensional projection to further increase the consistency of the annotations. Our dataset consists of 13,907 MF and 36,379 hard negatives. We achieved a mean F1-score of 0.791 on the test set and of up to 0.696 on a human breast cancer dataset.},
author = {Aubreville, Marc and Bertram, Christof A. and Donovan, Taryn A. and Marzahl, Christian and Maier, Andreas and Klopfleisch, Robert},
doi = {10.1038/s41597-020-00756-z},
faupublication = {yes},
journal = {Scientific Data},
note = {CRIS-Team Scopus Importer:2020-12-04},
peerreviewed = {Yes},
title = {{A} completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research},
volume = {7},
year = {2020}
}
@inproceedings{faucris.118743724,
author = {Xia, Yan and Dennerlein, Frank and Bauer, Sebastian and Berger, Martin and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the Third International Conference on Image Formation in X-Ray Computed Tomography},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.aconeb{\_}8},
pages = {178-181},
title = {{A} {Cone}-beam {Reconstruction} {Algorithm} for {Dose}-minimized {Short} {Scan} and {Super} {Short} {Scan}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Xia14-ACR.pdf},
venue = {Salt Lake City, UT, USA},
year = {2014}
}
@inproceedings{faucris.120190884,
abstract = {Machine learning techniques like pointwise classification are widely used for object detection and segmentation. However, for large search spaces like CT images, this approach becomes computationally very demanding. Designing strong yet compact classifiers is thus of great importance for systems that ought to be clinically used as time is a limiting factor in clinical routine. The runtime of a system plays an important role in the decision about its application. In this paper we propose a novel technique for reducing the computational complexity of voxel classification systems based on the well-known AdaBoost algorithm in general and Probabilistic Boosting Trees in particular. We describe a means of incorporating a measure of hypothesis complexity into the optimization process, resulting in classifiers with lower evaluation cost. More specifically, in our approach the hypothesis generation that is performed during the AdaBoost training is no longer based only on the error of a hypothesis but also on its complexity. This leads to a reduced overall classifier complexity and thus shorter evaluation times. The validity of the approach is shown in an experimental evaluation. In a cross validation experiment, a system for automatic segmentation of liver tumors in CT images, that is based on the Probabilistic Boosting Tree, was trained with and without the proposed extension. In this preliminary study, the evaluation cost for classifying previously unseen samples could be reduced by 83% using the methods described here without losing classification accuracy. © 2011 SPIE.},
author = {Militzer, Arne and Tietjen, Christian and Hornegger, Joachim},
booktitle = {Medical Imaging 2011: Computer-Aided Diagnosis},
doi = {10.1117/12.877944},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{A} cost constrained boosting algorithm for fast lesion detection and segmentation},
venue = {Lake Buena Vista, FL},
volume = {7963},
year = {2011}
}
@inproceedings{faucris.261183615,
author = {Pérez Toro, Paula Andrea and Vasquez Correa, Juan and Arias Vergara, Tomás and Klumpp, Philipp and Sierra-Castrillón, Melissa and Roldán-López, Mildred Estefania and Aguillón, David and Hincapié-Henao, Liliana and Tóbon-Quintero, Carlos Andres and Bocklet, Tobias and Schuster, Maria and Orozco-Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP39728.2021.9414009},
faupublication = {yes},
pages = {8338-8342},
peerreviewed = {unknown},
publisher = {IEEE},
title = {{Acoustic} and {Linguistic} {Analyses} to {Assess} {Early}-{Onset} and {Genetic} {Alzheimer}'s {Disease}},
url = {https://ieeexplore.ieee.org/abstract/document/9414009},
year = {2021}
}
@article{faucris.225556569,
abstract = {Objectives The purposes of this study were to validate the Acoustic Breathiness Index (ABI) for the Japanese-speaking population and to determine whether it is independent of factors such as sex, age, and perceptual ratings of roughness. Method First, the concurrent validity of the ABI for perceptual breathiness was evaluated on the concatenations of continuous speech and sustained vowels from 288 patients with varying degrees of dysphonia. The diagnostic accuracy was examined on 343 samples with 55 additional normophonic speakers. Second, the validity related to responsiveness-to-change was estimated on 222 samples obtained before and after interventions for 111 voice-disordered patients. Third, the relationships between the ABI and other variables (i.e., perceptual hoarseness/breathiness/roughness, sex, and age) were explored using bivariate and multivariate analyses for the 288 patients. Results First, the concurrent validity and the responsiveness-to-change validity were confirmed by strong correlation coefficients of .890 and .878, respectively. Second, the receiver operating characteristic analysis showed the area under the curve to be 0.939, indicating excellent accuracy. The ABI of 3.44 exhibited a sensitivity of 76.3% and a specificity of 94.1%. Third, although bivariate analyses revealed a weak relationship between ABI and roughness and an ABI difference by age, multiple regression analyses showed a strong relation between only ABI and breathiness, without a meaningful contribution from roughness, sex, and age factors. Conclusion The study confirmed that the ABI is an accurate and specific tool to estimate breathiness levels in the Japanese-speaking population and neither roughness, sex, nor age significantly affects the ABI.},
author = {Hosokawa, Kiyohito and von Latoszek, Ben Barsties and Ferrer Riesgo, Carlos Ariel and Iwahashi, Toshihiko and Iwahashi, Mio and Iwaki, Shinobu and Kato, Chieri and Yoshida, Misao and Umatani, Masanori and Miyauchi, Akira and Matsushiro, Naoki and Inohara, Hidenori and Ogawa, Makoto and Maryn, Youri},
doi = {10.1044/2019{\_}JSLHR-S-19-0077},
faupublication = {yes},
journal = {Journal of Speech Language and Hearing Research},
note = {CRIS-Team Scopus Importer:2019-09-03},
pages = {2617-2631},
peerreviewed = {Yes},
title = {{Acoustic} {Breathiness} {Index} for the {Japanese}-{Speaking} {Population}: {Validation} {Study} and {Exploration} of {Affecting} {Factors}},
volume = {62},
year = {2019}
}
@inproceedings{faucris.244856985,
abstract = {Voice Onset Time (VOT) has been used as an acoustic measure for a better understanding of the impact of different motor speech disorders in speech production. The purpose of our paper is to present a methodology for the manual measuring of VOT in voiceless plosive sounds and to analyze its suitability to detect specific articulation problems in Parkinson’s disease (PD) patients. The experiments are performed with recordings of the diadochokinetic evaluation which consists in the rapid repetition of the syllables /pa-ta-ka/. A total of 50 PD patients and 50 healthy speakers (HC) participated in this study. Manual measurements include VOT values and also duration of the closure phase, duration of the consonant, and the maximum spectral energy during the burst phase. Results indicate that the methodology is consistent and allows the automatic classification between PD patients and healthy speakers with accuracies of up to $$77\,\%$$.},
author = {Argüello-Vélez, Patricia and Arias-Vergara, Tomas and González-Rátiva, María Claudia and Orozco-Arroyave, Juan Rafael and Nöth, Elmar and Schuster, Maria Elke},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2020-09-08/2020-09-11},
doi = {10.1007/978-3-030-58323-1{\_}33},
editor = {Petr Sojka, Ivan Kopecek, Karel Pala, Aleš Horák},
faupublication = {yes},
isbn = {9783030583224},
keywords = {Acoustic analysis; Diadochokinesis; Speech processing; Voice onset time},
note = {CRIS-Team Scopus Importer:2020-11-06},
pages = {303-311},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Acoustic} characteristics of vot in plosive consonants produced by parkinson’s patients},
venue = {Brno},
volume = {12284 LNAI},
year = {2020}
}
@inproceedings{faucris.108124324,
address = {-},
author = {Stemmer, Georg and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Proc. European Conf. on Speech Communication and Technology},
editor = {Dalsgaard P., Lindberg B., Benner H.},
faupublication = {yes},
pages = {2745-2748},
publisher = {-},
title = {{Acoustic} {Modeling} of {Foreign} {Words} in a {German} {Speech} {Recognition} {System}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2001/Stemmer01-AMO.pdf},
venue = {Aalborg},
year = {2001}
}
@inproceedings{faucris.121385704,
author = {Stemmer, Georg and Hacker, Christian and Steidl, Stefan and Nöth, Elmar},
booktitle = {Proc. European Conf. on Speech Communication and Technology},
date = {2003-09-01/2003-09-04},
editor = {Eurospeech},
faupublication = {yes},
pages = {1313-1316},
title = {{Acoustic} {Normalization} of {Children}'s {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Stemmer03-ANO.pdf},
venue = {Geneva},
year = {2003}
}
@inproceedings{faucris.119884644,
abstract = {When we address speaker states like sleepiness, two partly competing interests can be observed: both within applications and engineering approaches, we aim at utmost performance in terms of classification or regression accuracy-which normally means using a very large feature vector and a brute force approach. The other interest is interpretation: we want to know what tells apart atypical (here: sleepy) speech from typical (here: non-sleepy) speech, i.e., their respective feature characteristics. Both interests cannot be served at the same time. In this paper, we preselect a small number of easily interpretable acoustic-prosodic features modelling spectrum and prosody, based on the literature and on the general idea of sleepiness being characterised by relaxation. Performance obtained with these single features and this small feature vector is compared with the performance obtained with a very large feature vector; moreover, we discuss to which extent the features chosen model relaxation as sleepiness characteristic.},
author = {Hönig, Florian Thomas and Batliner, Anton and Nöth, Elmar and Schnieder, Sebastian and Krajewski, Jarek},
booktitle = {Proceedings of the 7th Biennial meeting of the Speech Prosody Special Interest Group (SProSIG) of the International Speech Communication Association (ISCA) (Speech Prosody 2014)},
date = {2014-05-20/2014-05-23},
faupublication = {yes},
keywords = {Brute forcing; Interpretation; Paralinguistics; Prosody; Sleepiness},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.acoust},
pages = {(to appear)},
publisher = {International Speech Communications Association},
title = {{Acoustic}-{Prosodic} {Characteristics} of {Sleepy} {Speech} - between {Performance} and {Interpretation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Hoenig14-ACO.pdf},
venue = {Dublin, Ireland},
year = {2014}
}
@article{faucris.120199024,
abstract = {Subtraction methods in angiography are generally applied in order to enhance the visualization of blood vessels by eliminating bones and surrounding tissues from X-ray images. The main limitation of these methods is the sensitivity to patient movement, which leads to artifacts and reduces the clinical value of the subtraction images. In this paper we present a novel method for rigid motion compensation with primary application to road mapping, frequently used in image-guided interventions. Using the general concept of image-based registration, we optimize the physical position and orientation of the C-arm X-ray device, thought of as the rigid 3D transformation accounting for the patient movement. The registration is carried out using a hierarchical optimization strategy and a similarity measure based on the variance of intensity differences, which has been shown to be most suitable for fluoroscopic images. Performance evaluation demonstrated the capabilities of the proposed approach to compensate for potential intra-operative patient motion, being more resilient to the fundamental problems of pure image-based registration. © 2008 Elsevier Ltd. All rights reserved.},
author = {Ionasec, Razvan and Heigl, Benno and Hornegger, Joachim},
doi = {10.1016/j.compmedimag.2008.12.006},
faupublication = {yes},
journal = {Computerized Medical Imaging and Graphics},
pages = {256-266},
peerreviewed = {Yes},
title = {{Acquisition}-related motion compensation for digital subtraction angiography},
volume = {33},
year = {2009}
}
@article{faucris.121132484,
author = {Paulus, Dietrich and Ahlrichs, Ulrike and Heigl, Benno and Denzler, Joachim and Hornegger, Joachim and Zobel, Matthias and Niemann, Heinrich},
faupublication = {yes},
journal = {Videre - A Journal Of Computer Vision Research},
pages = {-},
peerreviewed = {Yes},
title = {{Active} {Knowledge}-{Based} {Scene} {Analysis}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2000/Paulus00-AKB.pdf},
volume = {1.0},
year = {2000}
}
@inproceedings{faucris.108149404,
address = {-},
author = {Paulus, Dietrich and Ahlrichs, Ulrike and Heigl, Benno and Denzler, Joachim and Hornegger, Joachim and Niemann, Heinrich},
booktitle = {Computer Vision Systems},
date = {1999-01-13/1999-01-15},
editor = {-},
faupublication = {yes},
pages = {180-199},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Active} {Knowledge} {Based} {Scene} {Analysis}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Paulus99-AKB.pdf},
venue = {Las Palmas},
year = {1999}
}
@article{faucris.112848604,
author = {Pasluosta, Cristian Federico and Steib, Simon and Klamroth, Sarah and Gaßner, Heiko and Goßler, Julia and Hannink, Julius and Von Tscharner, Vinzenz and Pfeifer, Klaus and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn},
doi = {10.3389/fnagi.2017.00316},
faupublication = {yes},
journal = {Frontiers in Aging Neuroscience},
pages = {316},
peerreviewed = {Yes},
title = {{Acute} {Neuromuscular} {Adaptations} in the {Postural} {Control} of {Patients} with {Parkinson}’s disease after {Perturbed} {Walking}},
url = {https://www.frontiersin.org/articles/10.3389/fnagi.2017.00316/full},
volume = {9},
year = {2017}
}
@inproceedings{faucris.120321784,
abstract = {
We introduce a new technique to improve the recognition of non-native speech. The underlying assumption is that for each non-native pronunciation of a speech sound, there is at least one sound in the target language that has a similar native pronunciation. The adaptation is performed by HMM interpolation between adequate native acoustic models. The interpolation partners are determined automatically in a data-driven manner. Our experiments show that this technique is suitable for both the offline adaptation to a whole group of speakers as well as for the unsupervised online adaptation to a single speaker. Results are given both for spontaneous non-native English speech as well as for a set of read non-native German utterances.
},
author = {Steidl, Stefan and Stemmer, Georg and Hacker, Christian and Nöth, Elmar},
booktitle = {Interspeech 2004 ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, Proceedings},
date = {2004-10-04/2004-10-08},
editor = {Kim S. H., Youn D. H.},
faupublication = {yes},
pages = {318-321},
peerreviewed = {Yes},
title = {{Adaptation} in the {Pronunciation} {Space} for {Non}-{Native} {Speech} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Steidl04-AIT.pdf},
venue = {Jeju Island},
year = {2004}
}
@inproceedings{faucris.113908124,
abstract = {Endovascular aneurysm repair (EVAR) has been gaining popularity over open repair of abdominal aortic aneurysms (AAAs) in the recent years. This paper describes a distortion correction approach to be applied during the EVAR cases. In a novel workflow, models (meshes) of the aorta and its branching arteries generated from preoperatively acquired computed tomography (CT) scans are overlayed with interventionally acquired fluoroscopic images. The overlay provides an arterial roadmap for the operator, with landmarks (LMs) marking the ostia, which are critical for stent placement. As several endovascular devices, such as angiographic catheters, are inserted, the anatomy may be distorted. The distortion reduces the accuracy of the overlay. To overcome the mismatch, the aortic and the iliac meshes are adapted to a device seen in uncontrasted intraoperative fluoroscopic images using the skeletonbased as-rigid-as-possible (ARAP) method. The deformation was evaluated by comparing the distance between an ostium and the corresponding LM prior to and after the deformation. The central positions of the ostia were marked in digital subtraction angiography (DSA) images as ground truth. The mean Euclidean distance in the image plane was reduced from 19.81+/-17.14mm to 4.56+/-2.81 mm.},
author = {Toth, Daniel and Pfister, Marcus and Maier, Andreas and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part I},
doi = {10.1007/978-3-319-24553-9{\_}42},
faupublication = {yes},
keywords = {computational geometry;as-rigid-as-possible;mesh deformation;abdominal aortic aneurysm;EVAR},
month = {Jan},
pages = {339-346},
peerreviewed = {unknown},
publisher = {Springer-verlag},
title = {{Adaption} of {3D} {Models} to {2D} {X}-{Ray} {Images} during {Endovascular} {Abdominal} {Aneurysm} {Repair}},
volume = {9349},
year = {2015}
}
@misc{faucris.203360309,
author = {Schirrmacher, Franziska and Köhler, Thomas and Riess, Christian},
doi = {10.1109/tci.2019.2956888},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Adaptive} {Quantile} {Sparse} {Image} ({AQuaSI}) {Prior} for {Inverse} {Imaging} {Problems}},
url = {http://arxiv.org/abs/1804.02152},
year = {2018}
}
@article{faucris.234343622,
abstract = {Inverse problems play a central role for many classical computer vision
and image processing tasks. Many inverse problems are ill-posed, and
hence require a prior to regularize the solution space. However, many of
the existing priors, like total variation, are based on ad-hoc
assumptions that have difficulties to represent the actual distribution
of natural images. Thus, a key challenge in research on image processing
is to find better suited priors to represent natural images. In this
article, we propose the Adaptive Quantile Sparse Image (AQuaSI) prior.
It is based on a quantile filter, can be used as a joint filter on
guidance data, and be readily plugged into a wide range of numerical
optimization algorithms. We demonstrate the efficacy of the proposed
prior in joint RGB/depth upsampling, on RGB/NIR image restoration, and
in a comparison with related regularization by denoising approache},
author = {Schirrmacher, Franziska and Riess, Christian and Köhler, Thomas},
doi = {10.1109/TCI.2019.2956888},
faupublication = {yes},
journal = {IEEE Transactions on Computational Imaging},
keywords = {Inverse problems; universal image prior; weighted quantile filter},
pages = {503--517},
peerreviewed = {Yes},
title = {{Adaptive} {Quantile} {Sparse} {Image} ({AQuaSI}) {Prior} for {Inverse} {Imaging} {Problems}},
url = {https://faui1-files.cs.fau.de/public/publications/mmsec/2020-Schirrmacher-AQS.pdf},
volume = {6},
year = {2020}
}
@inproceedings{faucris.121221584,
abstract = {We present various kinds of variational PDE based methods to interpolate missing sinogram data for tomographic image reconstruction. Using the observed sinogram data we inpaint the projection data by diffusion. To overcome the problem of contour blurring we consider nonlinear and anisotropic diffusion based regularizers and include optical flow information in order to preserve the sinuodal traces corresponding to object contours in the reconstructed image. We compare our results to a spectral deconvolution based interpolation and show that the method can easily be extended to 3D, © 2006 IEEE.},
author = {Hornegger, Joachim and Köstler, Harald and Rüde, Ulrich and Prümmer, Marcus},
booktitle = {Proceedings of the ICPR 2006},
date = {2006-08-20/2006-08-24},
doi = {10.1109/ICPR.2006.225},
faupublication = {yes},
pages = {778-781},
peerreviewed = {unknown},
title = {{Adaptive} variational sinogram interpolation of sparsely sampled {CT} data},
venue = {Hong Kong},
volume = {3},
year = {2006}
}
@inproceedings{faucris.119813804,
abstract = {Wearable body sensors have become an important basis for today's medical and fitness applications. To assist athletes or to take care of elderly people in everyday life situations, sensor data can be collected and processed to give helpful feedback. However, the data collection process of multiple or different sensor systems still had to be done manually by the user or an expert, which usually takes a lot of time and can lead to errors. This paper presents an embedded data collection and communication module based on an AT90USB microcontroller, which can automatically acquire data from various wired and wireless sensors (e.g. via USB or Bluetooth® ). The obtained data can be cached, preprocessed and transmitted to a specified central server using LAN, Wi-Fi or GMS/GPRS. Through unified expansion slots, additional communication devices and a BeagleBoneTM embedded can be extended to handle many different sensor systems. Moreover, wired sensors can be charged through appropriate circuits. This data collection and communication module operates without any input settings and special knowledge by the user. Five prototypes with different configurations and extension units concerning communication interfaces and computation power have been built up. The evaluation of the transfer reliability with 100%, whereupon 98% of data could be transmitted at once and the remaining 2% with the next attempt, confirms the stability of data transmission.},
author = {Blank, Peter and Kugler, Patrick and Schuldhaus, Dominik and Eskofier, Björn},
booktitle = {Proceedings of the 9th International Conference on Body Area Networks},
date = {2014-09-29/2014-10-01},
doi = {10.4108/icst.bodynets.2014.257018},
faupublication = {yes},
isbn = {9781631900471},
keywords = {Autonomous; BeagleBone; Data acquisition and transmission; Embedded computing; GSM/GPRS; mHealth; Microcontroller; Telemedicine; USB; Wearable sensors},
note = {UnivIS-Import:2016-06-01:Pub.2014.tech.IMMD.IMMD5.adatac},
pages = {154-158},
peerreviewed = {unknown},
publisher = {ICST},
title = {{A} data collection and communication module for telemedicine and mhealth systems},
venue = {London, Great Britain},
year = {2014}
}
@inproceedings{faucris.269631698,
author = {Hofmann, Andreas and Lomakin, Konstantin and Sippel, Mark and Gold, Gerald},
booktitle = {German Microwave Conference},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Additively} {Manufactured} {Broadwall} {Waveguide} {Couplers} for {V}-{Band} {Applications}},
venue = {Ulm},
year = {2022}
}
@inproceedings{faucris.269631319,
author = {Hofmann, Andreas and Lomakin, Konstantin and Sippel, Mark and Gold, Gerald},
booktitle = {IEEE/MTT-S International Microwave Symposium (IMS)},
doi = {10.1109/ims37962.2022.9865365},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Additively} {Manufactured} {Slotted} {Waveguides} for {THz} {Applications}},
venue = {Denver, CO},
year = {2022}
}
@inproceedings{faucris.277200179,
author = {Hofmann, Andreas and Klein, Laura and Lomakin, Konstantin and Sippel, Mark and Gold, Gerald},
booktitle = {European Microwave Conference (EuMC)},
doi = {10.23919/eumc54642.2022.9924342},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Additively} {Manufactured} {WR15} {Waveguide} to {Microstrip} {Transition} for {Broadband} {V}-{Band} {Applications}},
venue = {Milan, Italy},
year = {2022}
}
@article{faucris.234236031,
abstract = {Currently methods for predicting absorbed dose after administering a radiopharmaceutical are rather crude in daily clinical practice. Most importantly, individual tissue density distributions as well as local variations of the concentration of the radiopharmaceutical are commonly neglected. The current study proposes machine learning techniques like Green's function-based empirical mode decomposition and deep learning methods on U-net architectures in conjunction with soft tissue kernel Monte Carlo (MC) simulations to overcome current limitations in precision and reliability of dose estimations for clinical dosimetric applications. We present a hybrid method (DNN-EMD) based on deep neural networks (DNN) in combination with empirical mode decomposition (EMD) techniques. The algorithm receives x-ray computed tomography (CT) tissue density maps and dose maps, estimated according to the MIRD protocol, i.e. employing whole organ S-values and related time-integrated activities (TIAs), and from measured SPECT distributions of 177Lu radionuclei, and learns to predict individual absorbed dose distributions. In a second step, density maps are replaced by their intrinsic modes as deduced from an EMD analysis. The system is trained using individual full MC simulation results as reference. Data from a patient cohort of 26 subjects are reported in this study. The proposed methods were validated employing a leave-one-out cross-validation technique. Deviations of estimated dose from corresponding MC results corroborate a superior performance of the newly proposed hybrid DNN-EMD method compared to its related MIRD DVK dose calculation. Not only are the mean deviations much smaller with the new method, but also the related variances are much reduced. If intrinsic modes of the tissue density maps are input to the algorithm, variances become even further reduced though the mean deviations are less affected. The newly proposed hybrid DNN-EMD method for individualized radiation dose prediction outperforms the MIRD DVK dose calculation method. It is fast enough to be of use in daily clinical practice.},
author = {Götz, Theresa and Schmidkonz, Christian and Chen, Shuqing and Al-Baddai, S. and Kuwert, Torsten and Lang, E. W.},
doi = {10.1088/1361-6560/ab65dc},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
note = {CRIS-Team Scopus Importer:2020-02-14},
pages = {035007-},
peerreviewed = {Yes},
title = {{A} deep learning approach to radiation dose estimation},
volume = {65},
year = {2020}
}
@article{faucris.222102746,
abstract = {Optical coherence tomography angiography (OCTA) is a relatively new imaging modality that generates microvasculature map. Meanwhile, deep learning has been recently attracting considerable attention in image-to-image translation, such as image denoising, super-resolution and prediction. In this paper, we propose a deep learning based pipeline for OCTA. This pipeline consists of three parts: training data preparation, model learning and OCTA predicting using the trained model. To be mentioned, the datasets used in this work were automatically generated by a conventional system setup without any expert labeling. Promising results have been validated by in-vivo animal experiments, which demonstrate that deep learning is able to outperform traditional OCTA methods. The image quality is improved in not only higher signal-to-noise ratio but also better vasculature connectivity by laser speckle eliminating, showing potential in clinical use. Schematic description of the deep learning based optical coherent tomography angiography pipeline.},
author = {Liu, Xi and Huang, Zhiyu and Wang, Zhenzhou and Wen, Chenyao and Jiang, Zhe and Yu, Zekuan and Liu, Jingfeng and Liu, Gangjun and Huang, Xiaolin and Maier, Andreas and Ren, Qiushi and Lu, Yanye},
doi = {10.1002/jbio.201900008},
faupublication = {yes},
journal = {Journal of Biophotonics},
keywords = {CNN; deep learning; OCT angiography},
note = {CRIS-Team Scopus Importer:2019-07-12},
peerreviewed = {Yes},
title = {{A} deep learning based pipeline for optical coherence tomography angiography},
year = {2019}
}
@inproceedings{faucris.107362684,
author = {Grimm, Robert and Court, Johannes and Fieselmann, Andreas and Block, Kai Tobias and Kiefer, Berthold and Hornegger, Joachim},
booktitle = {Proceedings of International Society for Magnetic Resonance in Medicine},
date = {2012-05-05/2012-05-11},
faupublication = {yes},
pages = {2559},
peerreviewed = {unknown},
title = {{A} {Digital} {Perfusion} {Phantom} for {T1}-weighted {DCE}-{MRI}},
venue = {Melbourne},
year = {2012}
}
@article{faucris.121176924,
abstract = {We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modality-specific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation models and the non-parametrically modeled INUs are estimated via EM during segmentation itself, a Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance-related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patient-specific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting tree (PBT) for classifying image voxels. It relies on the surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3D Haar-like features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real-world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81± 0.09 (WM) and 0.82 ± 0.06 (GM) and 0.87 ± 0.05 (WM) and 0.83 ± 0.12 (GM) for the two collections of real-world data sets - consisting of 20 and 18 volumes, respectively - provided by the Internet Brain Segmentation Repository. © 2011 Institute of Physics and Engineering in Medicine.},
author = {Wels, Michael and Zheng, Yefeng and Huber, Martin and Hornegger, Joachim and Comaniciu, Dorin},
doi = {10.1088/0031-9155/56/11/007},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {3269-3300},
peerreviewed = {Yes},
title = {{A} discriminative model-constrained em approach to {3D} {MRI} brain tissue classification and intensity non-uniformity correction},
volume = {56},
year = {2011}
}
@book{faucris.121203984,
abstract = {In this paper we present a fully automated approach to the segmentation of pediatric brain tumors in multi-spectral 3-D magnetic resonance images. It is a top-down segmentation approach based on a Markov random field (MRF) model that combines probabilistic boosting trees (PBT) and lower-level segmentation via graph cuts. The PBT algorithm provides a strong discriminative observation model that classifies tumor appearance while a spatial prior takes into account the pair-wise homogeneity in terms of classification labels and multi-spectral voxel intensities. The discriminative model relies not only on observed local intensities but also on surrounding context for detecting candidate regions for pathology. A mathematically sound formulation for integrating the two approaches into a unified statistical framework is given. The proposed method is applied to the challenging task of detection and delineation of pediatric brain tumors. This segmentation task is characterized by a high non-uniformity of both the pathology and the surrounding non-pathologic brain tissue. A quantitative evaluation illustrates the robustness of the proposed method. Despite dealing with more complicated cases of pediatric brain tumors the results obtained are mostly better than those reported for current state-of-the-art approaches to 3-D MR brain tumor segmentation in adult patients. The entire processing of one multi-spectral data set does not require any user interaction, and takes less time than previously proposed methods. © 2008 Springer-Verlag Berlin Heidelberg.},
address = {Berlin},
author = {Wels, Michael and Carneiro, Gustavo and Aplas, Alexander and Huber, Martin and Hornegger, Joachim and Comaniciu, Dorin},
doi = {10.1007/978-3-540-85988-8{\_}9},
faupublication = {yes},
isbn = {3-540-44707-5},
note = {UnivIS-Import:2015-04-16:Pub.2008.tech.IMMD.IMMD5.adiscr},
pages = {67-75},
peerreviewed = {Yes},
publisher = {Springer-verlag},
series = {Lecture Notes on Computer Science},
title = {{A} discriminative model-constrained graph cuts approach to fully automated pediatric brain tumor segmentation in 3-{D} {MRI}},
volume = {5241},
year = {2008}
}
@inproceedings{faucris.229900998,
abstract = {Deep neural networks have achieved tremendous success in various fields including medical image segmentation. However, they have long been criticized for being a black-box, in that interpretation, understanding and correcting architectures is difficult as there is no general theory for deep neural network design. Previously, precision learning was proposed to fuse deep architectures and traditional approaches. Deep networks constructed in this way benefit from the original known operator, have fewer parameters, and improved interpretability. However, they do not yield state-of-the-art performance in all applications. In this paper, we propose to analyze deep networks using known operators, by adopting a divide-and-conquer strategy to replace network components, whilst retaining networks performance. The task of retinal vessel segmentation is investigated for this purpose. We start with a high-performance U-Net and show by step-by-step conversion that we are able to divide the network into modules of known operators. The results indicate that a combination of a trainable guided filter and a trainable version of the Frangi filter yields a performance at the level of U-Net (AUC 0.974 vs. 0.972) with a tremendous reduction in parameters (111, 536 vs. 9, 575). In addition, the trained layers can be mapped back into their original algorithmic interpretation and analyzed using standard tools of signal processing.<},
address = {Shenzhen},
author = {Fu, Weilin and Breininger, Katharina and Schaffert, Roman and Ravikumar, Nishant and Maier, Andreas},
booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI 2019)},
date = {2019-10-13/2019-10-17},
doi = {10.1007/978-3-030-32239-7{\_}21},
editor = {Dinggang Shen, Tianming Liu, Terry M. Peters, Lawrence H. Staib, Caroline Essert, Sean Zhou, Pew-Thian Yap, Ali Khan},
faupublication = {yes},
isbn = {978-3-030-32238-0},
keywords = {Precision Learning; Debugging; CNN},
pages = {183-192},
peerreviewed = {Yes},
publisher = {Springer, Cham},
title = {{A} {Divide}-and-{Conquer} {Approach} towards {Understanding} {Deep} {Networks}},
url = {https://link.springer.com/chapter/10.1007/978-3-030-32239-7{\_}21},
venue = {Shenzhen, China},
year = {2019}
}
@article{faucris.286930849,
abstract = {Purpose: The aim of this study was to investigate the speech prosody of post-lingually deaf cochlear implant (CI) users compared with control speakers without hearing or speech impairment. Method: Speech recordings of 74 CI users (37 males and 37 females) and 72 age-balanced control speakers (36 males and 36 females) are considered. All participants are German native speakers and read Der Nordwind und die Sonne (The North Wind and the Sun), a standard text in pathological speech analysis and phonetic transcriptions. Automatic acoustic analysis is performed considering pitch, loudness, and duration features, including speech rate and rhythm. Results: In general, duration and rhythm features differ between CI users and control speakers. CI users read slower and have a lower voiced segment ratio compared with control speakers. A lower voiced ratio goes along with a prolongation of the voiced segments’ duration in male and with a prolongation of pauses in female CI users. Rhythm features in CI users have higher variability in the duration of vowels and consonants than in control speakers. The use of bilateral CIs showed no advantages concerning speech prosody features in comparison to unilateral use of CI. Conclusions: Even after cochlear implantation and rehabilitation, the speech of postlingually deaf adults deviates from the speech of control speakers, which might be due to changed auditory feedback. We suggest considering changes in temporal aspects of speech in future rehabilitation strategies. Supplemental Material: https://doi.org/10.23641/asha.21579171.},
author = {Arias-Vergara, Tomás and Batliner, Anton and Rader, Tobias and Polterauer, Daniel and Högerle, Catalina and Müller, Joachim and Orozco-Arroyave, Juan Rafael and Nöth, Elmar and Schuster, Maria},
doi = {10.1044/2022{\_}JSLHR-21-00116},
faupublication = {yes},
journal = {Journal of Speech Language and Hearing Research},
note = {CRIS-Team Scopus Importer:2022-12-23},
pages = {4623-4636},
peerreviewed = {Yes},
title = {{Adult} {Cochlear} {Implant} {Users} {Versus} {Typical} {Hearing} {Persons}: {An} {Automatic} {Analysis} of {Acoustic}–{Prosodic} {Parameters}},
volume = {65},
year = {2022}
}
@phdthesis{faucris.296592773,
abstract = {X-ray imaging is a standard technique for examinations and interventions in medicine. Based on X-rays, Phase-Contrast Imaging (PCI) can provide an excellent soft-tissue contrast. The most promising setup for measuring phase-contrast in a medical context is the Talbot-Lau Interferometer (TLI), where specialized gratings are integrated between a regular medical X-ray tube and X-ray detector. The TLI allows to measure the classical X-ray attenuation in combination with the phase-contrast and dark-field signal. All three signals provide unique information and can in combination with each other enable an improved medical diagnostic. Acquiring volumetric scans with a TLI enables multi-modal imaging in which the reconstructed volumes are inherently registered. While medical procedures could greatly benefit from such a system, current implementations of such a setup in a medical environment are prevented by hardware- and software-based problems. In this work, we propose algorithms for solving algorithmic challenges towards the reconstruction of phase-contrast and dark-field signals with clinical compatibility.
In the first part, advanced reconstruction techniques for the differential phase-contrast signal from a TLI are investigated. Here, the focus is on improving the reconstruction of the phase contrast data from a TLI for large objects. Current Talbot-Lau systems suffer from a small field of view, which leads to truncation for large objects, such as humans. To avoid artifacts in the reconstruction, we propose a method for phase-sensitive Region-of-Interest (ROI) Computed Tomography (CT). The proposal involves a special setup, where a large detector allows measuring complete non-truncated attenuation images, while additional gratings allow for phase-contrast imaging of a ROI. A corresponding correction algorithm is proposed to correct the truncation of the phase-contrast images. With experiments, we show that the proposed method can enable a clinically practical TLI implementation. Unfortunately, the signal strength of the phase measurement depends on the position of the object in setup. This leads to a change in the projection model and subsequent artifacts in the reconstruction. The artifacts prevent the evaluation of quantitative values and, therefore, the use of the data in a medical environment. In particular, this challenge introduces artifacts in the reconstruction of large objects. We propose two correction algorithms to alleviate this issue. The excellent performance of both algorithms in the experiments indicate the possibility for phase-sensitive CT for large objects.
In the second part we consider the reconstruction of the dark-field signal. The scattering of the dark-field signal is high-dimensional, which leads to an orientation-dependent signal strength and prevents the use of Filtered Back-Projection (FBP) algorithms. Current projection models describe the signal formation only in two dimensions. Therefore, in order to reconstruct the dark-field, complex sampling trajectories must be used, which are clinically impractical. To tackle this challenge, we propose a general 3-D dark-field projection model, which enables to model the signal formation directly in 3-D. The general description facilitates a high degree of flexibility and enables modeling complex trajectories such as a helix. Our experimental evaluation shows a good agreement with wavefront simulations and real measurements. The projection model also allows a reconstruction of the dark-field signal with a true 3-D dark-field reconstruction algorithm. Experiments show the feasibility of a helical reconstruction and investigated the stability of the algorithm with respect to different influences. Overall, these promising first results indicate that a reconstruction of directed structures with a spiral trajectory is feasible.
Face detection is a computer technology that determines the locations and sizes of human faces in arbitrary (digital) images. It detects facial features and ignores anything else, such as buildings, trees and other parts of the body. In this paper, we present a face detection system based on the Schneiderman-Kanade method. This system is trained using visual attributes extracted from training samples.},
author = {Setyawan, Iwan and Wibowo, Yohan and Timotius, Ivanna and Febrianto, Andreas A.},
booktitle = {2011 6th International Conference on Telecommunication Systems, Services, and Applications (TSSA)},
date = {2011-10-20/2011-10-21},
doi = {10.1109/TSSA.2011.6095395},
faupublication = {no},
isbn = {978-1-4577-1441-2},
peerreviewed = {Yes},
title = {{A} human face detection system based on {Schneiderman}-{Kanade} method},
url = {http://ieeexplore.ieee.org/document/6095395/},
venue = {Bali},
year = {2011}
}
@inproceedings{faucris.111140524,
abstract = {In this paper, we propose a monocular vision system for autonomous obstacle avoidance and simultaneous stabilization of dynamic bipedal walking using the Aldebaran Nao robot. In particular, we address the case where erroneous bipedal locomotion causes the robot to drift away from a planned trajectory over time. To eliminate drifting, we use hybrid control patterns. This results in an efficient, self-correcting system that does not require to alter the robot's world representation. We confirm the efficiency and accuracy of the proposed system in a set of experiments.},
author = {Ullrich, Christian and Deitsch, Sergiu and Gallwitz, Florian},
booktitle = {15th International Conference on Innovations for Community Services (I4CS)},
date = {2015-07-08/2015-07-10},
doi = {10.1109/I4CS.2015.7294493},
faupublication = {no},
isbn = {978-1-4673-7327-2},
keywords = {Cameras;Collision avoidance;Computer architecture;Legged locomotion;Navigation;GRK-1773},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.ahybri},
pages = {1-6},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{A} {Hybrid} {Approach} for {Simultaneous} {Obstacle} {Avoidance} and {Stabilization} of {Dynamic} {Bipedal} {Walking} using the {Aldebaran} {Nao} {Robot}},
venue = {Nuremberg, Germany},
year = {2015}
}
@inproceedings{faucris.203716571,
abstract = {Detection of lesions is an essential part of making a diagnosis in mammography and therefore is a main focus in the development of algorithms built for image quality assessment. We propose a hybrid approach with an accurate lesion projection model and embedding of lesions into clinical images that already contain relevant structures of anatomical noise. Using an algebraic lesion model, lesions with different sizes and contrasts are generated. The projection algorithm incorporates the modeling of blur effects due to system movement and the physical extent of the anode. Signal and background patches are extracted and used to evaluate channelized Hotelling observers with Laguerre-Gauss channels and with Gabor channels. A four-alternative forced-choice study with five medical imaging experts is performed and the inter-reader agreement with and without the model observers is determined by using Fleiss' kappa. Analyzing three different sizes for tiny, dense lesions and four density levels for larger mass-like lesions we find a good detection rate of the tiny lesions for both human as well as model observers. The inter-reader agreement using the common interpretation of Fleiss' kappa is substantial or better. Comparing full-field digital mammography and digital breast tomosynthesis w.r.t. the different mass densities we find that human readers and model observers perform well on the DBT data and the detection rate drops with lesion contrast as expected. The inter-reader agreement here is fair for the lowest contrast and substantial for the denser cases. Both human readers and model observers show difficulty in detecting the low contrast lesions in FFDM images. The inter-reader agreement is rather poor among all readers. Overall, the results indicate a good agreement between human observers and model observers and a distinctive benefit of 3-D reconstruction over FFDMs for low contrast lesions.},
author = {Schebesch, Frank and Magdalena, Herbst and Mertelmeier, Thomas and Maier, Andreas and Ritschl, Ludwig},
booktitle = {Proc. of SPIE},
date = {2018-07-08/2018-07-11},
doi = {10.1117/12.2318452},
faupublication = {yes},
isbn = {9781510620070},
keywords = {model observer; digital breast tomosynthesis; mammography; image quality; lesion detection},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.ahybri{\_}2},
pages = {107180Z},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{A} {Hybrid} {Approach} for {Virtual} {Clinical} {Trials} for {Mammographic} {Imaging}},
venue = {Atlanta, GA, USA},
volume = {10718},
year = {2018}
}
@book{faucris.311098410,
abstract = {Artificial intelligence has the potential to fundamentally transform medicine. Even as of today, AI programs show that they can outperform doctors in the evaluation of medical imaging data. Sensor-based monitoring in combination with self-learning algorithms shifts the focus increasingly from the clinic to the home environment, from therapy to prevention. The systematic analysis of structured information using data mining methods provides new insights into the causes of diseases and the success of medical interventions and therapies. The key will be how information is integrated in the future and how the individual retains sovereignty over his or her data.},
author = {Hornegger, Joachim},
doi = {10.1007/978-3-658-40232-7{\_}33},
faupublication = {yes},
isbn = {9783658402327},
month = {Jan},
note = {CRIS-Team Scopus Importer:2023-09-29},
peerreviewed = {unknown},
publisher = {Springer Fachmedien Wiesbaden},
title = {{AI} {Makes} {Medicine} {More} {Efficient}, {Individual} and {Preventive}},
year = {2023}
}
@inproceedings{faucris.111339184,
abstract = {In radiation therapy, tumor tracking allows to adjust the beam
such that it follows the respiration-induced tumor motion.
However, most clinical approaches rely on implanted fiducial
markers to locate the tumor and, thus, only provide sparse
information. Motion models have been investigated to estimate dense internal displacement fields from an external
surrogate signal, such as range imaging. With increasing
surrogate complexity, we propose a respiratory motion estimation framework based on kernel ridge regression to cope
with high-dimensional domains. This approach was validated
on five patient datasets, consisting of a planning 4DCT and a
follow-up 4DCT for each patient. Mean residual error was at
best 2.73 ± 0.25 mm, but varied greatly between patients.
We introduce a novel, large-scale dataset for microscopy cell annotations. The dataset includes 32 whole slide images (WSI) of canine cutaneous mast cell tumors, selected to include both low grade cases as well as high grade cases. The slides have been completely annotated for mitotic figures and we provide secondary annotations for neoplastic mast cells, inflammatory granulocytes, and mitotic figure look-alikes. Additionally to a blinded two-expert manual annotation with consensus, we provide an algorithm-aided dataset, where potentially missed mitotic figures were detected by a deep neural network and subsequently assessed by two human experts. We included 262,481 annotations in
total, out of which 44,880 represent mitotic figures. For algorithmic validation, we used a customized RetinaNet approach, followed by a cell classification network. We find F1-Scores of 0.786 and 0.820 for the manually labelled and the algorithm-aided dataset, respectively. The dataset provides, for the first time, WSIs completely annotated for mitotic figures and thus enables assessment of mitosis detection algorithms on complete WSIs as well as region of interest detection algorithms.
},
author = {Bertram, Christof A. and Aubreville, Marc and Marzahl, Christian and Maier, Andreas and Klopfleisch, Robert},
doi = {10.1038/s41597-019-0290-4},
faupublication = {yes},
journal = {Scientific Data},
keywords = {mitotic figure detection; tumor grading; digital pathology},
pages = {1-9},
peerreviewed = {Yes},
title = {{A} large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor},
url = {https://www.nature.com/articles/s41597-019-0290-4.pdf},
volume = {6},
year = {2019}
}
@article{faucris.213040285,
abstract = {PurposeBenefiting from multi-energy x-ray imaging technology, material decomposition facilitates the characterization of different materials in x-ray imaging. However, the performance of material decomposition is limited by the accuracy of the decomposition model. Due to the presence of nonideal effects in x-ray imaging systems, it is difficult to explicitly build the imaging system models for material decomposition. As an alternative, this paper explores the feasibility of using machine learning approaches for material decomposition tasks.},
author = {Lu, Yanye and Kowarschik, Markus and Huang, Xiaolin and Xia, Yan and Choi, Jang-Hwan and Chen, Shuqing and Hu, Shiyang and Ren, Qiushi and Fahrig, Rebecca and Hornegger, Joachim and Maier, Andreas},
doi = {10.1002/mp.13317},
faupublication = {yes},
journal = {Medical Physics},
note = {CRIS-Team WoS Importer:2019-03-12},
pages = {689-703},
peerreviewed = {Yes},
title = {{A} learning-based material decomposition pipeline for multi-energy x-ray imaging},
volume = {46},
year = {2019}
}
@inproceedings{faucris.110275044,
abstract = {In this paper we propose an algebraic full multigrid algorithm for ef- ficient and robust numerical solution of arbitrary linear systems of equations arising in image reconstruction from projections in computerized tomography. Numerical experiments and comparisons with the classical Kaczmarz algebraic reconstruction technique are presented.},
address = {Bukarest},
author = {Köstler, Harald and Popa, Constantin and Prümmer, Marcus and Rüde, Ulrich},
booktitle = {Series on Mathematical Modelling of Environmental and Life Sciences, Proceedings of the fifth workshop, September, 2006, Constanta, Romania},
date = {2006-09-10/2006-09-13},
editor = {Stelian I, Marinoschi G, Popa C},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2008.tech.IMMD.lsinfs.algebr},
pages = {123-130},
peerreviewed = {unknown},
publisher = {Editura Academiei Romane},
title = {{Algebraic} {Full} {Multigrid} in {Image} {Reconstruction}},
url = {https://www10.cs.fau.de/publications/papers/2008/KoestlPopaPruemmRuede08.pdf},
venue = {Constanta, Romania},
year = {2008}
}
@inproceedings{faucris.238078313,
author = {Dalsaß, Manuel and Deitsch, Sergiu and Moerman, Daniil and Gallwitz, Florian and Brabec, Christoph},
booktitle = {32. Symposium Photovoltaische Solarenergie},
date = {2017-03-07/2017-03-10},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Algorithmus} zur {IR}-{Panoramabilderstellung} aus {IR}-{Luftaufnahmen} von {PV}-{Freiflächenanlagen}},
venue = {Bad Staffelstein},
year = {2017}
}
@inproceedings{faucris.121426184,
author = {Stürmer, Michael and Seiler, Claude and Becker, Guido and Hornegger, Joachim},
booktitle = {ISB2011 Brussels, Conference book Program & Abstracts},
date = {2011-07-03},
editor = {Serge Van Sint Jan, Veronique Feipel, Dirk Aerenhouts, Jean-Pierre Baeyenes, Alain Carpentier, Erik Cattrysse, Jan-Pieter Clarys, Jacques Duchateau, Nathalie Guissard, Thierry Leloup, Steven Provyn, Marcel Rooze, Aldo Scafoglieri, Frederic Schuind, Peter Van Roy, Nadine Warzee},
faupublication = {yes},
pages = {205.0},
peerreviewed = {unknown},
title = {{Alignment} of multiple {Time}-of-{Flight} {3D} {Cameras} for {Reconstruction} of walking feet},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Stuermer11-AOM.pdf},
venue = {Brussels},
year = {2011}
}
@inproceedings{faucris.107896184,
address = {Berlin},
author = {Weber, Stefan and Schüle, Thomas and Schnörr, Christoph and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2003},
doi = {10.1007/978-3-642-18993-7{\_}9},
editor = {Wittenberg Thomas, Hastreiter Peter, Handels Heinz, Horsch A., Meinzer H.-P.},
faupublication = {yes},
pages = {41-45},
peerreviewed = {unknown},
publisher = {Springer},
title = {{A} linear programming approach to limited angle 3d reconstruction from dsa- projections},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Weber03-ALPA.pdf},
venue = {Berlin},
year = {2003}
}
@article{faucris.120208484,
abstract = {Objectives: We investigate the feasibility of binary-valued 3D tomographic reconstruction using only a small number of projections acquired over a limited range of angles. Methods: Regularization of this strongly ill-posed problem is achieved by (i) confining the reconstruction to binary vessel/non-vessel decisions, and (ii) by minimizing a global functional involving a smoothness prior. Results: Our approach successfully reconstructs volumetric vessel structures from three projections taken within 90°. The percentage of reconstructed voxels differing from ground truth is below 1%. Conclusion: We demonstrate that for particular applications - like Digital Subtraction Angiography - 3D reconstructions are possible where conventional methods must fail, due to a severely limited imaging geometry. This could play an important role for dose reduction and 3D reconstruction using non-conventional technical setups.},
author = {Weber, Stefan and Schüle, Thomas and Schnörr, Christoph and Hornegger, Joachim},
doi = {10.1267/METH04040320},
faupublication = {yes},
journal = {Methods of Information in Medicine},
note = {UnivIS-Import:2015-03-09:Pub.2004.tech.IMMD.IMMD5.alinea},
pages = {320-326},
peerreviewed = {Yes},
title = {{A} linear programming approach to limited angle {3D} recostruction from {DSA} projections},
volume = {43},
year = {2004}
}
@inproceedings{faucris.108045784,
author = {Weber, Stefan and Schnörr, Christoph and Hornegger, Joachim},
booktitle = {Proc. of 9th International Workshop on Combinatorial Image Analysis},
editor = {A. Kuba, A. Del Lungo, V. Di Gesu},
faupublication = {yes},
pages = {1-15},
peerreviewed = {unknown},
title = {{A} linear programming relaxation for binary tomography with smoothness priors},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Weber03-ALPR.pdf},
venue = {Palermo},
year = {2003}
}
@misc{faucris.117645484,
author = {Weber, Stefan and Schnörr, Christoph and Hornegger, Joachim},
faupublication = {yes},
note = {UnivIS-Import:2016-06-30:Pub.2002.tech.IMMD.IMMD5.alinea},
peerreviewed = {automatic},
title = {{A} linear programming relaxation for binary tomography with smoothness priors},
year = {2002}
}
@inproceedings{faucris.284134860,
abstract = {Cross-lingual approaches are growing in popularity in the machine learning domain, where large amounts of data are required to obtain better generalizations. Moreover, one of the biggest problems is the availability of clinical speech data, where most of the resources are in English. For instance, not many available Alzheimer's Disease (AD) corpora in different languages can be found in the literature. Despite the phonological and phonemic differences between Spanish and English, fortunately, there are also similarities between these two languages, e.g., around 40% of all words in English have a related word in Spanish. In this work, we want to investigate the feasibility of combining information from English and Spanish languages to discriminate AD. Two datasets were considered: part of the Pitt Corpus, which is composed of English speakers, and a Spanish AD dataset composed of speakers from Chile. We based our analysis on known acoustic (Wav2Vec) and word (BERT, RoBERTa) embeddings using different classifiers. Strong language dependencies were found, even using multilingual representations. We observed that linguistic information was more important for classifying English AD (F-Score=0.76) and acoustic for Spanish AD (F-Score=0.80). Using knowledge transferred from English to Spanish achieved F-scores of up to 0.85 for discriminating AD.},
author = {Pérez Toro, Paula Andrea and Klumpp, Philipp and Hernandez, Abner and Arias Vergara, Tomás and Lillo, P. and Slachevsky, A. and García, A. M. and Schuster, M. and Maier, Andreas and Nöth, Elmar and Orozco Arroyave, Juan Rafael},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2022-09-18/2022-09-22},
doi = {10.21437/Interspeech.2022-10883},
faupublication = {yes},
keywords = {Acoustic Embeddings; Alzheimer's Disease; Cross-Lingual Analysis; Linguistic Embeddings},
note = {CRIS-Team Scopus Importer:2022-10-28},
pages = {2483-2487},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{Alzheimer}'s {Detection} from {English} to {Spanish} {Using} {Acoustic} and {Linguistic} {Embeddings}},
venue = {Incheon},
volume = {2022-September},
year = {2022}
}
@article{faucris.256883785,
abstract = {Patients with Parkinson's disease (PD) have distinctive voice patterns, often perceived as expressing sad emotion. While this characteristic of Parkinsonian speech has been supported through the perspective of listeners, where both PD and healthy control (HC) subjects repeat the same speaking tasks, it has never been explored through a machine learning modelling approach. Our work provides an objective evaluation of this characteristic of the PD speech, by building a transfer learning system to assess how the PD pathology affects the sadness perception. To do so we introduce a Mixture-of-Experts (MoE) architecture for speech emotion recognition designed to be transferable across datasets. Firstly, by relying on publicly available emotional speech corpora, we train the MoE model and then we use it to quantify perceived sadness in never seen before PD and matched HC speech recordings. To build our models (experts), we extracted spectral features of the voicing parts of speech and we trained a gradient boosting decision trees model in each corpus to predict happiness vs. sadness. MoE predictions are created by weighting each expert's prediction according to the distance between the new sample and the expert-specific training samples. The MoE approach systematically infers more negative emotional characteristics in PD speech than in HC. Crucially, these judgments are related to the disease severity and the severity of speech impairment in the PD patients: the more impairment, the more likely the speech is to be judged as sad. Our findings pave the way towards a better understanding of the characteristics of PD speech and show how publicly available datasets can be used to train models that provide interesting insights on clinical data.},
author = {Sechidis, Konstantinos and Fusaroli, Riccardo and Orozco Arroyave, Juan Rafael and Wolf, Detlef and Zhang, Yan Ping},
doi = {10.1016/j.artmed.2021.102061},
faupublication = {yes},
journal = {Artificial Intelligence in Medicine},
keywords = {Machine learning; Mixture-of-experts; Parkinson's disease; Speech emotion recognition},
note = {CRIS-Team Scopus Importer:2021-04-30},
peerreviewed = {Yes},
title = {{A} machine learning perspective on the emotional content of {Parkinsonian} speech},
volume = {115},
year = {2021}
}
@inproceedings{faucris.108215624,
address = {Berlin Heidelberg},
author = {Wu, Hao and Berger, Martin and Maier, Andreas and Lohmann, Daniel},
booktitle = {Bildverarbeitung für die Medizin},
faupublication = {yes},
isbn = {978-3-662-49465-3},
keywords = {GRK-1773},
note = {UnivIS-Import:2016-06-01:Pub.2016.tech.IMMD.IMMD5.amemor},
pages = {206-211},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{A} {Memory} {Management} {Library} for {CT}-{Reconstruction} on {GPUs}},
venue = {Berlin},
year = {2016}
}
@inproceedings{faucris.121390544,
address = {Brighton, England},
author = {Maier, Andreas and Wenhardt, Stefan and Haderlein, Tino and Schuster, Maria and Nöth, Elmar},
booktitle = {Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech 2009)},
date = {2009-09-06/2009-09-10},
editor = {Moore Roger},
faupublication = {yes},
pages = {951-954},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{A} {Microphone}-independent {Visualization} {Technique} for {Speech} {Disorders}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Maier09-AMV.pdf},
venue = {Brighton},
year = {2009}
}
@inproceedings{faucris.255841896,
abstract = {In interventional angiography, kinematic simulation of robotic system prototypes in early development phases facilitates the detection of design errors. In this work, a game engine visualization with output is developed for such a robotic simulation. The goal of this is a better perception of the prototype by more realistic visualization. The achieved realism is evaluated in a user study. Additionally, the inclusion of real rooms� walls into the simulation�s collision model is tested and evaluated, to verify smartglasses as a tool for interactive room planning. The walls are reconstructed from point clouds using a mean shift segmentation and RANSAC. Afterwards, the obtained wall estimates are ordered using a simple neighborhood graph.},
author = {Leipert, Martin and Sadowski, Jenny and Kießling, Michèle and Ngandeu, Emeric Kwemou and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}49},
editor = {Thomas Tolxdorff, Klaus H. Maier-Hein, Andreas Maier, Heinz Handels, Christoph Palm, Thomas M. Deserno},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2021-04-20},
pages = {219-224},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{A} {Mixed} {Reality} {Simulation} for {Robotic} {Systems}},
venue = {Lübeck},
year = {2019}
}
@article{faucris.121148544,
author = {Fieselmann, Andreas and Dennerlein, Frank and Deuerling-Zheng, Yu and Boese, Jan and Fahrig, Rebecca and Hornegger, Joachim},
doi = {10.1088/0031-9155/56/12/016},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {3701-3717},
peerreviewed = {Yes},
title = {{A} model for filtered backprojection reconstruction artifacts due to time-varying attenuation values in perfusion {C}-arm {CT}},
volume = {56},
year = {2011}
}
@inproceedings{faucris.120327284,
address = {-},
author = {Nöth, Elmar and Batliner, Anton and Buckow, Jan-Constantin and Huber, Richard and Warnke, Volker and Niemann, Heinrich},
booktitle = {Proc. of the Workshop on Multi-Lingual Speech Communication},
editor = {-},
faupublication = {yes},
pages = {110-115},
publisher = {-},
title = {{A} {Multilingual} {Prosody} {Module} in a {Speech}-to-{Speech} {Translation} {System}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2000/Noeth00-AMP.pdf},
venue = {Kyoto},
year = {2000}
}
@article{faucris.110846384,
abstract = {The capsule endoscope is a state-of-the-art tool to detect abnormal problems of the small intestines, such as chyme blockage, suspected blood indicator (SBI), and white spots (ulcer). However, each examination using a capsule endoscope produces several tens of thousands images, and it is time-consuming for a physician to examine all the images. This paper proposes an automatic recognition system to identify suspected capsule endoscope images to save image viewing time. The system is basically a four-stage classifier. The first stage uses the hue, saturation, and intensity (HSI) color model to find the images with large yellow-green abnormal areas (could be chyme-blocked). For those not selected in the first stage, the second stage uses fuzzy c-means clustering analysis to further recognize the images with large abnormal areas (could be SBI). Most of the images encountered at the third stage have either large normal and uniform areas, or small abnormal areas. Thus, this stage attempts to exclude uniform images which are likely to be normal. Finally, the last stage uses a back-propagation neural network to detect the images with small abnormal areas (could be white spots). Experimental results showed that this cascaded classification system could perform much better than its individual stages or some combinations of the stages. The overall recognition accuracy is about 89%, resulting in unavoidable misclassified images. However, the detection sensitivity for abnormal images by the system was as high as 97.7%. Furthermore, since abnormality of the small intestines usually appears in a group of consecutive images, it would be overlooked only when every abnormal image in the group was misclassified. Thus, as an abnormality screening tool for physicians, the proposed system is valuable.},
author = {Miaou, Shaou-Gang and Chang, Feng-Ling and Timotius, Ivanna and Huang, Han-Chang and Su, Jenn-Lung and Liao, Rung-Sheng and Lin, Tah-Yeong},
faupublication = {no},
journal = {Journal of Medical and Biological Engineering},
keywords = {Automatic image recognition; Suspected blood indicator; capsule endoscope; chyme-blockage; multistage recognition; white spots on small intestines},
pages = {114 - 121},
peerreviewed = {Yes},
title = {{A} {Multi}-{Stage} {Recognition} {System} to {Detect} {Different} {Types} of {Abnormality} in {Capsule} {Endoscope} {Images}},
url = {http://jmbe.bme.ncku.edu.tw/index.php?action=archives2&no=363},
volume = {29},
year = {2009}
}
@inproceedings{faucris.224604955,
abstract = {Early detection and segmentation of skin lesions is crucial for timely diagnosis and treatment, necessary to improve the survival rate of patients. However, manual delineation is time consuming and subject to intra- and inter-observer variations among dermatologists. This underlines the need for an accurate and automatic approach to skin lesion segmentation. To tackle this issue, we propose a multi-task convolutional neural network (CNN) based, joint detection and segmentation framework, designed to initially localize the lesion and subsequently, segment it. A ‘Faster region-based convolutional neural network’ (Faster-RCNN) which comprises a region proposal network (RPN), is used to generate bounding boxes/region proposals, for lesion localization in each image. The proposed regions are subsequently refined using a softmax classifier and a bounding-box regressor. The refined bounding boxes are finally cropped and segmented using ‘SkinNet’, a modified version of U-Net. We trained and evaluated the performance of our network, using the ISBI 2017 challenge and the PH2 datasets, and compared it with the state-of-the-art, using the official test data released as part of the challenge for the former. Our approach outperformed others in terms of Dice coefficients (>0.93), Jaccard index (>0.88), accuracy (>0.96) and sensitivity (>0.95), across five-fold cross validation experiments.},
author = {Vesal, Sulaiman and Patil, Shreyas Malakarjun and Ravikumar, Nishant and Maier, Andreas},
booktitle = {OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis},
date = {2018-09-16/2018-09-20},
doi = {10.1007/978-3-030-01201-4{\_}31},
faupublication = {yes},
isbn = {978-3-030-01201-4},
note = {UnivIS-Import:2019-08-15:Pub.2018.tech.IMMD.IMMD5.amulti{\_}3},
pages = {285-293},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{A} {Multi}-task {Framework} for {Skin} {Lesion} {Detection} and {Segmentation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Vesal18-AMF.pdf},
venue = {Granada, Spain},
volume = {11041 LNCS},
year = {2018}
}
@inproceedings{faucris.206780007,
author = {Vasquez Correa, Juan and Arias Vergara, Tomás and Orozco-Arroyave, J. R. and Nöth, Elmar},
booktitle = {Proceedings of INTERSPEECH},
doi = {10.21437/Interspeech.2018-1988},
faupublication = {yes},
pages = {456-460},
peerreviewed = {unknown},
title = {{A} {Multitask} {Learning} {Approach} to {Assess} the {Dysarthria} {Severity} in {Patients} with {Parkinson}'s {Disease}},
url = {https://www.isca-speech.org/archive/Interspeech{\_}2018/abstracts/1988.html},
year = {2018}
}
@inproceedings{faucris.107969664,
address = {Heidelberg},
author = {Schuldhaus, Dominik and Dorn, Sabrina and Leutheuser, Heike and Tallner, Alexander and Klucken, Jochen and Eskofier, Björn},
booktitle = {The 15th International Conference on Biomedical Engineering},
date = {2013-12-04/2013-12-07},
editor = {Goh James},
faupublication = {yes},
pages = {124-127},
peerreviewed = {Yes},
publisher = {Springer},
title = {{An} {Adaptable} {Inertial} {Sensor} {Fusion}-{Based} {Approach} for {Energy} {Expenditure} {Estimation}.},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Schuldhaus14-AAI.pdf},
venue = {University Town, Singapore},
year = {2013}
}
@article{faucris.262685534,
abstract = {Introduction Automatic assessment of speech impairment is a cutting edge topic in Parkinson's disease (PD). Language disorders are known to occur several years earlier than typical motor symptoms, thus speech analysis may contribute to the early diagnosis of the disease. Moreover, the remote monitoring of dysphonia could allow achieving an effective follow-up of PD clinical condition, possibly performed in the home environment. Methods In this work, we performed a multi-level analysis, progressively combining features extracted from the entire signal, the voiced segments, and the on-set/off-set regions, leading to a total number of 126 features. Furthermore, we compared the performance of early and late feature fusion schemes, aiming to identify the best model configuration and taking advantage of having 25 isolated words pronounced by each subject. We employed data from the PC-GITA database (50 healthy controls and 50 PD patients) for validation and testing. Results We implemented an optimized k-Nearest Neighbours model for the binary classification of PD patients versus healthy controls. We achieved an accuracy of 99.4% in 10-fold cross-validation and 94.3% in testing on the PC-GITA database (average value of male and female subjects). Conclusion The promising performance yielded by our model confirms the feasibility of automatic assessment of PD using voice recordings. Moreover, a post-hoc analysis of the most relevant features discloses the option of voice processing using a simple smartphone application.},
author = {Orozco Arroyave, Juan Rafael and Amato, Federica and Borzi, Luigi and Olmo, Gabriella},
doi = {10.1007/s13755-021-00162-8},
faupublication = {yes},
journal = {Health Information Science and Systems},
note = {CRIS-Team WoS Importer:2021-08-13},
peerreviewed = {Yes},
title = {{An} algorithm for {Parkinson}'s disease speech classification based on isolated words analysis},
volume = {9},
year = {2021}
}
@inproceedings{faucris.109689624,
abstract = {Flat-Panel C-arm Computed Tomography (CT) suffers from pixel saturation due to the detector’s limited dynamic range. We describe a novel approach to analog, non-linear tone mapping (TM) for preventing detector saturation. An analog TM operator (TMO) applies a non-linear transformation in a CMOS sensor and its inverse TMO based on 14-bit digital raw data. This is done in order to prevent overexposure and to enhance image quality to 32 bits. The method was applied to the cases of low-contrast head imaging and to that of imaging both knees. Cone-beam projection data with and without overexposure was simulated for a 200° short-scan of the knees and a 360° full-scan of a Forbild head phantom. The results show an increased correlation coefficient of 0.99 compared to 0.96 for overexposed knee data and a higher low-contrast visibility (CC=0.99) compared to linear quantization (CC=0.97},
author = {Shi, Lan and Berger, Martin and Bier, Bastian and Söll, Christopher and Röber, Jürgen and Fahrig, Rebecca and Eskofier, Björn and Maier, Andreas and Maier, Jennifer},
booktitle = {IEEE Medical Imaging Conference (MIC)},
faupublication = {yes},
keywords = {GRK-1773},
note = {elib2cris::1512001600,shi2016a},
peerreviewed = {Yes},
title = {{Analog} {Non}-{Linear} {Transformation}-{Based} {Tone} {Mapping} for {Image} {Enhancement} in {C}-arm {CT}},
venue = {Strasbourg, France},
year = {2016}
}
@misc{faucris.232144217,
abstract = {Der Marktanteil elektronischer Bucher (E-Books) am Buchmarkt wächst beständig. Um E-Books zu rezipieren, benötigt man spezielle Leseumgebungen, die als Software (im Browser oder als eigene Anwendung) oder als Spezialgerät (E-Reader) realisiert sein können. Diese Leseumgebungen sind geeignet, Daten über das Leseverhalten zu sammeln. Im Rahmen einer universitären Lehrveranstaltung wurden die Software-Leseumgebungen der beiden deutschen Marktführer Kindle und Tolino untersucht. Der vorliegende Bericht fasst die Ergebnisse dieser Analysen zusammen. Das Ergebnis ist eine umfassende Bestandsaufnahme der digitalen Spuren, die durch die Benutzung der Programme entstehen. Betrachtet wurden die zum Untersuchungszeitpunkt aktuellen Versionen der jeweiligen Webanwendungen und Android-Apps sowie des Kindle-Windows-Clients. Die Ergebnisse entstanden im Rahmen einer Übung zur Vorlesung "Fortgeschrittene forensische Informatik II" im Wintersemester 2018/19 an der Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), die gemeinsam durchgeführt wurde vom Lehrstuhl fur Informatik 1 und dem Institut für Buchwissenschaft an der FAU.},
author = {Benenson, Zinaida and Berger, Frederik and Cherepantsev, Anatoliy and Datsevich, Sergey and Do, Long and Eckert, Moritz and Elsberger, Tassilo and Freiling, Felix and Frinken, Marius and Glameyer, Hendrik and Hafner, Steffen and Hagenhoff, Svenja and Hammer, Andreas and Hammerl, Stefan and Hantke, Florian and Heindorf, Felix and Henninger, Marcel and Höfer, Daniel and Kuhrt, Phillip and Lattka, Maximilian and Leis, Tobias and Leubner, Christian and Leyrer, Katharina and Lindenmeier, Christian and Del Medico, Katharina and Moussa, Denise and Nissen, Michael and Öz, Alina and Ottmann, Jenny and Reif, Katharina and Ripley, Nora and Roth, Armin and Schilling, Joshua and Schleicher, Robert and Schulz, David and Stephan, Milan and Volkert, Christoph and Wehner, Max and Wild, Matthias and Wirth, Johannes and Wolf, Julian and Wunder, Julia and Zlatanovic, Jovana},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Analyse} verbreiteter {Anwendungen} zum {Lesen} von elektronischen {Büchern}},
url = {http://nbn-resolving.de/urn:nbn:de:bvb:29-opus4-125519},
year = {2019}
}
@article{faucris.215005397,
author = {Rios-Urrego, Cristian David and Vargas-Bonilla, Francisco and Nöth, Elmar and Lopera, Francisco and Orozco Arroyave, Juan Rafael},
doi = {10.1016/j.cmpb.2019.03.005},
faupublication = {yes},
journal = {Computer Methods and Programs in Biomedicine},
pages = {43-52},
peerreviewed = {Yes},
title = {{Analysis} and evaluation of handwriting in patients with {Parkinson}’s disease using kinematic, geometrical, and non-linear features},
url = {https://www.sciencedirect.com/science/article/pii/S0169260719300574},
volume = {173},
year = {2019}
}
@article{faucris.252090597,
abstract = {Automatic sleep stage scoring based on deep neural networks has come into focus of sleep researchers and physicians, as a reliable method able to objectively classify sleep stages would save human resources and simplify clinical routines. Due to novel open-source software libraries for machine learning, in combination with enormous recent progress in hardware development, a paradigm shift in the field of sleep research towards automatic diagnostics might be imminent. We argue that modern machine learning techniques are not just a tool to perform automatic sleep stage classification, but are also a creative approach to find hidden properties of sleep physiology. We have already developed and established algorithms to visualize and cluster EEG data, facilitating first assessments on sleep health in terms of sleep-apnea and consequently reduced daytime vigilance. In the following study, we further analyze cortical activity during sleep by determining the probabilities of momentary sleep stages, represented as hypnodensity graphs and then computing vectorial cross-correlations of different EEG channels. We can show that this measure serves to estimate the period length of sleep cycles and thus can help to find disturbances due to pathological conditions.},
author = {Krauß, Patrick and Metzner, Claus and Joshi, Nidhi and Schulze, Holger and Traxdorf, Maximilian and Maier, Andreas and Schilling, Achim},
doi = {10.1016/j.nbscr.2021.100064},
faupublication = {yes},
journal = {Neurobiology of Sleep and Circadian Rhythms},
keywords = {Artificial neural networks; Deep learning; Electroencephalography (EEG); Hypnodensity graphs; Multidimensional scaling (MDS); Polysomnography (PSG); Sleep cycle analysis; Sleep stage scoring},
note = {CRIS-Team Scopus Importer:2021-03-19},
peerreviewed = {Yes},
title = {{Analysis} and visualization of sleep stages based on deep neural networks},
volume = {10},
year = {2021}
}
@inproceedings{faucris.229373610,
abstract = {Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate. However, such models suffer from a very slow signal generation mechanism due to their sample-by-sample modelling approach. In this work, we introduce a new methodology for neural speech vocoding based on generative adversarial networks (GANs). A fake speech signal is generated from a very compressed representation of the glottal excitation using conditional GANs as a deep generative model. This fake speech is then refined using the LPC parameters of the original speech signal to obtain a natural reconstruction. The reconstructed speech waveforms based on this approach show a higher perceptual quality than the classical vocoder counterparts according to subjective and objective evaluation scores for a dataset of 30 male and female speakers. Moreover, the usage of GANs enables to generate signals in one-shot compared to autoregressive generative models. This makes GANs promising for exploration to implement high-quality neural vocoders.},
author = {Mustafa, Ahmed and Biswas, Arijit and Bergler, Christian and Schottenhamml, Julia and Maier, Andreas},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2019-09-15/2019-09-19},
doi = {10.21437/Interspeech.2019-1195},
editor = {Gernot Kubin, Thomas Hain, Bjorn Schuller, Dina El Zarka, Petra Hodl},
faupublication = {yes},
keywords = {Deep learning; Generative adversarial networks; Neural vocoder; Speech coding},
note = {CRIS-Team Scopus Importer:2019-11-19},
pages = {191-195},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{Analysis} by adversarial synthesis - {A} novel approach for speech vocoding},
venue = {Graz, AUT},
volume = {2019-September},
year = {2019}
}
@inproceedings{faucris.121338404,
author = {Schmitt, Katharina and Schöndube, Harald and Stierstorfer, Karl and Hornegger, Joachim and Noo, Frédéric},
booktitle = {Proceedings of the second international conference on image formation in x-ray computed tomography},
date = {2012-06-24/2012-06-27},
editor = {Noo Frédéric},
faupublication = {yes},
pages = {288-292},
peerreviewed = {unknown},
title = {{Analysis} of bias induced by various forward projection models in iterative reconstruction},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Schmitt12-AOB.pdf},
venue = {Salt Lake City, UT},
year = {2012}
}
@article{faucris.287251686,
abstract = {Objective: Alterations in the neuromuscular coordination of swallowing are known as dysphagia, which can produce malnutrition, dehydration and aspiration pneumonia. Its instrumental diagnosis is invasive and expertise dependent. Thus, we introduced a non-invasive multimodal approach for dysphagia screening using surface electromyography (sEMG) and accelerometry-based cervical auscultation (Acc). Methods: Thirty healthy individuals and 30 patients with functional oropharyngeal dysphagia were recruited. Swallowing tasks of saliva and 5, 10, and 20 mL of yogurt and water were performed. Supra- and infrahyoid sEMG and tri-axial Acc signals were recorded. Linear and non-linear features were extracted and selected. Two unimodal and one multimodal classification scenarios were tested. Classical algorithms were applied and the Area Under the ROC curve (AUC) was the criterion for hyperparameters optimization. Results: The Acc related features were the most consistently selected. Although the classification results with Acc signals were higher than with sEMG, the signal fusion improved the unimodal results regardless of swallowing task (AUC > 0.82). The highest classification results were achieved with small volumes of water (AUC = 0.86 ± 0.15) and yogurt (AUC = 0.87 ± 0.12). Conclusion: The combination of non-invasive sEMG and Acc signals improves the performance of automatic classification models for dysphagia detection. Significance: This paper proposes a multimodal approach based on electrophysiological and mechanical swallowing dimensions, for automatic, non-invasive and quantitative dysphagia screening.},
author = {Roldan-Vasco, Sebastian and Restrepo-Uribe, Juan Pablo and Orozco-Duque, Andres and Suarez-Escudero, Juan Camilo and Orozco Arroyave, Juan Rafael},
doi = {10.1016/j.bspc.2022.104533},
faupublication = {yes},
journal = {Biomedical Signal Processing and Control},
keywords = {Accelerometry; Dysphagia; Machine learning; Multiple signal classification; Surface electromyography (EMG); Swallowing},
note = {CRIS-Team Scopus Importer:2023-01-06},
peerreviewed = {Yes},
title = {{Analysis} of electrophysiological and mechanical dimensions of swallowing by non-invasive biosignals},
volume = {82},
year = {2023}
}
@article{faucris.223270884,
abstract = {In automotive manufacturing, high strength materials, and aluminum alloys are widely used to address the requirement of ensuring a lightweight car body and correspondingly, reducing pollution. In this context of complexity of materials and structures, an optimized process design with finite element analyses (FEA) is mandatory, as well as a correct definition of the material forming limits. For this purpose, in sheet metal forming, the forming limit curve (FLC) is used. The FLC is defined by the onset of necking. The standard evaluation method according to DIN EN ISO 12004-2 is based on the cross-section method and assumes that the failure occurs due to a clear localized necking. However, this approach has its limitations, specifically in the case of brittle materials that do not exhibit a distinct necking phase. To overcome this challenge, a pattern recognition-based evaluation is proposed. Although pattern recognition and machine learning techniques have been widely employed in the medical field, few studies have investigated them in the context of analyzing metal sheet forming limits. The application of pattern recognition in metal forming is subject to the exact definition of the forming behaviors. Thereby, it is challenging to relate patterns on the strain distribution during Nakajima tests with the onset of necking for the FLC determination. Thus, the first approach was based on the crack evaluation, since this class is well-defined. However, of substantial interest is the evaluation of the general material instabilities that precede failure. Therefore, in the present study, the analysis of the material behavior during stretching is conducted in order to characterize instability classes. The results of Nakajima tests are investigated using an optical measurement system. A conventional pattern recognition approach based on texture features, considering the outcomes of expert interviews for the definition of classes is used for the FLC determination. Moreover, an analysis of the validity of the supervised learning is conducted. The results show a good prediction of the onset of necking, even for high strength materials with a recall of up to 92%. Some deviations are observed in the determination of the diffuse necking. The discrepancies of the different experts' prognoses highlight the user-dependency of the FLC, suggesting further investigations with an data-driven approach, could be beneficial.},
author = {Affronti, Emanuela and Jaremenko, Christian and Merklein, Marion and Maier, Andreas},
doi = {10.3390/ma11091495},
faupublication = {yes},
journal = {Materials},
keywords = {Forming limit curve; Machine learning; Pattern recognition; Sheet metal forming},
note = {LFT Import::2019-07-29 (2319)},
peerreviewed = {Yes},
title = {{Analysis} of {Forming} {Limits} in {Sheet} {Metal} {Forming} with {Pattern} {Recognition} {Methods}. {Part} 1: {Characterization} of {Onset} of {Necking} and {Expert} {Evaluation}},
volume = {11},
year = {2018}
}
@article{faucris.223271632,
abstract = {The forming limit curve (FLC) is used in finite element analysis (FEA) for the modeling of onset of sheet metal instability during forming. The FLC is usually evaluated by achieving forming measurements with optical measurement system during Nakajima tests. Current evaluation methods such as the standard method according to DIN EN ISO 12004-2 and time-dependent methods limit the evaluation range to a fraction of the available information and show weaknesses in the context of brittle materials that do not have a pronounced constriction phase. In order to meet these challenges, a supervised pattern recognition method was proposed, whose results depend on the quality of the expert annotations. In order to alleviate this dependence on experts, this study proposes an unsupervised classification approach that does not require expert annotations and allows a probabilistic evaluation of the onset of localized necking. For this purpose, the results of the Nakajima tests are examined with an optical measuring system and evaluated using an unsupervised classification method. In order to assess the quality of the results, a comparison is made with the time-dependent method proposed by Volk and Hora, as well as expert annotations, while validated with metallographic investigations. Two evaluation methods are presented, the deterministic FLC, which provides a lower and upper limit for the onset of necking, and a probabilistic FLC, which allows definition of failure quantiles. Both methods provide a necking range that shows good correlation with the expert opinion as well as the results of the time-dependent method and metallographic examinations.},
author = {Jaremenko, Christian and Affronti, Emanuela and Maier, Andreas and Merklein, Marion},
doi = {10.3390/ma11101892},
faupublication = {yes},
journal = {Materials},
keywords = {Forming limit curve; Machine learning; Pattern recognition; Sheet metal forming},
note = {LFT Import::2019-07-29 (2327)},
pages = {1892},
peerreviewed = {Yes},
title = {{Analysis} of {Forming} {Limits} in {Sheet} {Metal} {Forming} with {Pattern} {Recognition} {Methods}. {Part} 2: {Unsupervised} {Methodology} and {Application}},
volume = {11},
year = {2018}
}
@inproceedings{faucris.121404624,
address = {Berlin},
author = {Maier, Andreas and Reuss, Alexander and Hacker, Christian and Schuster, Maria and Nöth, Elmar},
booktitle = {Text, Speech and Dialogue},
date = {2008-09-08/2008-09-12},
editor = {Sojka Petr, Horak Ales, Kopecek Ivan, Pala Karel},
faupublication = {yes},
pages = {389-396},
peerreviewed = {Yes},
publisher = {Springer},
title = {{ANALYSIS} {OF} {HYPERNASAL} {SPEECH} {IN} {CHILDREN} {WITH} {CLEFT} {LIP} {AND} {PALATE}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Maier08-AOH.pdf},
venue = {Brno},
year = {2008}
}
@book{faucris.307043936,
abstract = {This book addresses the automatic analysis of speech disorders resulting from a clinical condition (Parkinson's disease and hearing loss) or the natural aging process. For Parkinson's disease, the progression of speech symptoms is evaluated by considering speech recordings captured in the short-term (4 months) and long-term (5 years). Machine learning methods are used to perform three tasks: (1) automatic classification of patients vs. healthy speakers. (2) regression analysis to predict the dysarthria level and neurological state. (3) speaker embeddings to analyze the progression of the speech symptoms over time.For hearing loss, automatic acoustic analysis is performed to evaluate whether the duration and onset of deafness (before or after speech acquisition) influence the speech production of cochlear implant users. Additionally, articulation, prosody, and phonemic analyses show that cochlear implant users present altered speech production even after hearing rehabilitatio},
address = {Erlangen, Bayern, Germany},
author = {Arias Vergara, Tomás},
edition = {Studien zur Mustererkennung},
faupublication = {yes},
isbn = {978-3-8325-5561-0},
keywords = {Speech processing; Machine learning; Deep Learning; Speech disorders; Aging;Smartphone applications; Acoustic Features; Pathological speech; Parkinson's disease; Cochlear Implant Users; Hearing loss},
peerreviewed = {unknown},
publisher = {Logos Verlag Berlin GmbH},
series = {Studien zur Mustererkennung},
title = {{Analysis} of {Pathological} {Speech} {Signals}},
url = {https://logos-verlag.eu/cgi-bin/engbuchmid?isbn=5561&lng=eng&id=},
volume = {50},
year = {2022}
}
@book{faucris.115590684,
abstract = {Different characterization approaches, including nonlinear dynamics (NLD), have been addressed for the automatic detection of PD; however, the obtained discrimination capability when only NLD features are considered has not been evaluated yet. This paper evaluates the discrimination capability of a set with ten different NLD features in the task of automatic classification of speech signals from people with Parkinson's disease (PPD) and a control set (CS). The experiments presented in this paper are performed considering the five Spanish vowels uttered by 20 PPD and 20 people from the CS. According the results, it is possible to achieve accuracy rates of up to 76,81% considering only utterances from the vowel/i/. When features calculated from the five Spanish vowels are combined, the performance of the system is not improved, indicating that the inclusion of more NLD features to the system does not guarantee better performance. © 2013 Springer-Verlag Berlin Heidelberg.},
address = {Berlin},
author = {Orozco-Arroyave, Juan Rafael and Arias-Londoño, Julián David and Vargas-Bonilla, Jesús Francisco and Nöth, Elmar},
doi = {10.1007/978-3-642-38847-7-15},
edition = {7911},
faupublication = {yes},
isbn = {9783642388460},
keywords = {complexity measures; Nonlinear dynamics; Parkinson's disease; speech signals},
note = {UnivIS-Import:2017-12-18:Pub.2013.tech.IMMD.IMMD5.analys},
pages = {112-119},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Analysis} of {Speech} from {People} with {Parkinson}'s {Disease} through {Nonlinear} {Dynamics}},
volume = {1},
year = {2013}
}
@inproceedings{faucris.108220904,
author = {Maier, Andreas and Choi, Jang-Hwan and Keil, Andreas and Niebler, Christine and Sarmiento, Marily and Fieselmann, Andreas and Gold, Garry and Delp, Scott and Fahrig, Rebecca},
booktitle = {Proc. SPIE Vol. 7961},
date = {2011-02-13},
editor = {SPIE},
faupublication = {yes},
pages = {7961231-7961238},
peerreviewed = {Yes},
title = {{Analysis} of {Vertical} and {Horizontal} {Circular} {C}-{Arm} {Trajectories}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Maier11-AOV.pdf},
venue = {Lake Buena Vista},
year = {2011}
}
@article{faucris.120760024,
abstract = {The retinal ganglion axons are an important part of the visual system, which can be directly observed by fundus camera. The layer they form together inside the retina is the retinal nerve fiber layer (RNFL). This paper describes results of a texture RNFL analysis in color fundus photographs and compares these results with quantitative measurement of RNFL thickness obtained from optical coherence tomography on normal subjects. It is shown that local mean value, standard deviation, and Shannon entropy extracted from the green and blue channel of fundus images are correlated with corresponding RNFL thickness. The linear correlation coefficients achieved values 0.694, 0.547, and 0.512 for respective features measured on 439 retinal positions in the peripapillary area from 23 eyes of 15 different normal subjects.},
author = {Kolar, Radim and Tornow, Ralf-Peter and Lämmer, Robert and Odstrcilik, Jan and Mayer, Markus Anton and Gazarek, Jiri and Jan, Jiri and Kubena, Tomas and Cernosek, Pavel},
doi = {10.1155/2013/134543},
faupublication = {yes},
journal = {Computational and Mathematical Methods in Medicine},
note = {EVALuna2:21171},
pages = {134543},
peerreviewed = {Yes},
title = {{Analysis} of visual appearance of retinal nerve fibers in high resolution fundus images: a study on normal subjects},
volume = {2013},
year = {2013}
}
@inproceedings{faucris.110770044,
address = {-},
author = {Jesorsky, Oliver and Denzler, Joachim and Nöth, Elmar and Wittenberg, Thomas},
booktitle = {Advances in Quantitative Laryngoscopy},
date = {1997-07-18/1997-07-19},
editor = {-},
faupublication = {yes},
pages = {51-58},
peerreviewed = {No},
publisher = {-},
title = {{Analysis} of voice-onset using active rays and hidden markov models},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Jesorsky97-AOV.pdf},
venue = {Erlangen},
year = {1997}
}
@inproceedings{faucris.230327867,
abstract = {This paper presents a derivation of the optimal weight to be assigned for an item so that it maximally increases the reliability of the aggregate. This aggregate is the best estimate of the underlying true repeating pattern. The approach differs from previous solutions in being analytical, based on the Signal to Noise Ratio (SNR) instead of the reliability itself, and the ability to visually inform the researcher about the relevance of the weighting strategy and the gains produced in the SNR. Optimal weighting of repetitive phenomena is a bonus not only in the behavioral sciences, but also in many engineering fields. Its uses may include the selection or discarding of raters, judges, repetitions, or epochs, depending on the field.},
author = {Ferrer, Carlos A. and Torres-Rodríguez, Idileisy and Taboada-Crispi, Alberto and Nöth, Elmar},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2019-10-28/2019-10-31},
doi = {10.1007/978-3-030-33904-3{\_}38},
editor = {Ingela Nyström, Yanio Hernández Heredia, Vladimir Milián Núñez},
faupublication = {yes},
isbn = {9783030339036},
keywords = {Composites; Ensemble Averages; Reliability; Signal-to-Noise Ratio},
note = {CRIS-Team Scopus Importer:2019-12-10},
pages = {408-416},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Analytical} {Solution} for the {Optimal} {Addition} of an {Item} to a {Composite} of {Scores} for {Maximum} {Reliability}},
venue = {Havana},
volume = {11896 LNCS},
year = {2019}
}
@inproceedings{faucris.124015804,
author = {Haji Ghassemi, Nooshin and Deisenroth, Marc},
booktitle = {Proc. of AISTATS},
faupublication = {no},
peerreviewed = {unknown},
title = {{Analytic} long-term forecasting with periodic {Gaussian} processes},
year = {2014}
}
@inproceedings{faucris.111771484,
abstract = {In X-ray Computed Tomography (CT) the measured projections and consequently the reconstructed CT images are subject to quantum and electronics noise. While noise in the projections can be well described and estimated with a corresponding physics model, the distribution of noise in the reconstructed CT images is not directly evident. Due to attenuation variations along different directions, the nature of noise in CT images is nonstationary and directed. This complicates the direct application of standard post-processing methods like bilateral filtering. this article we describe a possibUity to compute precise orientation dePendent noise estimates for every pixel position. This is done by analytic propagation of projection noise estimates through indirect fan-beam filtered backprojection reconstruction. The resulting orientation dePendent image noise estimates are subsequently used in adaptive bUateral filters. Taking into account the non-stationary and non-isotropic nature of noise in CT images, an averag improvement in SNR of about 60% is achieved compared to linear filtering at the same resolution. ©2008 IEEE.},
author = {Borsdorf, Anja and Kappler, Steffen and Raupach, Rainer and Hornegger, Joachim},
booktitle = {2008 IEEE Nuclear Science Symposium Conference Record, NSS/MIC 2008},
doi = {10.1109/NSSMIC.2008.4774438},
faupublication = {yes},
pages = {5335-5338},
peerreviewed = {unknown},
title = {{Analytic} noise propagation for anisotropic denoising of ct images},
venue = {Dresden},
volume = {null},
year = {2008}
}
@inproceedings{faucris.121204424,
abstract = {Precise knowledge of the local image noise is an essential ingredient to efficient application of post-processing methods such as wavelet or diffusion filtering to computed tomography (CT) images. The non-stationary, object dependent nature of noise in CT images is a direct result from the noise present in the projection data. Since quantum and electronics noise are the dominating noise sources, comparably simple models can be used for direct noise estimates in the individual projections. In this article, we describe the analytic propagation of these noise estimates through fan-beam filtered backprojection (FBP) reconstruction. Contrary to earlier publications in this field, we include the correlations within the parallel projections resulting from the rebinning, the convolution, and the backprojection processes. The method has been validated against Monte-Carlo results and good accuracy with an average relative error below 3.6% was achieved for arbitrary objects and over the full range of commonly used convolution kernels and field-of-view settings.},
author = {Borsdorf, Anja and Kappler, Steffen and Raupach, Rainer and Hornegger, Joachim},
booktitle = {Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE},
date = {2008-08-20/2008-08-25},
doi = {10.1109/IEMBS.2008.4649759},
faupublication = {yes},
pages = {2701-2704},
peerreviewed = {unknown},
title = {{Analytic} noise-propagation in indirect fan-beam {FBP} reconstruction},
venue = {Vancouver, BC},
volume = {2008},
year = {2008}
}
@inproceedings{faucris.231367866,
abstract = {Comparison of microvascular circulation on fundoscopic images is a non-invasive clinical indication for the diagnosis and monitoring of diseases, such as diabetes and hypertensions. The differences between intra-patient images can be assessed quantitatively by registering serial acquisitions. Due to the variability of the images (i.e. contrast, luminosity) and the anatomical changes of the retina, the registration of fundus images remains a challenging task.
Recently, several deep learning approaches have been proposed to register fundus images in an end-to-end fashion, achieving remarkable results.However, the results are difficult to interpret and analyze. In this work, we propose an imitation learning framework for the registration of 2D color funduscopic images for a wide range of applications such as disease monitoring, image stitching and super-resolution. We follow a divide-and-conquer approach to improve the interpretability of the proposed network, and analyze both the influence of the input image and the hyperparameters on the registration result.The results show that the proposed registration network reduces the initial target registration error up to 95 %
Methods : A 1050 nm, 400 kHz swept-source (SS)-OCT system was used to perform OCTA imaging of 89 eyes from 51 diabetic patients and 63 eyes from 32 normal subjects. Of the 89 eyes from diabetic patients, 51 eyes had no clinically detected retinopathy, 29 eyes had non-proliferative diabetic retinopathy (NPDR), and 9 eyes had proliferative diabetic retinopathy (PDR). OCTA en face images of the retinal vasculature were generated. The vessel structure in each image was highlighted using a vesselness filter; next, a binary image was obtained through a marching algorithm designed to exploit continuity constraints. Finally, the ICA were determined via connected components and subsequently used to generate false color images highlighting areas of non-perfusion.
Results : Representative ICA maps for a normal eye and a NPDR eye are shown in Figure 1. The ICA maps can visualize areas of non-perfusion and enable rapid assessment of the vascular changes that occur in DR. Similar, but less pronounced changes were observed in eyes of diabetics without retinopathy.
Conclusions : A fully automatic algorithm for quantifying ICA in OCTA images was developed. Preliminary results suggest ICA may be a useful metric for assessing diabetes and DR. Further work is needed to develop quantitative measures, validate the algorithm, and evaluate robustness in the presence of OCTA image artifact},
author = {Schottenhamml, Julia and Moult, Eric M. and Ploner, Stefan and Lee, Byungkun and Lu, Chen D. and Husvogt, Lennart and Waheed, Nadia K. and Duker, Jay S. and Hornegger, Joachim and Fujimoto, James G.},
booktitle = {Investigative Ophthalmology & Visual Science},
date = {2016-05-01/2016-05-05},
edition = {12},
faupublication = {yes},
keywords = {oct;octa;oct angiography;diabetic retinopathy;intercapillary area},
note = {UnivIS-Import:2018-09-11:Pub.2016.tech.IMMD.IMMD5.anauto},
pages = {5960},
peerreviewed = {Yes},
title = {{An} automatic algorithm measuring the retinal intercapillary area to assess diabetic retinopathy},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Schottenhamml16-AAA.pdf},
venue = {Seattle, WA, USA},
volume = {57},
year = {2016}
}
@inproceedings{faucris.121376904,
author = {Tian, Mengqiu and Yang, Qiao and Maier, Andreas and Schasiepen, Ingo and Maass, Nicole and Elter, Matthias},
booktitle = {Proceedings des Workshops Bildverarbeitung für die Medizin 2013},
date = {2013-03-03},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {277-282},
peerreviewed = {Yes},
title = {{An} automatic histogram-based initializing algorithm for {K}-means clustering in {CT}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Tian13-AAH.pdf},
venue = {Heidelberg, Germany},
year = {2013}
}
@article{faucris.110062964,
abstract = {Purpose: To develop a robust, sensitive, and fully automatic algorithm to quantify diabetes-related capillary dropout using optical coherence tomography (OCT) angiography (OCTA). Methods: A 1,050-nm wavelength, 400 kHz A-scan rate swept-source optical coherence tomography prototype was used to perform volumetric optical coherence tomography angiography imaging over 3 mm × 3 mm fields in normal controls (n = 5), patients with diabetes without diabetic retinopathy (DR) (n = 7), patients with nonproliferative diabetic retinopathy (NPDR) (n = 9), and patients with proliferative diabetic retinopathy (PDR) (n = 5); for each patient, one eye was imaged. A fully automatic algorithm to quantify intercapillary areas was developed. Results: Of the 26 evaluated eyes, the segmentation was successful in 22 eyes (85%). The mean values of the 10 and 20 largest intercapillary areas, either including or excluding the foveal avascular zone, showed a consistent trend of increasing size from normal control eyes, to eyes with diabetic retinopathy but without diabetic retinopathy, to nonproliferative diabetic retinopathy eyes, and finally to PDR eyes. Conclusion: Optical coherence tomography angiography-based screening and monitoring of patients with diabetic retinopathy is critically dependent on automated vessel analysis. The algorithm presented was able to automatically extract an intercapillary areabased metric in patients having various stages of diabetic retinopathy. Intercapillary areabased approaches are likely more sensitive to early stage capillary dropout than vascular density-based method},
author = {Schottenhamml, Julia and Moult, Eric M. and Ploner, Stefan and Lee, Byungkun and Novais, Eduardo A. and Cole, Emily D. and Dang, Sabin and Lu, Chen D. and Husvogt, Lennart and Waheed, Nadia K. and Duker, Jay S. and Hornegger, Joachim and Fujimoto, James G.},
doi = {10.1097/IAE.0000000000001288},
faupublication = {yes},
journal = {Retina (Philadelphia, Pa.)},
keywords = {Capillary dropout; Diabetic retinopathy; Intercapillary area; Optical coherence tomography; Optical coherence tomography angiography},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.anauto{\_}6},
pages = {S93-S101},
peerreviewed = {Yes},
title = {{An} {Automatic}, {Intercapillary} {Area}-based {Algorithm} for {Quantifying} {Diabetes}-related {Capillary} {Dropout} {Using} {Optical} {Coherence} {Tomography} {Angiography}},
url = {https://www.ncbi.nlm.nih.gov/pubmed/28005667},
volume = {36},
year = {2016}
}
@inproceedings{faucris.311094696,
abstract = {Early detection and monitoring of Parkinson's disease are crucial for properly treating and managing the symptoms. Automatic speech and language analysis has emerged as a promising non-invasive method to monitor the patient's state. This study analyzed different speech and language representations for automatic classification between Parkinson's disease patients and healthy controls. First, each modality is analyzed independently. General representations such as Wav2vec or BETO are used together with representations oriented to model disease traits such as phonemic identifiability in speech modality and grammatical units analysis in language modality. The best speech and language representations were combined using a fusion strategy based on Gated Multimodal Units. The best results are achieved with the multimodal approach, outperforming all results obtained with unimodal representations and the traditional fusion strategy.},
author = {Escobar-Grisales, Daniel and Arias-Vergara, Tomás and Rios-Urrego, Cristian David and Nöth, Elmar and García, Adolfo M. and Orozco-Arroyave, Juan Rafael},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2023-08-20/2023-08-24},
doi = {10.21437/Interspeech.2023-2287},
faupublication = {yes},
keywords = {language analysis; multimodal; Speech analysis},
note = {CRIS-Team Scopus Importer:2023-09-29},
pages = {1703-1707},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{An} {Automatic} {Multimodal} {Approach} to {Analyze} {Linguistic} and {Acoustic} {Cues} on {Parkinson}'s {Disease} {Patients}},
venue = {Dublin, IRL},
volume = {2023-August},
year = {2023}
}
@inproceedings{faucris.108135984,
author = {Bocklet, Tobias and Winterholler, Cordula and Maier, Andreas and Schuster, Maria and Nöth, Elmar},
booktitle = {Proceedings of WOCCI 2009},
date = {2009-11-05},
editor = {WOCCI},
faupublication = {yes},
pages = {no pagination},
peerreviewed = {Yes},
title = {{An} {Automatic} {Screening} {Test} for {Preschool} {Children}: {Theory} and {Data} {Collection}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Bocklet09-AAS.pdf},
venue = {Cambridge, MA},
year = {2009}
}
@article{faucris.108129384,
author = {Maier, Andreas and Hönig, Florian Thomas and Steidl, Stefan and Nöth, Elmar and Horndasch, Stefanie and Sauerhöfer, Elisabeth and Kratz, Oliver and Moll, Gunther},
doi = {10.1145/1998384.1998391},
faupublication = {yes},
journal = {ACM Transactions on Speech and Language Processing},
pages = {17:1-17:15},
peerreviewed = {unknown},
title = {{An} automatic version of a reading disorder test},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Maier11-AAV.pdf},
volume = {7.0},
year = {2011}
}
@inproceedings{faucris.120319584,
address = {Berlin},
author = {Haderlein, Tino and Riedhammer, Korbinian Thomas and Maier, Andreas and Nöth, Elmar and Toy, Hikmet and Rosanowski, Frank},
booktitle = {Proc. Text, Speech and Dialogue; 10th International Conference},
date = {2007-09-03/2007-09-07},
editor = {Matousek Vaclav, Mautner Pavel},
faupublication = {yes},
pages = {238-245},
peerreviewed = {Yes},
publisher = {Springer},
title = {{An} {Automatic} {Version} of the {Post}-{Laryngectomy} {Telephone} {Test}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Haderlein07-AAV.pdf},
venue = {Pilsen},
year = {2007}
}
@inproceedings{faucris.226810264,
author = {Wilke, Peter},
faupublication = {yes},
peerreviewed = {unknown},
title = {{A} {Neural} {Network} {Simulation} {Environment} with {Components} for {Genetic} {Algorithms} and {Fuzzy} {Logic}},
year = {1994}
}
@article{faucris.203204383,
abstract = {A copy-move forgery is created by copying and pasting content within the same image, and potentially postprocessing it. In recent years, the detection of copy-move forgeries has become one of the most actively researched topics in blind image forensics. A considerable number of different algorithms have been proposed focusing on different types of postprocessed copies. In this paper, we aim to answer which copy-move forgery detection algorithms and processing steps (e.g., matching, filtering, outlier detection, affine transformation estimation) perform best in various postprocessing scenarios. The focus of our analysis is to evaluate the performance of previously proposed feature sets. We achieve this by casting existing algorithms in a common pipeline. In this paper, we examined the 15 most prominent feature sets. We analyzed the detection performance on a per-image basis and on a per-pixel basis. We created a challenging real-world copy-move dataset, and a software framework for systematic image manipulation. Experiments show, that the keypoint-based features SIFT and SURF, as well as the block-based DCT, DWT, KPCA, PCA and ZERNIKE features perform very well. These feature sets exhibit the best robustness against various noise sources and downsampling, while reliably identifying the copied regions.
},
author = {Christlein, Vincent and Riess, Christian and Jordan, Johannes Michael and Riess, Corinna and Angelopoulou, Elli},
doi = {10.1109/TIFS.2012.2218597},
faupublication = {yes},
journal = {IEEE Transactions on Information Forensics and Security},
keywords = {Benchmark dataset; copy-move forgery; comparative study; manipulation detection; image forensics},
pages = {1841-1854},
peerreviewed = {Yes},
title = {{An} {Evaluation} of {Popular} {Copy}-{Move} {Forgery} {Detection} {Approaches}},
url = {https://www5.cs.fau.de/research/groups/computer-vision/image-forensics/evaluation-of-copy-move-forgery-detection/},
volume = {7},
year = {2012}
}
@article{faucris.117779244,
author = {Paulus, Jan and Hornegger, Joachim and Schmidt, Michael and Eskofier, Björn and Michelson, Georg},
doi = {10.1167/13.9.1171},
faupublication = {yes},
journal = {Journal of Vision},
pages = {1171},
peerreviewed = {Yes},
title = {{An} evaluation system for stereopsis of beach volleyball players measuring perception time as a function of disparity within a virtual environment},
volume = {13},
year = {2013}
}
@article{faucris.121094424,
author = {Merklein, Marion and Maier, Andreas and Kinnstätter, Daniel and Jaremenko, Christian and Affronti, Emanuela},
faupublication = {yes},
journal = {Key Engineering Materials},
note = {UnivIS-Import:2015-04-14:Pub.2015.tech.IMMD.IMMD5.anewap},
pages = {333-338},
peerreviewed = {Yes},
title = {{A} new approach to the evaluation of forming limits in sheet metal forming},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Merklein15-ANA.pdf},
volume = {639},
year = {2015}
}
@inproceedings{faucris.121317724,
address = {Berlin},
author = {Jäger, Florian and Deuerling-Zheng, Yu and Frericks, Bernd and Wacker, Frank and Hornegger, Joachim},
booktitle = {Vision Modeling and Visualization 2006},
editor = {Kobbelt L., Kuhlen T., Aach T., Westermann R.},
faupublication = {yes},
pages = {296-276},
peerreviewed = {unknown},
publisher = {Aka GmbH},
title = {{A} new {Method} for {MRI} {Intensity} {Standardization} with {Application} to {Lesion} {Detection} in the {Brain}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Jaeger06-ANM.pdf},
venue = {Aachen},
year = {2006}
}
@inproceedings{faucris.111084424,
abstract = {This paper proposes a scale space total variation
(ssTV) algorithm to reduce large scale streaks in limited angle
tomography. The weighted total variation (wTV) algorithm is
able to remove most small scale streaks. However, it fails to
reduce larger streaks since total variation (TV) regularization
is scale-dependent and may regard them as homogeneous areas.
Derived from the wTV algorithm, the proposed ssTV algorithm
applies wTV regularization on the image at different scales using
down-sampling and up-sampling operations and thus can reduce
streaks more effectively. Advantages of the ssTV algorithm are
demonstrated on both 2-D numerical data and a 3-D clinical
dataset.
identification of target species or smaller acoustic units, such as distinct call types. However, manually
identifying the signal of interest is time-intensive, error-prone, and becomes unfeasible with large
data volumes. Therefore, machine-driven algorithms are increasingly applied to various bioacoustic
signal identification challenges. Nevertheless, biologists still have major difficulties trying to transfer
existing animal- and/or scenario-related machine learning approaches to their specific animal datasets
and scientific questions. This study presents an animal-independent, open-source deep learning
framework, along with a detailed user guide. Three signal identification tasks, commonly encountered
in bioacoustics research, were investigated: (1) target signal vs. background noise detection, (2)
species classification, and (3) call type categorization. ANIMAL-SPOT successfully segmented human-
annotated target signals in data volumes representing 10 distinct animal species and 1 additional
genus, resulting in a mean test accuracy of 97.9%, together with an average area under the ROC
curve (AUC) of 95.9%, when predicting on unseen recordings. Moreover, an average segmentation
accuracy and F1-score of 95.4% was achieved on the publicly available BirdVox-Full-Night data corpus.
In addition, multi-class species and call type classification resulted in 96.6% and 92.7% accuracy on
unseen test data, as well as 95.2% and 88.4% regarding previous animal-specific machine-based
detection excerpts. Furthermore, an Unweighted Average Recall (UAR) of 89.3% outperformed the
multi-species classification baseline system of the ComParE 2021 Primate Sub-Challenge. Besides
animal independence, ANIMAL-SPOT does not rely on expert knowledge or special computing
resources, thereby making deep-learning-based bioacoustic signal identification accessible to a broad
audience.
In this paper, we consider the deformation field as a Gaussian Process (GP), whereas the selected features are regarded as prior information on the valid deformations. Using GP, we are able to estimate the both dense displacement field and a corresponding uncertainty map at once. Furthermore, we evaluated the performance of different hyperparameter settings for squared exponential kernels with synthetic, phantom and clinical data respectively. The quantitative comparison shows, GP-based interpolation has performance on par with state-of-the-art B-spline interpolation. The greatest clinical benefit of GP-based interpolation is that it gives a reliable estimate of the mathematical uncertainty of the calculated dense displacement map.
},
address = {NEW YORK},
author = {Scheuerer, Ralph and Haderlein, Tino and Nöth, Elmar and Bocklet, Tobias},
booktitle = {2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU)},
doi = {10.1109/ASRU51503.2021.9688278},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2022-05-27},
pages = {1079-1086},
peerreviewed = {unknown},
publisher = {IEEE},
title = {{APPLYING} {X}-{VECTORS} {ON} {PATHOLOGICAL} {SPEECH} {AFTER} {LARYNX} {REMOVAL}},
venue = {Online},
year = {2021}
}
@article{faucris.123373844,
abstract = {
Smart embedded systems often run sophisticated pattern recognition algorithms and are found in many areas like automotive, sports and medicine. The developer of such a system is often confronted with the accuracy–cost conflict as the resulting system should be as accurate as possible while being able to run on resource constraint hardware. This article introduces a method to support the solution of this design conflict with accuracy–cost reports. These reports compare classification systems regarding their classification rate (accuracy) and the mathematical operations and parameters of the working phase (cost). Our method is used to deduce the specific cost of various popular pattern recognition algorithms and to derive the overall cost of a classification system. We also show how our analysis can be used to estimate the computational cost for specific hardware architectures. A software toolbox to create accuracy–cost reports was implemented to facilitate the automatic classification system comparison with the presented methodology. The software is available for download and as supplementary material. We performed different experiments on synthetic and real-world data to underline the value of this analysis. Accurate and computationally cheap classification systems were easily identified. We were even able to find a better implementation candidate in an existing embedded classification problem. This work is the first step towards a comprehensive support tool for the design of embedded classification systems.},
author = {Jensen, Ulf and Kugler, Patrick and Ring, Matthias and Eskofier, Björn},
doi = {10.1007/s10044-015-0503-1},
faupublication = {yes},
journal = {Pattern Analysis and Applications},
keywords = {Machine learning; Real-time systems; Cost estimation; Classification system design},
note = {UnivIS-Import:2016-02-10:Pub.2015.tech.IMMD.IMMD5.approa},
pages = {839-855},
peerreviewed = {Yes},
title = {{Approaching} the accuracy-cost conflict in embedded classification system design},
volume = {19},
year = {2016}
}
@inproceedings{faucris.279699736,
abstract = {Statistical iterative reconstruction (IR) techniques have demonstrated many advantages in X-ray CT reconstruction. The statistical iterative reconstruction approach is often modeled as an optimization problem including a data fitting function and a penalty function. The tuning parameter values that regulate the strength of the penalty function are critical for achieving good reconstruction results. However, appropriate tuning parameter values that are suitable for the scan protocols and imaging tasks are often difficult to choose. In this work, we propose a path seeking algorithm that is capable of generating a series of IR images with different strengths of the penalty function. The path seeking algorithm uses the ratio of the gradients of the data fitting function and the penalty function to select pixels for small fixed size updates. We describe the path seeking algorithm for penalized weighted least squares (PWLS) with a Huber penalty function in both the directions of increasing and decreasing tuning parameter value. Simulations using the XCAT phantom show the proposed method produces path images that are very similar to the IR images that are computed via direct optimization. The root-mean- squared-error of one path image generated by the proposed method relative to full iterative reconstruction is about 6 HU for the entire image and 10 HU for a small region. Different path seeking directions, increment sizes and updating percentages of the path seeking algorithm are compared in simulations. The proposed method may reduce the dependence on selection of good tuning parameter values by instead generating multiple IR images, without significantly increasing the computational load.},
author = {Wu, Meng and Yang, Qiao and Maier, Andreas and Fahrig, Rebecca},
booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
date = {2015-02-22/2015-02-25},
doi = {10.1117/12.2081442},
editor = {Christoph Hoeschen, Despina Kontos, Christoph Hoeschen},
faupublication = {yes},
isbn = {9781628415025},
keywords = {CT; Iterative reconstruction; Path seeking},
note = {CRIS-Team Scopus Importer:2022-08-05},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{Approximate} path seeking for statistical iterative reconstruction},
venue = {Orlando, FL, USA},
volume = {9412},
year = {2015}
}
@article{faucris.120335864,
author = {Dennerlein, Frank and Maier, Andreas},
doi = {10.1088/0031-9155/58/17/6133},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {6133-6148},
peerreviewed = {Yes},
title = {{Approximate} truncation robust computed tomography - {ATRACT}},
volume = {58.0},
year = {2013}
}
@article{faucris.236676854,
abstract = {This study aimed to provide a calibration criterion based on the condition number (Cond, Q) of the basis material matrix (BMM) to optimize experimental performance of basis of material decomposition (BMD) results. Cond(Q) was first elaborated theoretically and then phantom studies, including the possible influence of a number of experimental parameters, such as X-ray spectrum, the number of energy bins and the width of the energy bins, were performed to validate the criterion. In the BMD phantom study, the quantitative relationship between the proposed criterion and BMD accuracy was explored. Results showed that the proposed criterion was negatively correlated to BMD accuracy, and each of the experimental parameters influenced the criterion and BMD accuracy in a similar pattern. In conclusion Cond(Q) can be used to optimize experimental configurations of BMD.},
author = {Yang, Kun and Zhai, Xiaohui and Xie, Zhaoheng and Zhou, Kun and Meng, Xiangxi and Ren, Qiushi and Lu, Yanye},
doi = {10.1016/j.aej.2020.03.009},
faupublication = {yes},
journal = {AEJ - Alexandria Engineering Journal},
keywords = {Basis material decomposition; Condition number; Image-based; Photon counting; Spectral weighting},
note = {CRIS-Team Scopus Importer:2020-03-31},
peerreviewed = {unknown},
title = {{A} practical calibration criterion for image-based material decomposition in spectral computed tomography},
year = {2020}
}
@article{faucris.108080324,
author = {Hahn, Dieter and Sun, Yiyong and Hornegger, Joachim and Sauer, Frank and Wolz, Gabriele and Kuwert, Torsten and Xu, Chenyang},
faupublication = {yes},
journal = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
pages = {870-879},
peerreviewed = {unknown},
title = {{A} practical salient region feature based 3d multimodality registration method for medical images},
year = {2006}
}
@inproceedings{faucris.121223344,
abstract = {We present a novel representation of 3D salient region features and its integration into a hybrid rigid-body registration framework. We adopt scale, translation and rotation invariance properties of those intrinsic 3D features to estimate a transform between underlying mono- or multi-modal 3D medical images. Our method combines advantageous aspects of both feature- and intensity-based approaches and consists of three steps: an automatic extraction of a set of 3D salient region features on each image, a robust estimation of correspondences and their sub-pixel accurate refinement with outliers elimination. We propose a region-growing based approach for the extraction of 3D salient region features, a solution to the problem of feature clustering and a reduction of the correspondence search space complexity. Results of the developed algorithm are presented for both mono- and multi-modal intra-patient 3D image pairs (CT, PET and SPECT) that have been acquired for change detection, tumor localization, and time based intra-person studies. The accuracy of the method is clinically evaluated by a medical expert with an approach that measures the distance between a set of selected corresponding points consisting of both anatomical and functional structures or lesion sites. This demonstrates the robustness of the proposed method to image overlap, missing information and artefacts. We conclude by discussing potential medical applications and possibilities for integration into a non-rigid registration framework.},
author = {Hahn, Dieter and Wolz, Gabriele and Sun, Yiyong and Hornegger, Joachim and Sauer, Frank and Kuwert, Torsten and Xu, Chenyang},
booktitle = {Medical Imaging 2006: Image Processing},
doi = {10.1117/12.653071},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{A} practical salient region feature based {3D} multi-modality registration method for medical images},
venue = {San Diego, CA},
volume = {null},
year = {2006}
}
@inproceedings{faucris.118745264,
abstract = {Polychromatic statistical reconstruction algorithms have very high computational demands due To The difficulty of The optimization problems and The large number of spectrum bins. We want To develop a more practical algorithm That has a simpler optimization problem, a faster numerical solver, and requires only a small amount of prior knowledge. In This paper, a modified optimization problem for polychromatic statistical reconstruction algorithms is proposed. The modified optimization problem utilizes The idea of determining scanned materials based on a first pass FBP reconstruction To fix The ratios between photoelectric and Compton scattering components of all image pixels. The reconstruction of a density image is easy To solve by a separable quadratic surrogate algorithm That is also applicable To The multi-material case. In addition, a spectrum binning method is introduced so That The full spectrum information is not required. The energy bins sizes and attenuations are optimized based on The True spectrum and object. With These approximations, The expected line integral values using only a few energy bins are very closed To The True polychromatic values. Thus both The problem size and computational demand caused by The large number of energy bins That are Typically used To model a full spectrum are reduced. Simulation showed That Three energy bins using The generalized spectrum binning method could provide an accurate approximation of The polychromatic X-ray signals. The average absolute error of The logarithmic detector signal is less Than 0.003 for a 120 kVp spectrum. The proposed modified optimization problem and spectrum binning approach can effectively suppress beam hardening artifacts while providing low noise images. © 2014 SPIE.},
author = {Wu, Meng and Yang, Qiao and Maier, Andreas and Fahrig, Rebecca},
booktitle = {Proc. SPIE Medical Imaging 2014},
date = {2014-02-17/2014-02-20},
doi = {10.1117/12.2043370},
faupublication = {yes},
keywords = {Beam hardening artifact; CT; Iterative reconstruction; Polychromatic X-ray; Spectrum binning},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.apract},
pages = {9033-26},
peerreviewed = {Yes},
title = {{A} practical statistical polychromatic image reconstruction for computed tomography using spectrum binning},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Wu14-APS.pdf},
venue = {San Diego, California, United States},
year = {2014}
}
@article{faucris.310529446,
abstract = {The detection of elongated structures like lines or edges is an essential component in semantic image analysis. Classical approaches that rely on significant image gradients quickly reach their limits when the structure is context-dependent, amorphous, or not directly visible. This study introduces a principled mathematical description of elongated structures with various origins and shapes. Among others, it serves as an expressive operational description of target functions that can be well approximated by Convolutional Neural Networks. The nominal position of a curve and its positional uncertainty are encoded as a heatmap by convolving the curve distribution with a filter function. We propose a low-error approximation to the expensive numerical integration by evaluating a distance-dependent function, enabling a lightweight implementation with linear time complexity. We analyze the method’s numerical approximation error and behavior for different curve types and signal-to-noise levels. Application to surgical 2D and 3D data, semantic boundary detection, skeletonization, and other related tasks demonstrate the method’s versatility at low errors.
This paper describes some of the results from the project entitled “New Parameterization for Emotional Speech Synthesis” held at the Summer 2011 JHU CLSP workshop. We describe experiments on how to use articulatory features as a meaningful intermediate representation for speech synthesis. This parameterization not only allows us to reproduce natural sounding speech but also allows us to generate stylistically varying speech. We show methods for deriving articulatory features from speech, predicting articulatory features from text and reconstructing natural sounding speech from the predicted articulatory features. The methods were tested on clean speech databases in English and German, as well as databases of emotionally and personality varying speech. The resulting speech was evaluated both objectively, using techniques normally used for emotion identification, and subjectively, using crowd-sourcing.
},
author = {Black, Alan W. and Bunnell, H. Timothy and Dou, Ying and Muthukumar, Prasanna Kumar and Metze, Florian and Perry, Daniel and Polzehl, Tim and Prahallad, Kishore S. and Steidl, Stefan and Vaughn, Callie},
booktitle = {Proc. ICASSP 2012},
date = {2012-03-25/2012-03-30},
editor = {IEEE},
faupublication = {yes},
keywords = {speech synthesis; articulatory features; emotional speech; meta-data extraction; evaluation},
pages = {4005-4008},
peerreviewed = {Yes},
title = {{Articulatory} {Features} for {Expressive} {Speech} {Synthesis}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Black12-AFF.pdf},
venue = {Kyoto},
year = {2012}
}
@phdthesis{faucris.296589062,
abstract = {As one of the most common types of heart arrhythmias, atrial fibrillation is a severe disorder of the heart rhythm affecting the left atrium. Among the most serious
complications count stroke and tachycardia mediated cardiomyopathy. Moreover, recurrent symptoms impair patients’ quality of life and functional status. Common
treatment options for rhythm control are antiarrhythmic drug therapy and
catheter ablation procedures. Cardiac ablation procedures are usually performed
minimally invasive in electrophysiology labs. During these procedures, ablation
catheters are navigated into the heart chamber via the venous system to ablate
specific areas involved in conduction of irregular impulses.
For treatment of paroxysmal atrial fibrillation, ipsilateral pulmonary vein isolation is a common ablation pattern. Interventional X-ray imaging is commonly employed for catheter guidance and control. Furthermore, electroanatomic mapping
systems can be used for treatment of complex arrhythmia. Ablation planning
data can be used during X-ray guided procedures as well as included in mapping systems to support the physician by supplying further context information.
In this thesis, artificial intelligence based methods for interventional treatment
of atrial fibrillation ablation procedures are presented. We developed an algorithm for automatic lesion planning targeted at pulmonary vein isolation procedures
for treatment of atrial fibrillation. This method facilitates a landmark-constrained non-rigid registration algorithm for accurate alignment of left atrium heart models.
Procedure planning data is generated for the individual patient anatomy to be superimposed during the ablation procedure. A quantitative and qualitative
evaluation of the algorithm was performed on clinical datasets. The accuracy of
the automatically generated ablation planning lines fulfilled clinical requirements. The mean error of 2.7 mm achieved implies a 29 % improvement compared to the state of the art algorithm. The qualitative evaluation showed full acceptance of the
automatically generated planning lines.
Another aspect investigated in this thesis is the optimization of individual fluoroscopic projection angles for X-ray guided cardiac procedures. We developed an
algorithm to estimate individual X-ray C-arm angulations based on pre-procedure planning information, taking individual patient anatomy into consideration. The C-arm angulations are optimized in respect to the orientation of the planning structure to minimize the foreshortening in the projection image. The mathematical framework can be applied for monoplane and biplane C-arm imaging systems.
Limitations of C-arm imaging systems in terms of feasible rotation angles are also
taken into account during optimization. The algorithm was evaluated on clinical
data for ipsilateral pulmonary vein isolation. Patient-specific C-arm angulations
were computed and compared against commonly used standard angulations in terms of foreshortening of planning structures in projection images. By applying individually optimized X-ray angulations, 28 % less foreshortening could be
achieved on average for biplane systems.
The amount of total body water (TBW) can be estimated based on bioimpedance measurements of the human body. In sports, TBW estimations are of importance because mild water losses can impair muscular strength and aerobic endurance. Severe water losses can even be life threatening. TBW estimations based on bioimpedance, however, fail during sports because the increased body temperature corrupts bioimpedance measurements. Therefore, this paper proposes a machine learning method that eliminates the effects of increased temperature on bioimpedance and, consequently, reveals the changes in bioimpedance that are due to TBW loss. This is facilitated by utilizing changes in skin and core temperature. The method was evaluated in a study in which bioimpedance, temperature, and TBW loss were recorded every 15 minutes during a two-hour running workout. The evaluation demonstrated that the proposed method is able to reduce the error of TBW loss estimation by up to 71%, compared to the state of art. In the future, the proposed method in combination with portable bioimpedance devices might facilitate the development of wearable devices for continuous and noninvasive TBW loss monitoring during sports.},
author = {Ring, Matthias and Lohmüller, Clemens and Rauh, Manfred and Mester, Joachim and Eskofier, Björn},
doi = {10.1109/JBHI.2015.2466076},
faupublication = {yes},
journal = {IEEE Journal of Biomedical and Health Informatics},
note = {EVALuna2:15227},
pages = {1477-1484},
peerreviewed = {Yes},
title = {{A} {Temperature}-{Based} {Bioimpedance} {Correction} for {Water} {Loss} {Estimation} {During} {Sports}},
volume = {20},
year = {2016}
}
@inproceedings{faucris.207561254,
author = {Maier, Andreas and Jiang, Zhenzhen and Jordan, Johannes Michael and Riess, Christian and Hofmann, Hannes and Hornegger, Joachim},
booktitle = {Medical Imaging 2013: Physics of Medical Imaging},
doi = {10.1117/12.2006843},
editor = {SPIE},
faupublication = {yes},
isbn = {9780819494429},
pages = {8668-83},
peerreviewed = {Yes},
title = {{Atlas}-{Based} {Linear} {Volume}-of-{Interest} ({ABL}-{VOI}) {Image} {Correction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Maier13-ALV.pdf},
venue = {Lake Buena Vista, FL},
volume = {8668},
year = {2013}
}
@inproceedings{faucris.319607485,
abstract = {The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique termed attention-guided erasing (AGE), devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. The proposed method integrates supplementary information during transfer learning, utilizing visual attention maps derived from a vision transformer backbone trained using the self-supervised DINO method. These maps are utilized to erase background regions in the mammogram images, unveiling only the potential areas of dense breast tissues to the network. Through the incorporation of AGE during transfer learning with varying random probabilities, we consistently surpass classification performance compared to scenarios without AGE and the traditional random erasing transformation. We validate our methodology using the publicly available VinDr-Mammo dataset. Specifically, we attain a mean F1-score of 0.5910, outperforming values of 0.5594 and 0.5691 corresponding to scenarios without AGE and with random erasing (RE), respectively. This superiority is further substantiated by t-tests, revealing a p-value of p<0.0001, underscoring the statistical significance of our approach.
Bioimpedance analysis (BIA) estimates the amount of total body water (TBW) in the human body. During sports, however, the increased skin temperature distorts bioimpedance measurements and, thus, prevents the application of BIA. In this paper, we propose a two-stage regression that includes temperature information in order to correct the temperature-distorted bioimpedance. In detail, the first regression stage corrects temperature-distored bioimpedance using information of skin and core temperature. The second regression stage estimates TBW loss on basis of the corrected bioimpedance. The two-stage regression was evaluated using data of an ongoing study. The results showed that estimations of TBW loss during sports can be considerably improved if temperature information is included. However, a remaining error was still observed. Therefore, additional measurements, e.g., skin blood flow, are discussed because they also influence bioimpedance and could further reduce the error.},
author = {Ring, Matthias and Lohmüller, Clemens and Rauh, Manfred and Eskofier, Björn},
booktitle = {Proceedings of the 2014 22nd International Conference on Pattern Recognition (ICPR)},
date = {2014-08-24/2014-08-28},
doi = {10.1109/ICPR.2014.773},
editor = {IEEE},
faupublication = {yes},
pages = {4519 - 4524},
peerreviewed = {Yes},
title = {{A} {Two}-{Stage} {Regression} {Using} {Bioimpedance} and {Temperature} for {Hydration} {Assessment} {During} {Sports}},
venue = {Stockholm},
year = {2014}
}
@misc{faucris.115615324,
author = {Stemmer, Georg and Nöth, Elmar and Parsa, V.},
doi = {10.1155/2010/835974},
faupublication = {yes},
month = {Jan},
peerreviewed = {automatic},
title = {{Atypical} {Speech}},
year = {2010}
}
@article{faucris.226999192,
abstract = {Increasing interest in unmanned aerial vehicles (UAVs), commonly referred to as drones, has occurred in recent years. Search and rescue scenarios where humans in emergency situations need to be quickly found in difficult-toaccess areas constitute an important field of application for this technology. Drones have already been used by humanitarian organizations in countries such as Haiti and the Philippines to map areas after a natural disaster using high-resolution embedded cameras, as documented in a recent United Nations report [1]. Although research efforts have focused mostly on developing video-based solutions for this task [2], UAV-embedded audio-based localization has received relatively less attention [3]-[7]. However, UAVs equipped with a microphone array could be of critical help to localize people in emergency situations, especially when video sensors are limited by a lack of visual feedback due to bad lighting conditions (such as at night or in fog) or obstacles limiting the field of view (Figure 1).},
author = {Deleforge, Antoine and Di Carlo, Diego and Strauß, Martin and Serizel, Romain and Marcenaro, Lucio},
doi = {10.1109/MSP.2019.2924687},
faupublication = {yes},
journal = {IEEE Signal Processing Magazine},
note = {CRIS-Team Scopus Importer:2019-09-24},
pages = {138-144},
peerreviewed = {Yes},
title = {{Audio}-{Based} {Search} and {Rescue} with a {Drone}: {Highlights} from the {IEEE} {Signal} {Processing} {Cup} 2019 {Student} {Competition} [{SP} {Competitions}]},
volume = {36},
year = {2019}
}
@inproceedings{faucris.107898824,
author = {Soutschek, Stefan and Maier, Andreas and Hönig, Florian Thomas and Spiegl, Werner and Steidl, Stefan and Hornegger, Joachim and Erzigkeit, Helmut and Kornhuber, Johannes},
booktitle = {Proceedings of the 5th Russian-Bavarian Conference on Biomedical Engineering},
date = {2009-07-01/2009-07-04},
editor = {In: Russian Bavarian Conference on Bio-Medical Engineering},
faupublication = {yes},
pages = {n.a.},
peerreviewed = {Yes},
title = {{Audio}-{Visual} {Feedback} {System} for {Reward}-{Based} {Training} {Sessions} of {Elderly} {People} in a {Home} {Environment}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Soutschek09-AVF.pdf},
venue = {München},
year = {2009}
}
@inproceedings{faucris.108242244,
author = {Bourier, Felix and Brost, Alexander and Hornegger, Joachim and Kiraly, Attila P. and Barbot, Julien and Strobel, Norbert and Zorger, Niels and Schneider, Hans-Jürgen and Heißenhuber, Frank and Kurzidim, Klaus},
booktitle = {ESC Congress},
date = {2011-08-27/2011-08-31},
editor = {European Society of Cardiology},
faupublication = {yes},
pages = {P3606},
peerreviewed = {unknown},
title = {{Augmented} fluoroscopy-based navigation on a biplane angiography system for pulmonary vein isolation},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Bourier11-AFN.pdf},
venue = {Paris},
year = {2011}
}
@inproceedings{faucris.113201044,
author = {Bourier, Felix and Schneider, Hans-Jürgen and Heißenhuber, Frank and Ganslmeier, Patrycja and Brost, Alexander and Koch, Martin and Hornegger, Joachim and Kleinöder, Andreas and Kiraly, Attila P. and Barbot, Julien and Strobel, Norbert and Kurzidim, Klaus},
booktitle = {Venice Arrhythmias 2011},
date = {2011-10-09/2011-10-12},
editor = {Journal of Cardiovascular Electrophysiology},
faupublication = {yes},
pages = {112.0},
peerreviewed = {unknown},
title = {{Augmented} {Fluoroscopy} to {Guide} {Transseptal} {Puncture}},
venue = {Venice},
year = {2011}
}
@inproceedings{faucris.217470056,
abstract = {Histopathological prognostication of neoplasia including most tumor grading systems are based upon a number of criteria. Probably the most important is the number of mitotic figures which are most commonly determined as the mitotic count (MC), i.e. number of mitotic figures within 10 consecutive high power fields. Often the area with the highest mitotic activity is to be selected for the MC. However, since mitotic activity is not known in advance, an arbitrary choice of this region is considered one important cause for high variability in the prognostication and grading. In this work, we present an algorithmic approach that first calculates a mitotic cell map based upon a deep convolutional network. This map is in a second step used to construct a mitotic activity estimate. Lastly, we select the image segment representing the size of ten high power fields with the overall highest mitotic activity as a region proposal for an expert MC determination. We evaluate the approach using a dataset of 32 completely annotated whole slide images, where 22 were used for training of the network and 10 for test. We find a correlation of r=0.936 in mitotic count estimate.},
author = {Aubreville, Marc and Bertram, Christof A. and Klopfleisch, Robert and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}71},
editor = {Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2019-05-14},
pages = {321-326},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Augmented} {Mitotic} {Cell} {Count} {Using} {Field} of {Interest} {Proposal}},
venue = {Lübeck},
year = {2019}
}
@inproceedings{faucris.122189584,
address = {Swansea, Wales},
author = {Köhler, Thomas and Jordan, Johannes Michael and Maier, Andreas and Hornegger, Joachim},
booktitle = {Proceedings of the British Machine Vision Conference (BMVC)},
faupublication = {yes},
isbn = {1-901725-53-7},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.aunifi},
pages = {143.1-143.12},
publisher = {BMVA Press},
title = {{A} {Unified} {Bayesian} {Approach} to {Multi}-{Frame} {Super}-{Resolution} and {Single}-{Image} {Upsampling} in {Multi}-{Sensor} {Imaging}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Koehler15-AUB.pdf},
venue = {Swansea, Wales},
year = {2015}
}
@inproceedings{faucris.282303429,
abstract = {The demand for both quantity and quality of online educational resources has skyrocketed during the last two years’ pandemic. Entire course series had since been recorded and distributed online. To reach a broader audience, videos could be transcribed, combined with supplementary material (e.g. lecture slides) and published in the style of blog posts. This had been done previously for Autoblog 2020, a corpus of lecture recordings that had been converted to blog posts, using automated speech recognition (ASR) for subtitle creation. This work aims to introduce a second series of recorded and manually transcribed lecture videos. The corresponding data includes lecture videos, slides, and blog posts/transcripts with aligned slide images and is published under creative commons license. A state-of-the-art Wav2Vec ASR model was used for automatic transcription of the content, using different n-gram language models (LM). The results were compared to the human ground truth annotation. Findings indicated that the ASR performed well on spontaneous lecture speech. Furthermore, LMs trained on large amounts of data with fewer out-of-vocabulary words were outperformed by much smaller LMs estimated over in-domain language. Annotated lecture recordings were deemed helpful for the creation of task-specific ASR solutions as well as their validation against a human ground truth.
The number of patients suffering from the glaucoma disease will increase in the future. A further automation of parts of the diagnostic routine is inevitable to use limited examination times more efficiently. Optical coherence tomography (OCT) technology has become a widespread tool for glaucoma diagnosis, and data collections in the clinics have been built up in recent years that now allow for data mining and pattern recognition approaches to be applied to the diagnostic challenge. A complete pattern recognition pipeline to automatically discriminate glaucomatous from normal eyes with OCT data is proposed, implemented and evaluated. A data collection of 1024 Spectralis HRA+OCT circular scans around the optic nerve head from 565 subjects build the basis for this work. The data collection is labeled with 4 diagnoses: 453 healthy (H), 179 ocular hypertension (OHT), 168 preperimetric glaucoma (PPG), and 224 perimetric glaucoma (PG) eyes.
In a first step, 6 retinal layer boundaries are automatically segmented by edge detection and the minimization of a custom energy functional, which was established in preceeding work by the author. The segmentation algorithm is evaluated on a subset consisting of 120 scans. The automatically segmented layer boundaries are compared to a gold standard (GS) created from manual corrections to the automated results by 5 observers. The mean absolute difference of the automated segmentation to the GS for the outer nerve fiber layer boundary is 2.84μm. The other layers have less or almost no segmentation error. No significant correlation between the segmentation error and scans of bad quality or glaucomatous eyes could be found for any layer boundary. The difference of the automated segmentation to the GS is not much worse than the single observer’s manual correction difference to the GS.
In a second step, the thickness profiles generated by the segmentation are used in a classification system: In total, 762 features are generated, including novel ratio and principal component analysis features. “Forward selection and backward elimi- nation” selects the best performing features with respect to the classwise averaged classification rate (CR) on the training data. The segmentations of the complete dataset were manually corrected so that the classification experiments could either be run on manually corrected or purely automated segmentations. Three classifiers were compared. The support vector machine classifier (SVM) performed best in a 10-fold cross-validation and differentiated non-glaucomatous (H and OHT) from glaucomatous (PPG and PG) eyes with a CR of 0.859 on manually corrected data. The classification system adapts to the less reliable purely automated segmentations by choosing features of a more global scale. Training with manually corrected and testing with purely automated data and vice versa shows that it is of advance to use manually corrected data for training, no matter what the type of test data is. The distance of the feature vectors to the SVM decision boundary is used as a basis for a novel glaucoma probability score based on OCT data, the OCT-GPS.
},
author = {Mayer, Markus Anton},
faupublication = {yes},
keywords = {Optische Kohärenztomografie; Maschinelles Lernen; Überwachtes Lernen; Bildverarbeitung; Bildsegmentierung; Glaukom},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.automa{\_}4},
peerreviewed = {automatic},
school = {Friedrich-Alexander-Universität Erlangen-Nürnberg},
title = {{Automated} {Glaucoma} {Detection} with {Optical} {Coherence} {Tomography}},
url = {https://opus4.kobv.de/opus4-fau/frontdoor/index/index/docId/9849},
year = {2018}
}
@inproceedings{faucris.203367159,
author = {Zach, Fabian and Riess, Christian and Angelopoulou, Elli},
booktitle = {Pattern Recognition - Joint 34th DAGM and 36th OAGM Symposium},
date = {2012-08-28/2012-08-31},
doi = {10.1007/978-3-642-32717-9{\_}19},
faupublication = {yes},
isbn = {9783642327162},
pages = {185-194},
peerreviewed = {Yes},
title = {{Automated} {Image} {Forgery} {Detection} through {Classification} of {JPEG} {Ghosts}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Zach12-AIF.pdf},
venue = {Graz},
year = {2012}
}
@article{faucris.113521144,
abstract = {We demonstrate an automated segmentation method for in-vivo 3D optical coherence tomography (OCT) imaging of the lamina cribrosa (LC). Manual segmentations of coronal slices of the LC were used as a gold standard in parameter selection and evaluation of the automated technique. The method was validated using two prototype OCT devices; each had a subject cohort including both healthy and glaucomatous eyes. Automated segmentation of in-vivo 3D LC OCT microstructure performed comparably to manual segmentation and is useful for investigative research and in clinical quantification of the LC. © 2013 Optical Society of America.},
author = {Nadler, Zach and Wang, Bo and Wollstein, Gadi and Nevins, Jessica and Ishikawa, Hiroshi and Kagemann, Larry and Sigal, Ian and Ferguson, Daniel and Hammer, Daniel and Grulkowski, Ireneusz and Liu, Jonathan J. and Kraus, Martin and Lu, Chen D. and Hornegger, Joachim and Fujimoto, James G. and Schuman, Joel},
doi = {10.1364/BOE.4.002596},
faupublication = {yes},
journal = {Biomedical Optics Express},
note = {UnivIS-Import:2015-03-09:Pub.2013.tech.IMMD.IMMD5.automa{\_}57},
pages = {25962608},
peerreviewed = {Yes},
title = {{Automated} lamina cribrosa microstructural segmentation in optical coherence tomography scans of healthy and glaucomatous eyes},
volume = {4},
year = {2013}
}
@inproceedings{faucris.111200804,
author = {Kurzendorfer, Tanja and Brost, Alexander and Forman, Christoph and Maier, Andreas},
booktitle = {Proceedings of the 2017 IEEE International Symposium on Biomedical Imaging: From Nano to Macro},
date = {2017-04-18/2017-04-21},
doi = {10.1109/ISBI.2017.7950646},
faupublication = {yes},
isbn = {9781509011711},
keywords = {Heart; Image Segmentation; Magnetic Resonance Imaging (MRI)},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.automa{\_}2},
pages = {831-834},
peerreviewed = {unknown},
publisher = {IEEE Computer Society},
title = {{Automated} {Left} {Ventricle} {Segmentation} in 2-{D} {LGE}-{MRI}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Kurzendorfer17-ALV.pdf},
venue = {Melbourne},
year = {2017}
}
@inproceedings{faucris.229477684,
abstract = {Left ventricle segmentation and morphological assessment are essential for improving diagnosis and our understanding of cardiomyopathy, which in turn is imperative for reducing risk of myocardial infarctions in patients. Convolutional neural network (CNN) based methods for cardiac magnetic resonance (CMR) image segmentation rely on supervision with pixel-level annotations, and may not generalize well to images from a different domain. These methods are typically sensitive to variations in imaging protocols and data acquisition. Since annotating multi-sequence CMR images is tedious and subject to inter- and intra-observer variations, developing methods that can automatically adapt from one domain to the target domain is of great interest. In this paper, we propose an approach for domain adaptation in multi-sequence CMR segmentation task using transfer learning that combines multi-source image information. We first train an encoder-decoder CNN on T2-weighted and balanced-Steady State Free Precession (bSSFP) MR images with pixel-level annotation and fine-tune the same network with a limited number of Late Gadolinium Enhanced-MR (LGE-MR) subjects, to adapt the domain features. The domain-adapted network was trained with just four LGE-MR training samples and obtained an average Dice score of $\sim$85.0\% on the test set comprises of 40 LGE-MR subjects. The proposed method significantly outperformed a network without adaptation trained from scratch on the same set of LGE-MR training data.
Batik cloth is Indonesia's national heritage. Across the archipelago, there are numerous patterns and motifs of batik, each having its own meaning and cultural significance. In this paper, we present the results of our investigation of various combinations of SIFT features moments used in automatic classification of batik motifs. The classification method used in this paper is the k-Nearest Neighbor. Our experiments show that the best performance of the system is obtained using feature vectors of length 7, yielding a classification accuracy rate of 31.43% for 7 classes of batik motifs with no batik motif classes having zero classification accuracy rate. Furthermore, our experiments suggest that the feature moment that seems to be the best for the classification process is the μc, while the feature moment that seems to hinder the classification process is the σc2.},
author = {Setyawan, Iwan and Timotius, Ivanna and Kalvin, Marchellius},
booktitle = {International Conference on Information Technology and Electrical Engineering},
doi = {10.1109/ICITEED.2015.7408954},
faupublication = {no},
keywords = {SIFT features; feature moments; pattern classification; batik motifs},
pages = {269 - 274},
peerreviewed = {unknown},
title = {{Automatic} {Batik} {Motifs} {Classification} using {Various} {Combinations} of {SIFT} {Features} {Moments} and k-{Nearest} {Neighbor}},
venue = {Chiang Mai},
year = {2015}
}
@inproceedings{faucris.113159464,
author = {Grimm, Robert and Li, Feng and Forman, Christoph and Hutter, Jana and Kiefer, Berthold and Hornegger, Joachim and Block, Kai Tobias},
booktitle = {International Society for Magnetic Resonance in Medicine},
date = {2013-04-20/2013-04-26},
editor = {Gold Garry E.},
faupublication = {yes},
pages = {696.0},
title = {{Automatic} {Bolus} {Analysis} for {DCE}-{MRI} {Using} {Radial} {Golden}-{Angle} {Stack}-of-stars {GRE} {Imaging}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Grimm13-ABA.pdf},
venue = {Salt Lake City, UT},
year = {2013}
}
@article{faucris.261569499,
abstract = {Background Imprecise articulation has a negative impact on speech intelligibility. Therefore, treatment of articulation is clinically relevant in patients with dysarthria. In order to be effective and according to the principles of motor learning, articulation therapy needs to be intensive, well organized, with adequate feedback and requires frequent practice. Aims The aims of this pilot study are (1) to evaluate the feasibility of a virtual articulation therapy (VAT) to guide patients with dysarthria through a boost articulation therapy (BArT) program; (2) to evaluate the acoustic models' performance used for automatic phonological error detection; and (3) to validate the system by end-users from their perspective. Methods & Procedures The VAT provides an extensive and well-structured package of exercises with visual and auditory modelling and adequate feedback on the utterances. The tool incorporates automated methods to detect phonological errors, which are specifically designed to analyse Dutch speech production. A total of 14 subjects with dysarthria evaluated the acceptability, usability and user interaction with the VAT based on two completed therapy sessions using a self-designed questionnaire. Outcomes & Results In general, participants were positive about the new computer-based therapy approach. The algorithm performance for phonological error detection shows it to be accurate, which contributes to adequate feedback of utterance production. The results of the study indicate that the VAT has a user-friendly interface that can be used independently by patients with dysarthria who have sufficient cognitive, linguistic, motoric and sensory skills to benefit from speech therapy. Recommendations were given by the end-users to further optimize the program and to ensure user engagement. Conclusions & Implications The initial implementation of an automatic BArT shows it to be feasible and well accepted by end-users. The tool is an appropriate solution to increase the frequency and intensity of articulation training that supports traditional methods. What this paper adds What is already known on the subject Behavioural interventions to improve articulation in patients with dysarthria demand intensive treatments, repetitive practice and feedback. However, the current treatments are mainly limited in time to the interactive sessions in the presence of speech-language pathology. Automatic systems addressing the needs of individuals with dysarthria are scarce. This study evaluates the feasibility of a VAT program and investigates its acceptability, usability and user interaction. What this paper adds to existing knowledge The computer-based speech therapy approach developed and applied in this study intends to support intensive articulation training of patients with dysarthria. The virtual speech therapy offers the possibility of an individualized and customized therapy programme, with an extensive database of exercises, visual and auditory models of the target utterances, and providing adequate feedback based on automatic acoustic analysis of speech. What are the potential or actual clinical implications of this work? The automatic BArT overcomes the limitation in time of face-to-face traditional speech therapy. It offers patients the opportunity to have access to speech therapy more intensively and frequently in their home environment.},
author = {Ramos, Viviana Mendoza and Vasquez Correa, Juan and Cremers, Rani and Van Den Steen, Leen and Nöth, Elmar and De Bodt, Marc and Van Nuffelen, Gwen},
doi = {10.1111/1460-6984.12647},
faupublication = {yes},
journal = {International Journal of Language & Communication Disorders},
note = {CRIS-Team WoS Importer:2021-07-16},
peerreviewed = {Yes},
title = {{Automatic} boost articulation therapy in adults with dysarthria: {Acceptability}, usability and user interaction},
year = {2021}
}
@inproceedings{faucris.243488155,
abstract = {Coronary CT angiography (CCTA) has established its role
as a non-invasive modality for the diagnosis of coronary artery disease
(CAD). The CAD-Reporting and Data System (CAD-RADS) has been
developed to standardize communication and aid in decision making
based on CCTA findings. The CAD-RADS score is determined by manual assessment of all coronary vessels and the grading of lesions within
the coronary artery tree.
We propose a bottom-up approach for fully-automated prediction of this
score using deep-learning operating on a segment-wise representation of
the coronary arteries. The method relies solely on a prior fully-automated
centerline extraction and segment labeling and predicts the segment-wise
stenosis degree and the overall calcification grade as auxiliary tasks in a
multi-task learning setup.
We evaluate our approach on a data collection consisting of 2,867 patients. On the task of identifying patients with a CAD-RADS score indicating the need for further invasive investigation our approach reaches an
area under curve (AUC) of 0.923 and an AUC of 0.914 for determining
whether the patient suffers from CAD. This level of performance enables
our approach to be used in a fully-automated screening setup or to assist
diagnostic CCTA reading, especially due to its neural architecture design
– which allows comprehensive predictions.
},
author = {Aubreville, Marc and Knipfer, Christian and Oetter, Nicolai and Jaremenko, Christian and Rodner, Erik and Denzler, Joachim and Bohr, Christopher and Neumann, Helmut and Stelzle, Florian and Maier, Andreas},
doi = {10.1038/s41598-017-12320-8},
faupublication = {yes},
journal = {Scientific Reports},
keywords = {Cancer imaging, translational research, deep learning},
pages = {s41598-017},
peerreviewed = {Yes},
title = {{Automatic} {Classification} of {Cancerous} {Tissue} in {Laserendomicroscopy} {Images} of the {Oral} {Cavity} using {Deep} {Learning}},
url = {https://www.nature.com/articles/s41598-017-12320-8.pdf},
volume = {7},
year = {2017}
}
@article{faucris.203341145,
abstract = {Electroluminescence (EL) imaging is a useful modality for the inspection of photovoltaic (PV) modules. EL images provide high spatial resolution, which makes it possible to detect even finest defects on the surface of PV modules. However, the analysis of EL images is typically a manual process that is expensive, time-consuming, and requires expert knowledge of many different types of defects. In this work, we investigate two approaches for automatic detection of such defects in a single image of a PV cell. The approaches differ in their hardware requirements, which are dictated by their respective application scenarios. The more hardware-efficient approach is based on hand-crafted features that are classified in a Support Vector Machine (SVM). To obtain a strong performance, we investigate and compare various processing variants. The more hardware-demanding approach uses an end-to-end deep Convolutional Neural Network (CNN) that runs on a Graphics Processing Unit (GPU). Both approaches are trained on 1,968 cells extracted from high resolution EL intensity images of mono- and polycrystalline PV modules. The CNN is more accurate, and reaches an average accuracy of 88.42%. The SVM achieves a slightly lower average accuracy of 82.44%, but can run on arbitrary hardware. Both automated approaches make continuous, highly accurate monitoring of PV cells feasible.
this area. It is a corpus of spontaneous, emotionally colored speech of children at the age of 10 to 13 years interacting with the Sony robot Aibo. 11 emotion-related states are labeled on the word level. Experiments are conducted on three subsets of the corpus on the word, the turn, and the intermediate chunk level. Best results have been obtained on the chunk level where a classwise averaged recognition rate of almost 70 % for the 4-class problem Anger, Emphatic, Neutral, and Motherese has been achieved. Applying the proposed entropy based measure for the evaluation of
decoders, the performance of the machine classifier on the word level is even slightly better than the one of the average human labeler. The presented set of features covers both acoustic and linguistic features. The linguistic features perform slightly worse than the acoustic features. An improvement can be achieved by combining both knowledge sources. The acoustic features are categorized into prosodic, spectral, and voice quality features. The energy and duration based prosodic features and
the spectral MFCC features are the most relevant acoustic features in this scenario. Unigram models and bag-of-words features are the most relevant linguistic features.},
address = {Berlin},
author = {Steidl, Stefan},
editor = {Heinrich Niemann, Elmar Nöth},
faupublication = {yes},
isbn = {978-3832521455},
keywords = {Emotion; emotionale Benutzerzustände; Automatische Klassifikation; Kindersprache},
pages = {260.0},
peerreviewed = {Yes},
publisher = {Logos Verlag},
series = {Studien zur Mustererkennung},
title = {{Automatic} {Classification} of {Emotion}-{Related} {User} {States} in {Spontaneous} {Children}'s {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Steidl09-ACO.pdf},
volume = {28},
year = {2009}
}
@inproceedings{faucris.311095437,
abstract = {Hypokinetic and hyperkinetic dysarthria are motor speech disorders that appear in patients with Parkinson's and Huntington's disease, respectively. They are caused due to progressive lesions or alterations in the basal ganglia. In particular, Huntington's disease (HD) is known to be more invasive and difficult to treat than Parkinson's disease (PD), producing more aggressive motor and cognitive alterations. Since speech production requires the movement and control of many different muscles and limbs, it constitutes a highly complex motor activity that may reflect relevant aspects of the patient's health state. This paper proposes the discrimination between patients with PD, HD, and healthy controls (HC) based on different speech dimensions. Speaker models based on Gaussian-mixture model supervectors are created with the features extracted from each speech dimension. The results suggest that it is possible to distinguish between PD and HD patients using the supervectors-based approach.},
author = {Rios-Urrego, C. D. and Rusz, J. and Nöth, Elmar and Orozco-Arroyave, J. R.},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2023-08-20/2023-08-24},
doi = {10.21437/Interspeech.2023-2146},
faupublication = {yes},
keywords = {Articulation; Huntington's disease; Parkinson's disease; Pathological speech; Phonation; Prosody},
note = {CRIS-Team Scopus Importer:2023-09-29},
pages = {2368-2372},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{Automatic} {Classification} of {Hypokinetic} and {Hyperkinetic} {Dysarthria} based on {GMM}-{Supervectors}},
venue = {Dublin, IRL},
volume = {2023-August},
year = {2023}
}
@inproceedings{faucris.120325304,
address = {-},
author = {Kompe, Ralf and Batliner, Anton and Kießling, Andreas and Kilian, Ute and Niemann, Heinrich and Nöth, Elmar and Regel-Brietzmann, Peter},
booktitle = {ICASSP},
date = {1994-04-19/1994-04-22},
editor = {ICASSP},
faupublication = {yes},
pages = {173-176},
publisher = {-},
title = {{Automatic} {Classification} of {Prosodically} {Marked} {Phrase} {Boundaries} in {German}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1994/Kompe94-ACO.pdf},
venue = {Adelaide},
year = {1994}
}
@inproceedings{faucris.108162164,
address = {New York},
author = {Maier, Andreas and Horndasch, Stefanie and Nöth, Elmar},
booktitle = {Workshop on Child, Computer, and Interaction 2009},
date = {2009-11-05},
editor = {-----},
faupublication = {yes},
pages = {no pagination},
peerreviewed = {Yes},
publisher = {ACM Order Department},
title = {{Automatic} {Classification} of {Reading} {Disorders} in a {Single} {Word} {Reading} {Test}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Maier09-ACO.pdf},
venue = {Boston, MA},
year = {2009}
}
@inproceedings{faucris.120179664,
author = {Schuldhaus, Dominik and Leutheuser, Heike and Eskofier, Björn},
booktitle = {Sportinformatik 2012},
date = {2012-09-12/2012-09-14},
editor = {Deutsche Vereinigung für Sportwissenschaft},
faupublication = {yes},
pages = {140-143},
title = {{Automatic} {Classification} of {Sport} {Exercises} for {Training} {Support}},
venue = {Konstanz},
year = {2012}
}
@inproceedings{faucris.122925044,
abstract = {
Several research tools and projects require groups of similar code changes as input. Examples are recommendation and bug finding tools that can provide valuable information to developers based on such data. With the help of similar code changes they can simplify the application of bug fixes and code changes to multiple locations in a project. But despite their benefit, the practical value of existing tools is limited, as users need to manually specify the input data, i.e., the groups of similar code changes.
To overcome this drawback, this paper presents and evaluates two syntactical similarity metrics, one of them is specifically designed to run fast, in combination with two carefully selected and self-tuning clustering algorithms to automatically detect groups of similar code changes.
We evaluate the combinations of metrics and clustering algorithms by applying them to several open source projects and also publish the detected groups of similar code changes online as a reference dataset. The automatically detected groups of similar code changes work well when used as input for LASE, a recommendation system for code changes.
},
author = {Kreutzer, Patrick and Dotzler, Georg and Ring, Matthias and Eskofier, Björn and Philippsen, Michael},
booktitle = {Proceedings of the 13th International Conference on Mining Software Repositories (MSR'16)},
date = {2016-05-14/2016-05-15},
doi = {10.1145/2901739.2901749},
faupublication = {yes},
isbn = {978-1-4503-4186-8},
pages = {61-72},
peerreviewed = {Yes},
title = {{Automatic} clustering of code changes},
url = {http://dl.acm.org/citation.cfm?id=2901749},
venue = {Austin, TX, USA},
year = {2016}
}
@article{faucris.107955364,
author = {Stelzle, Florian and Ugrinovic, Biljana and Knipfer, Christian and Bocklet, Tobias and Nöth, Elmar and Schuster, Maria and Eitner, Stefan and Seiss, Martin and Nkenke, Emeka},
faupublication = {yes},
journal = {Journal of Oral Rehabilitation},
pages = {209-216},
peerreviewed = {Yes},
title = {{Automatic}, computer-based analysis of speech intelligibility on edentulous patients with and without complete dentures - preliminary results},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Stelzle10-ACS.pdf},
volume = {37.0},
year = {2010}
}
@article{faucris.119082304,
abstract = {Dental rehabilitation of edentulous patients with complete dentures includes not only aesthetics and mastication of food, but also speech quality. It was the aim of this study to introduce and validate a computer-based speech recognition system (ASR) for automatic speech assessment in edentulous patients after dental rehabilitation with complete dentures. To examine the impact of dentures on speech production, the speech outcome of edentulous patients with and without complete dentures was compared. Twenty-eight patients reading a standardized text were recorded twice - with and without their complete dentures in situ. A control group of 40 healthy subjects with natural dentition was recorded under the same conditions. Speech quality was evaluated by means of a polyphone-based ASR according to the percentage of the word accuracy (WA). Speech acceptability assessment by expert listeners and the automatic rating of the WA by the ASR showed a high correlation (corr = 0.71). Word accuracy was significantly reduced in edentulous speakers (55.42 +/- 13.1) compared to the control group's WA (69.79 +/- 10.6). On the other hand, wearing complete dentures significantly increased the WA of the edentulous patients (60.00 +/- 15.6). Speech production quality is significantly reduced after complete loss of teeth. Reconstitution of speech production quality is an important part of dental rehabilitation and can be improved for edentulous patients by means of complete dentures. The ASR has proven to be a useful and easily applicable tool for automatic speech assessment in a standardized way.},
author = {Stelzle, Florian and Ugrinovic, Biljana and Knipfer, Christian and Bocklet, Tobias and Nöth, Elmar and Schuster, Maria and Eitner, Stefan and Seiss, Martin and Nkenke, Emeka},
doi = {10.1111/j.1365-2842.2009.02047.x},
faupublication = {yes},
journal = {Journal of Oral Rehabilitation},
keywords = {speech quality;automatic speech recognition;objective speech assessment;edentulism;complete dentures;oral rehabilitation},
pages = {209-216},
peerreviewed = {Yes},
title = {{Automatic}, computer-based speech assessment on edentulous patients with and without complete dentures - preliminary results},
volume = {37},
year = {2010}
}
@article{faucris.246072629,
abstract = {Dementia is one of the most common neurological syndromes in the world. Usually, diagnoses are made based on paper-and-pencil tests and scored depending on personal judgments of experts. This technique can introduce errors and has high inter-rater variability. To overcome these issues, we present an automatic assessment of the widely used paper-based clock-drawing test by means of deep neural networks. Our study includes a comparison of three modern architectures: VGG16, ResNet-152, and DenseNet-121. The dataset consisted of 1315 individuals. To deal with the limited amount of data, which also included several dementia types, we used optimization strategies for training the neural network. The outcome of our work is a standardized and digital estimation of the dementia screening result and severity level for an individual. We achieved accuracies of 96.65% for screening and up to 98.54% for scoring, overcoming the reported state-of-the-art as well as human accuracies. Due to the digital format, the paper-based test can be simply scanned by using a mobile device and then be evaluated also in areas where there is a staff shortage or where no clinical experts are available.
PurposeDual‐energy computed tomography (DECT) has shown great potential in many clinical applications. By incorporating the information from two different energy spectra, DECT provides higher contrast and reveals more material differences of tissues compared to conventional single‐energy CT (SECT). Recent research shows that automatic multi‐organ segmentation of DECT data can improve DECT clinical applications. However, most segmentation methods are designed for SECT, while DECT has been significantly less pronounced in research. Therefore, a novel approach is required that is able to take full advantage of the extra information provided by DECT.
Methods
In the scope of this work, we proposed four three‐dimensional (3D) fully convolutional neural network algorithms for the automatic segmentation of DECT data. We incorporated the extra energy information differently and embedded the fusion of information in each of the network architectures.
Results
Quantitative evaluation using 45 thorax/abdomen DECT datasets acquired with a clinical dual‐source CT system was investigated. The segmentation of six thoracic and abdominal organs (left and right lungs, liver, spleen, and left and right kidneys) were evaluated using a fivefold cross‐validation strategy. In all of the tests, we achieved the best average Dice coefficients of 98% for the right lung, 98% for the left lung, 96% for the liver, 92% for the spleen, 95% for the right kidney, 93% for the left kidney, respectively. The network architectures exploit dual‐energy spectra and outperform deep learning for SECT.
Conclusions
The results of the cross‐validation show that our methods are feasible and promising. Successful tests on special clinical cases reveal that our methods have high adaptability in the practical application.
},
author = {Chen, Shuqing and Zhong, Xia and Hu, Shiyang and Dorn, Sabrina and Kachelriess, Marc and Lell, Michael and Maier, Andreas},
doi = {10.1002/mp.13950},
faupublication = {yes},
journal = {Medical Physics},
keywords = {Multi-organ; DECT; FCN; U-Net; deep learning},
pages = {552-562},
peerreviewed = {Yes},
title = {{Automatic} {Multi}-organ {Segmentation} in {Dual} {Energy} {CT} ({DECT}) with {Dedicated} {3D} {Fully} {Convolutional} {DECT} {Networks}},
volume = {47},
year = {2020}
}
@inproceedings{faucris.203717612,
author = {Chen, Shuqing and Zhong, Xia and Hu, Shiyang and Dorn, Sabrina and Kachelriess, Marc and Lell, Michael and Maier, Andreas},
booktitle = {MIDL},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.automa{\_}98},
pages = {n.a.},
peerreviewed = {unknown},
title = {{Automatic} {Multi}-{Organ} {Segmentation} in {Dual} {Energy} {CT} using {3D} {Fully} {Convolutional} {Network}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Chen18-AMS.pdf},
venue = {Amsterdam},
year = {2018}
}
@inproceedings{faucris.108035224,
author = {Köhler, Thomas and Budai, Attila and Kraus, Martin and Odstrcilik, Jan and Michelson, Georg and Hornegger, Joachim},
booktitle = {2013 26th IEEE International Symposium on Computer-Based Medical Systems (CBMS)},
doi = {10.1109/CBMS.2013.6627771},
editor = {IEEE},
faupublication = {yes},
pages = {95-100},
title = {{Automatic} {No}-{Reference} {Quality} {Assessment} for {Retinal} {Fundus} {Images} {Using} {Vessel} {Segmentation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Koehler13-ANQ.pdf},
venue = {Porto, Portugal},
year = {2013}
}
@inproceedings{faucris.108207264,
author = {Stelzle, Florian and Schuster, Maria and Maier, Andreas and Bocklet, Tobias and Nöth, Elmar and Seiß, Martin and Neukam, Friedrich Wilhelm and Nkenke, Emeka},
booktitle = {3rd International IZKF-Symposium},
date = {2009-05-14/2009-05-16},
editor = {Reis André},
faupublication = {yes},
pages = {-- (Poster)},
peerreviewed = {Yes},
title = {{Automatic} {Objective} {Analysis} of {Speech} {Disorders} on {Patients} with {Oral} {Squamous} {Cell} {Carcinoma}},
venue = {Bad Staffelstein},
year = {2009}
}
@article{faucris.107398104,
abstract = {Over the past ten years similarity measures based on intensity distributions have become state-of-the-art in automatic multimodal image registration. An implementation for clinical usage has to support a plurality of images. However, a generally applicable parameter configuration for the number and sizes of histogram bins, optimal Parzen-window kernel widths or background thresholds cannot be found. This explains why various research groups present partly contradictory empirical proposals for these parameters. This paper proposes a set of data-driven estimation schemes for a parameter-free implementation that eliminates major caveats of heuristic trial and error. We present the following novel approaches: a new coincidence weighting scheme to reduce the influence of background noise on the similarity measure in combination with Max-Lloyd requantization, and a tradeoff for the automatic estimation of the number of histogram bins. These methods have been integrated into a state-of-the-art rigid registration that is based on normalized mutual information and applied to CTMR, PETMR, and MRMR image pairs of the RIRE 2.0 database. We compare combinations of the proposed techniques to a standard implementation using default parameters, which can be found in the literature, and to a manual registration by a medical expert. Additionally, we analyze the effects of various histogram sizes, sampling rates, and error thresholds for the number of histogram bins. The comparison of the parameter selection techniques yields 25 approaches in total, with 114 registrations each. The number of bins has no significant influence on the proposed implementation that performs better than both the manual and the standard method in terms of acceptance rates and target registration error (TRE). The overall mean TRE is 2.34 mm compared to 2.54 mm for the manual registration and 6.48 mm for a standard implementation. Our results show a significant TRE reduction for distortion-corrected magnetic resonance images. © 2010 IEEE.},
author = {Hahn, Dieter and Daum, Volker and Hornegger, Joachim},
doi = {10.1109/TMI.2010.2041358},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
note = {UnivIS-Import:2015-03-09:Pub.2010.tech.IMMD.IMMD5.automa},
pages = {1140-1155},
peerreviewed = {Yes},
title = {{Automatic} {Parameter} {Selection} for {Multi}-{Modal} {Image} {Registration}},
volume = {29},
year = {2010}
}
@inproceedings{faucris.121477224,
address = {Berlin Heidelberg},
author = {Grimm, Robert and Sukkau, Johann and Hornegger, Joachim and Greiner, Günther},
booktitle = {Informatik aktuell},
date = {2011-03-20/2011-03-22},
doi = {10.1007/978-3-642-19335-4{\_}84},
editor = {Handels Heinz, Ehrhardt Jan},
faupublication = {yes},
pages = {409-413},
peerreviewed = {No},
publisher = {Springer},
title = {{Automatic} {Patient} {Pose} {Estimation} {Using} {Pressure} {Sensing} {Mattresses}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Grimm11-APP.pdf},
venue = {Lübeck},
year = {2011}
}
@inproceedings{faucris.123543024,
abstract = {Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.},
author = {Bocklet, Tobias and Riedhammer, Korbinian Thomas and Eysholdt, Ulrich and Nöth, Elmar},
faupublication = {yes},
keywords = {Pathology;automatic assessment;spectral features;GMM;fMLLR},
month = {Jan},
pages = {7572-7576},
peerreviewed = {unknown},
title = {{AUTOMATIC} {PHONEME} {ANALYSIS} {IN} {CHILDREN} {WITH} {CLEFT} {LIP} {AND} {PALATE}},
year = {2013}
}
@article{faucris.110719664,
author = {Sindran, Fadi and Mualla, Firas and Haderlein, Tino and Daqrouq, Khaled and Nöth, Elmar},
faupublication = {yes},
journal = {International Journal of Computational Linguistics},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.automa{\_}8},
pages = {38-53},
peerreviewed = {Yes},
title = {{Automatic} {Phonetization}-based {Statistical} {Linguistic} {Study} of {Standard} {Arabic}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Sindran16-APS.pdf},
volume = {7},
year = {2016}
}
@inproceedings{faucris.255673258,
author = {Martín Vicario, Celia and Kordon, Florian Johannes and Denzinger, Felix and Weiten, Markus and Thomas, Sarina and Kausch, Lisa and Franke, Jochen and Keil, Holger and Maier, Andreas and Kunze, Holger},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}40},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-19},
pages = {170-},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Automatic} {Plane} {Adjustment} in {Surgical} {Cone} {Beam} {CT}-volumes},
venue = {Regensburg},
year = {2021}
}
@article{faucris.117697624,
author = {Koch, Martin and Brost, Alexander and Bourier, Felix and Hornegger, Joachim and Strobel, Norbert},
doi = {10.1117/1.JMI.1.1.015002},
faupublication = {yes},
journal = {Journal of Medical Imaging},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.automa{\_}7},
pages = {015002},
peerreviewed = {Yes},
title = {{Automatic} planning of atrial fibrillation ablation lines using landmark-constrained nonrigid registration},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Koch14-APO.pdf},
volume = {1},
year = {2014}
}
@inproceedings{faucris.108713264,
address = {Cham, Switzerland},
author = {Sindran, Fadi and Mualla, Firas and Haderlein, Tino and Daqrouq, Khaled and Nöth, Elmar},
booktitle = {Proc. Text, Speech and Dialogue; 20th International Conference, TSD 2017},
date = {2017-08-27/2017-08-31},
doi = {10.1007/978-3-319-64206-2{\_}23},
faupublication = {yes},
isbn = {978-3-319-64205-5},
keywords = {Allophones; Diphones; Linguistic content; Phonetically rich; SA written corpora},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.automa{\_}11},
pages = {201-209},
peerreviewed = {Yes},
publisher = {Springer International Publishing},
series = {LNAI},
title = {{Automatic} {Preparation} of {Standard} {Arabic} {Phonetically} {Rich} {Written} {Corpora} with {Different} {Linguistic} {Units}},
venue = {Prague, Czech Republic},
volume = {10415},
year = {2017}
}
@book{faucris.312790649,
author = {Rios-Urrego, Cristian David and Escobar-Grisales, Daniel and Moreno-Acevedo, Santiago Andres and Pérez Toro, Paula Andrea and Nöth, Elmar and Orozco Arroyave, Juan Rafael},
doi = {10.1007/978-3-031-40498-6{\_}30},
faupublication = {no},
isbn = {9783031404979},
keywords = {English; Pronunciation assessment; Phonological Analysis; Speech},
pages = {339-348},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Automatic} {Pronunciation} {Assessment} of {Non}-native {English} {Based} on {Phonological} {Analysis}},
year = {2023}
}
@article{faucris.121330484,
author = {Cincarek, Tobias and Gruhn, Rainer and Hacker, Christian and Nöth, Elmar and Nakamura, Satoshi},
doi = {10.1016/j.csl.2008.03.001},
faupublication = {yes},
journal = {Computer Speech and Language},
pages = {65-88},
peerreviewed = {Yes},
title = {{Automatic} {Pronunciation} {Scoring} of {Words} and {Sentences} {Independent} from the {Non}-{Native}'s {First} {Language}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Cincarek09-APS.pdf},
volume = {23},
year = {2009}
}
@article{faucris.108117724,
author = {Stelzle, Florian and Maier, Andreas and Nöth, Elmar and Bocklet, Tobias and Knipfer, Christian and Schuster, Maria and Neukam, Friedrich Wilhelm and Nkenke, Emeka},
doi = {10.1016/j.joms.2010.05.077},
faupublication = {yes},
journal = {Journal of Maxillofacial and Oral Surgery},
pages = {1493-1500},
peerreviewed = {unknown},
title = {{Automatic} {Quantification} of {Speech} {Intelligibility} in {Patients} after {Treatment} for {Oral} {Squamous} {Cell} {Carcinoma}},
volume = {69.0},
year = {2011}
}
@article{faucris.111851124,
author = {Windrich, Martin and Maier, Andreas and Kohler, Regina and Nöth, Elmar and Nkenke, Emeka and Eysholdt, Ulrich and Schuster, Maria},
doi = {10.1159/000121004},
faupublication = {yes},
journal = {Folia Phoniatrica Et Logopaedica},
pages = {151-156},
peerreviewed = {Yes},
title = {{Automatic} {Quantification} of {Speech} {Intelligibility} of {Adults} with {Oral} {Squamous} {Cell} {Carcinoma}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Windrich08-AQO.pdf},
volume = {60/2008},
year = {2008}
}
@inproceedings{faucris.121345004,
address = {Berlin, Heidelberg},
author = {Haderlein, Tino and Moers, Cornelia and Möbius, Bernd and Nöth, Elmar},
booktitle = {Proc. Text, Speech and Dialogue; 15th International Conference, TSD 2012},
date = {2012-09-03/2012-09-07},
doi = {10.1007/978-3-642-32790-2},
editor = {Sojka Petr, Horak Ales, Kopecek Ivan, Pala Karel},
faupublication = {yes},
pages = {573-580},
publisher = {Springer-Verlag},
title = {{Automatic} {Rating} of {Hoarseness} by {Text}-based {Cepstral} and {Prosodic} {Evaluation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Haderlein12-ARO.pdf},
venue = {Brno},
year = {2012}
}
@inproceedings{faucris.121380424,
abstract = {
Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after laryngectomy, i.e. the removal of the larynx. TE speech often shows low audibility and intelligibility which also makes it a challenge to automatic speech recognition. We improved the recognition results by adapting a speech recognizer trained on normal, non-pathologic voices to single TE speakers by unsupervised HMM interpolation. In speech rehabilitation the patient’s voice quality has to be evaluated. As no objective classification means exists until now and an automation of this procedure is desirable we performed initial experiments for automatic evaluation of the intelligibility. We compared scoring results for TE speech from five experienced raters with the word accuracy from different types of speech recognizers. Correlation coefficients of about -0.8 are promising for future work.
},
address = {Berlin, Heidelberg},
author = {Haderlein, Tino and Steidl, Stefan and Nöth, Elmar and Rosanowski, Frank and Schuster, Maria},
booktitle = {Proc. Text, Speech and Dialogue; 7th International Conference, TSD 2004},
date = {2004-09-08/2004-09-11},
editor = {Sojka P., Kopecek I., Pala K.},
faupublication = {yes},
pages = {331-338},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Automatic} {Recognition} and {Evaluation} of {Tracheoesophageal} {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Haderlein04-ARA.pdf},
venue = {Brno},
year = {2004}
}
@inproceedings{faucris.106575964,
abstract = {Diagnosis and severity staging of Parkinsons disease (PD) relies mainly on subjective clinical examination. To better monitor disease progression and therapy success in PD patients, new objective and rater independent parameters are required. Surface electromyography (EMG) during dynamic movements is one possible modality. However, EMG signals are often difficult to understand and interpret clinically. In this study pattern recognition was applied to find suitable parameters to differentiate PD patients from healthy controls. EMG signals were recorded from 5 patients with PD and 5 younger healthy controls, while performing a series of standardized gait tests. Wireless surface electrodes were placed bilaterally on tibialis anterior and gastrocnemius medialis and lateralis. Accelerometers were positioned on both heels and used for step segmentation. Statistical and frequency features were extracted and used to train a Support Vector Machine classifier. Sensitivity and specificity were high at 0.90 using leave-one-subject-out cross-validation. Feature selection revealed kurtosis and mean frequency as best features, with a significant difference in kurtosis (p=0.013). Evaluated on a bigger population, this could lead to objective diagnostic and staging tools for P},
author = {Kugler, Patrick and Jaremenko, Christian and Schlachetzki, Johannes and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn},
booktitle = {Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE},
date = {2013-07-03/2013-07-07},
doi = {10.1109/EMBC.2013.6610865},
editor = {IEEE Engineering in Medicine and Biology Society},
faupublication = {yes},
pages = {5781-5784},
peerreviewed = {unknown},
title = {{Automatic} {Recognition} of {Parkinson}s {Disease} {Using} {Surface} {Electromyography} {During} {Standardized} {Gait} {Tests}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Kugler13-ARO.pdf},
venue = {Osaka, Japan},
year = {2013}
}
@inproceedings{faucris.118455744,
abstract = {In computed tomography fiducial markers are frequently used to obtain accurate point correspondences for further processing. These markers typically cause metal artefacts, decreasing image quality of the subsequent reconstruction and are therefore often removed from the projection data. The placement of such markers is usually done on a surface, separating two materials, e.g. skin and air. Hence, a correct restoration of the occluded area is difficult. In this work six state-of-the-art interpolation techniques for the removal of high-density fiducial markers from cone-beam CT projection data are compared. We conducted a qualitative and quantitative evaluation for the removal of such markers and the ability to reconstruct the adjoining edge. Results indicate that an iterative spectral deconvolution is best suited for this application, showing promising results in terms of edge, as well as noise restoration.},
author = {Berger, Martin and Forman, Christoph and Schwemmer, Chris and Choi, Jang-Hwan and Müller, Kerstin and Maier, Andreas and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Bildverarbeitung für die Medizin 2014},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}59},
faupublication = {yes},
isbn = {9783642541100},
keywords = {GRK-1773; Interpolation; C-arm CT; Metal Artifact},
note = {UnivIS-Import:2015-07-08:Pub.2014.tech.IMMD.IMMD5.automa{\_}5},
pages = {168-173},
publisher = {Kluwer Academic Publishers},
title = {{Automatic} {Removal} of {Externally} {Attached} {Fiducial} {Markers} in {Cone} {Beam} {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Berger14-ARO.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.115533264,
abstract = {Phonetization is the process of encoding language sounds using phonetic symbols. It is used in many natural language processing tasks such as speech processing, speech synthesis, and computer-aided pronunciation assessment. A common phonetization approach is the use of letter-to-sound rules developed by linguists for the transcription form orthography to sound. In this paper, we address the problem of rule-based phonetization of standard Arabic. The paper contributions can be summarized as follows: 1) Discussing the transcription rules of standard Arabic which were used in literature on the phonemic and phonetic levels. 2) Important improvements of these rules were suggested and the resulting rules set was tested on large datasets. 3) We present a reliable automatic phonetic transcription of standard Arabic on five levels: phoneme, allophone, syllable, word, and sentence. An encoding which covers all sounds of standard Arabic is proposed and several pronunciation dictionaries were automatically generated. These dictionaries were manually verified yielding an accuracy of 100% with standard Arabic texts that do not contain dates, numbers, acronyms, abbreviations, and special symbols. They are available for research purposes along with the software package which performs the automatic transcription.},
author = {Sindran, Fadi and Mualla, Firas and Bobzin, Katharina and Nöth, Elmar},
doi = {10.1007/978-3-319-24033-6{\_}50},
faupublication = {yes},
keywords = {Standard Arabic;Phonetic transcription;Pronunciation dictionaries;Transcription rules},
month = {Jan},
pages = {442-451},
peerreviewed = {unknown},
publisher = {Springer-verlag},
title = {{Automatic} {Robust} {Rule}-{Based} {Phonetization} of {Standard} {Arabic}},
volume = {9302},
year = {2015}
}
@inproceedings{faucris.113151984,
address = {Bonn},
author = {Maier, Andreas and Schuster, Maria and Batliner, Anton and Nöth, Elmar and Nkenke, Emeka},
booktitle = {Interspeech 2007},
date = {2007-08-27/2007-08-31},
editor = {Interspeech},
faupublication = {yes},
pages = {1206-1209},
peerreviewed = {Yes},
publisher = {Uni Bonn},
title = {{Automatic} {Scoring} of the {Intelligibility} in {Patients} with {Cancer} of the {Oral} {Cavity}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Maier07-ASO.pdf},
venue = {Antwerpen},
year = {2007}
}
@inproceedings{faucris.108178884,
address = {Portugal},
author = {El-Rafei, Ahmed Mohamed Ibrahim and Hornegger, Joachim and Engelhorn, Tobias and Dörfler, Arnd and Wärntges, Simone and Michelson, Georg},
booktitle = {Computational Vision and Medical Image Processing - VipIMAGE 2009},
date = {2009-10-14/2009-10-16},
editor = {Tavares João Manuel R.S., Jorge R.M. Natal},
faupublication = {yes},
pages = {293-298},
peerreviewed = {unknown},
publisher = {Taylor and Francis},
title = {{Automatic} {Segmentation} of the {Optic} {Radiation} using {DTI} in {Glaucoma} {Patients}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Elrafei09-ASO.pdf},
venue = {Porto},
year = {2009}
}
@article{faucris.121406604,
author = {El-Rafei, Ahmed Mohamed Ibrahim and Engelhorn, Tobias and Wärntges, Simone and Dörfler, Arnd and Hornegger, Joachim and Michelson, Georg},
faupublication = {yes},
journal = {Computational Vision and Medical Image Processing},
pages = {1-15},
peerreviewed = {Yes},
title = {{Automatic} {Segmentation} of the {Optic} {Radiation} {Using} {DTI} in {Healthy} {Subjects} and {Patients} with {Glaucoma}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Elrafei11-ASO.pdf},
volume = {19.0},
year = {2011}
}
@inproceedings{faucris.121429924,
author = {Bocklet, Tobias and Stelzle, Florian and Haderlein, Tino and Nöth, Elmar},
booktitle = {Proceedings of the 9th International Conference on Advances in Quantitative Laryngology, Voice and Speech Research},
date = {2010-09-10/2010-09-11},
editor = {Michael Doellinger},
faupublication = {yes},
pages = {42.0},
title = {{Automatic} speech recognition for edentulous speakers with insufficient dentures},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Bocklet10-ASR.pdf},
venue = {Erlangen},
year = {2010}
}
@article{faucris.121356664,
author = {Maier, Andreas and Haderlein, Tino and Stelzle, Florian and Nöth, Elmar and Nkenke, Emeka and Rosanowski, Frank and Schützenberger, Anne and Schuster, Maria},
doi = {10.1155/2010/926951},
faupublication = {yes},
journal = {EURASIP Journal on Audio, Speech, and Music Processing},
pages = {-},
peerreviewed = {Yes},
title = {{Automatic} {Speech} {Recognition} {Systems} for the {Evaluation} of {Voice} and {Speech} {Disorders} in {Head} and {Neck} {Cancer}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Maier10-ASR.pdf},
year = {2010}
}
@inproceedings{faucris.107008044,
address = {-},
author = {Nöth, Elmar and Niemann, Heinrich and Haderlein, Tino and Decher, Michael and Eysholdt, Ulrich and Rosanowski, Frank and Wittenberg, Thomas},
booktitle = {Proc. Int. Conf. on Spoken Language Processing},
date = {2000-10-16/2000-10-20},
editor = {Yuan B., Huang T., Tang X.},
faupublication = {yes},
pages = {65-68},
publisher = {China Military Friendship Publish},
title = {{Automatic} {Stuttering} {Recognition} using {Hidden} {Markov} {Models}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2000/Noeth00-ASR.pdf},
venue = {Beijing},
year = {2000}
}
@inproceedings{faucris.121222684,
abstract = {Registration of an individual's image data set to an anatomical atlas provides valuable information to the physician. In many cases, the individual image data sets are partial data, which may be mapped to one part or one organ of the entire atlas data. Most of the existing intensity based image registration approaches are designed to align images of the entire view. When they are applied to the registration with partial data, a manual pre-registration is usually required. This paper proposes a fully automatic approach to the registration of the incomplete image data to an anatomical atlas. The spatial transformations are modelled as any parametric functions. The proposed method is built upon a random search mechanism, which allows to find the optimal transformation randomly and globally even when the initialization is not ideal. It works more reliably than the existing methods for the partial data registration because it successfully overcomes the local optimum problem. With appropriate similarity measures, this framework is applicable to both mono-modal and multi-modal registration problems with partial data. The contribution of this work is the description of the mathematical framework of the proposed algorithm and the implementation of the related software. The medical evaluation on the MRI data and the comparison of the proposed method with different existing registration methods show the feasibility and superiority of the proposed method.},
author = {Han, Jingfeng and Qiao, Min and Hornegger, Joachim and Kuwert, Torsten and Bautz, Werner and Römer, Wolfgang},
booktitle = {Medical Imaging 2006: Image Processing},
doi = {10.1117/12.652281},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Automatic} sub-volume registration by probabilistic random search},
venue = {San Diego, CA},
volume = {null},
year = {2006}
}
@inproceedings{faucris.111341164,
author = {Löber, Patrick and Stimpel, Bernhard and Syben-Leisner, Christopher and Maier, Andreas and Ditt, Hendrik and Schramm, Peter and Raczkowski, Boy and Kemmling, Andre},
booktitle = {Eurographics Proceedings 2017},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.automa{\_}9},
pages = {125-129},
peerreviewed = {unknown},
title = {{Automatic} thrombus detection in non-enhanced computed tomography images in patients with acute ischemic stroke},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Loeber17-ATD.pdf},
venue = {Bremen, Deutschland},
year = {2017}
}
@phdthesis{faucris.203751840,
abstract = {Bright field microscopy is preferred over other microscopic imaging modalities whenever ease of implementation and minimization of expenditure are main concerns. This simplicity in hardware comes at the cost of image quality yielding images of low contrast. While staining can be employed to improve the contrast, it may complicate the experimental setup and cause undesired side effects on the cells. In this thesis, we tackle the problem of automatic cell detection in bright field images of unstained cells. The research was done in context of the interdisciplinary research project COSIR. COSIR aimed at developing a novel microscopic hardware having the following feature: the device can be placed in an incubator so that cells can be cultivated and observed in a controlled environment. In order to cope with design difficulties and manufacturing costs, the bright field technique was chosen for implementing the hardware. The contributions of this work are briefly outlined in the text which follows.
An automatic cell detection pipeline was developed based on supervised learning. It employs Scale Invariant Feature Transform (SIFT) keypoints, random forests, and agglomerative hierarchical clustering (AHC) in order to reliably detect cells. A keypoint classifier is first used to classify keypoints into cell and background. An intensity profile is extracted between each two nearby cell keypoints and a profile classifier is then utilized to classify the two keypoints whether they belong to the same cell (inner profile) or to different cells (cross profile). This two-classifiers approach was used in the literature. The proposed method, however, compares to the state-of-the-art as follows: 1) It yields high detection accuracy (at least 14% improvement compared to baseline bright field methods) in a fully-automatic manner with short runtime on the low-contrast bright field images. 2) Adaptation of standard features in literature from being pixel-based to adopting a keypoint-based extraction scheme: this scheme is sparse, scale-invariant, orientation-invariant, and feature parameters can be tailored in a meaningful way based on a relevant keypoint scale and orientation.
3) The pipeline is highly invariant with respect to illumination artifacts, noise, scale and orientation changes. 4) The probabilistic output of the profile classifier is used as input for an AHC step which improves detection accuracy. A novel linkage method was proposed which incorporates the information of SIFT keypoints into the linkage. This method was proved to be combinatorial, and thus, it can be computed efficiently in a recursive manner.
Due to the substantial difference in contrast and visual appearance between suspended and adherent cells, the above-mentioned pipeline attains higher accuracy in separate learning of suspended and adherent cells compared to joint learning. Separate learning refers to the situation when training and testing are done either only on suspended cells or only on adherent cells. On the other hand, joint learning refers to training the algorithm to detect cells in images which contain both suspended and adherent cells. Since these two types of cells coexist in cell cultures with shades of gray between the two terminal cases, it is of practical importance to improve joint learning accuracy. We showed that this can be achieved using two types of phase-based features: 1) physical light phase obtained by solving the transport of intensity equation, 2) monogenic local phase obtained from a low-passed axial derivative image.
In addition to the supervised cell detection discussed so far, a cell detection approach based on unsupervised learning was proposed. Technically speaking, supervised learning was utilized in this approach as well. However, instead of training the profile classifier using manually-labeled ground truth, a self-labeling algorithm was proposed with which ground truth labels can be automatically generated from cells and keypoints in the input image itself. The algorithm learns from extreme cases and applies the learned model on the intermediate ones. SIFT keypoints were successfully employed for unsupervised structure-of-interest measurements in cell images such as mean structure size and dominant curvature direction. Based on these measurements, it was possible to define the notion of extreme cases in a way which is independent from image resolution and cell type.
To facilitate comprehensive studies, this paper introduces the publicly available Super-Resolution Erlangen (SupER) database that includes real low-resolution images along with high-resolution ground truth data. Our database comprises image sequences with more than 20k images captured from 14 scenes under various types of motions and photometric conditions. The datasets cover four spatial resolution levels using camera hardware binning. With this database, we benchmark 15 single-image and multi-frame SR algorithms. Our experiments quantitatively analyze SR accuracy and robustness under realistic conditions including independent object and camera motion or photometric variation},
author = {Köhler, Thomas and Bätz, Michel and Naderi Boldaji, Farzad and Kaup, André and Maier, Andreas and Riess, Christian},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Benchmarking} {Super}-{Resolution} {Algorithms} on {Real} {Data}},
url = {http://arxiv.org/abs/1709.04881},
year = {2017}
}
@inproceedings{faucris.107363564,
author = {Grimm, Robert and Block, Kai Tobias and Kiefer, Berthold and Hornegger, Joachim},
booktitle = {Proceedings of International Society for Magnetic Resonance in Medicine},
date = {2011-05-07/2011-05-13},
faupublication = {yes},
pages = {2677},
peerreviewed = {unknown},
title = {{Bias} {Correction} for {Respiration} {Detection} in {Radial} {3D} {Gradient}-{Echo} {Imaging}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Grimm11-BCF.pdf},
venue = {Montréal},
year = {2011}
}
@inproceedings{faucris.230328122,
abstract = {This paper describes a problem in a reported Dynamic Time Warping (DTW) alignment procedure to compare the reference and detected glottal pulse length sequences, oriented to compare the evaluation of Pitch Detection Algorithms (PDAs) in pathological voices. The problem in the existing alignment method tends to overestimate the failure of the PDA, by aligning only the detected to the reference sequence. A solution is presented, which performs a bidirectional alignment reducing the differences present in the definitive comparison. The proposal is evaluated in both synthetic and real voice signals, by running three well-known PDAs, and the magnitude of the error reduction along with comments on the possible factors influencing its value, are given. The alignment variant introduced in this paper allows to perform a fairer comparison of the PDAs performances.},
author = {Ferrer, Carlos A. and Guillén, Reinier Rodríguez and Nöth, Elmar},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2019-10-28/2019-10-31},
doi = {10.1007/978-3-030-33904-3{\_}67},
editor = {Ingela Nyström, Yanio Hernández Heredia, Vladimir Milián Núñez},
faupublication = {yes},
isbn = {9783030339036},
keywords = {Alignment; Dynamic Time Warping; Jitter; Pitch Detection Algorithms},
note = {CRIS-Team Scopus Importer:2019-12-10},
pages = {707-716},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Bidirectional} {Alignment} of {Glottal} {Pulse} {Length} {Sequences} for the {Evaluation} of {Pitch} {Detection} {Algorithms}},
venue = {Havana, CUB},
volume = {11896 LNCS},
year = {2019}
}
@inproceedings{faucris.107379404,
author = {Köhler, Thomas and Maier, Andreas and Christlein, Vincent},
booktitle = {Pattern Recognition},
doi = {10.1007/978-3-319-24947-6{\_}8},
faupublication = {yes},
isbn = {978-3-319-24947-6},
note = {UnivIS-Import:2015-11-17:Pub.2015.tech.IMMD.IMMD5.binari{\_}4},
pages = {91-102},
peerreviewed = {Yes},
title = {{Binarization} {Driven} {Blind} {Deconvolution} for {Document} {Image} {Restoration}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Köhler15-BDB.pdf},
venue = {RWTH Aachen},
year = {2015}
}
@misc{faucris.121320364,
author = {Weber, Stefan and Schnörr, Christoph and Schüle, Thomas and Hornegger, Joachim},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Binary} {Tomography} by {Iterating} {Linear} {Programs}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Weber05-BTB.pdf},
year = {2005}
}
@book{faucris.111821204,
abstract = {In this paper we improve the behavior of a reconstruction algorithm for binary tomography in the presence of noise. This algorithm which has recently been published is derived from a primal-dual subgradient method leading to a sequence of linear programs. The objective function contains a smoothness prior that favors spatially homogeneous solutions and a concave functional gradually enforcing binary solutions. We complement the objective function with a term to cope with noisy projections and evaluate its performance. © Springer-Verlag 2004.},
author = {Weber, Stefan and Schüle, Thomas and Hornegger, Joachim and Schnörr, Christoph},
doi = {10.1007/978-3-540-30503-3{\_}3},
faupublication = {yes},
pages = {38-51},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Binary} tomography by iterating linear programs from noisy projections},
volume = {3322},
year = {2004}
}
@inproceedings{faucris.116401824,
abstract = {In this paper we improve the behavior of a reconstruction algorithm for binary tomography in the presence of noise. This algorithm which has recently been published is derived from a primal-dual subgradient method leading to a sequence of linear programs. The objective function contains a smoothness prior that favors spatially homogeneous solutions and a concave functional gradually enforcing binary solutions. We complement the objective function with a term to cope with noisy projections and evaluate its performance. © Springer-Verlag 2004.},
address = {Berlin},
author = {Weber, Stefan and Schüle, Thomas and Hornegger, Joachim and Schnörr, Christoph},
booktitle = {Proceedings of International Workshop on Combinatorial Image Analysis (IWCIA)},
faupublication = {yes},
keywords = {Discrete Tomography; Combinatorial Optimization; Linear},
note = {UnivIS-Import:2015-04-16:Pub.2004.tech.IMMD.IMMD5.binary},
pages = {38-51},
peerreviewed = {unknown},
publisher = {Springer-verlag},
title = {{Binary} {Tomography} by {Iterating} {Linear} {Programs} from {Noisy} {Projections}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Weber04-BTB.pdf},
venue = {Auckland},
year = {2004}
}
@inproceedings{faucris.121165704,
abstract = {Parkinson's disease (PD) is the most frequent neurodegenerative movement disorder. Early diagnosis and effective therapy monitoring is an important prerequisite to treat patients and reduce health care costs. Objective and non-invasive assessment strategies are an urgent need in order to achieve this goal. In this study we apply a mobile, lightweight and easy applicable sensor based gait analysis system to measure gait patterns in PD and to distinguish mild and severe impairment of gait. Examinations of 16 healthy controls, 14 PD patients in an early stage, and 13 PD patients in an intermediate stage were included. Subjects performed standardized gait tests while wearing sport shoes equipped with inertial sensors (gyroscopes and accelerometers). Signals were recorded wirelessly, features were extracted, and distinct subpopulations classified using different classification algorithms. The presented system is able to classify patients and controls (for early diagnosis) with a sensitivity of 88% and a specificity of 86%. In addition it is possible to distinguish mild from severe gait impairment (for therapy monitoring) with 100% sensitivity and 100% specificity. This system may be able to objectively classify PD gait patterns providing important and complementary information for patients, caregivers and therapists. © 2011 IEEE.},
author = {Barth, Jens and Klucken, Jochen and Kugler, Patrick and Kammerer, Thomas and Steidl, Ralph and Winkler, Jürgen and Hornegger, Joachim and Eskofier, Björn},
booktitle = {Engineering in Medicine and Biology Society,EMBC, 2011 Annual International Conference of the IEEE},
date = {2011-08-30/2011-09-03},
doi = {10.1109/IEMBS.2011.6090226},
faupublication = {yes},
pages = {868-871},
peerreviewed = {unknown},
title = {{Biometric} and {Mobile} {Gait} {Analysis} for {Early} {Detection} and {Therapy} {Monitoring} in {Parkinson}'s {Disease}},
venue = {Boston, MA},
volume = {null},
year = {2011}
}
@inproceedings{faucris.121379984,
address = {Erlangen},
author = {Scherl, Holger and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {Frontiers in Simulation},
date = {2005-09-12/2005-09-15},
editor = {Hülsemann Frank, Kowarschik Markus, Rüde Ulrich},
faupublication = {yes},
pages = {662-667},
peerreviewed = {unknown},
publisher = {SCS Publishing House e.V.},
title = {{Bit}-{Accurate} {Simulation} of {Convolution}-{Based} {Filtering} on {Reconfigurable} {Hardware}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Scherl05-BSO.pdf},
venue = {Erlangen},
year = {2005}
}
@inproceedings{faucris.291298119,
abstract = {In this paper a blood flow quantification method that is based on a physically motivated dense 2D flow estimation algorithm is outlined. It yields accurate time varying volumetric flow rate measurements based on digital subtraction angiography (DSA) image sequences, with robustness to significant inter-frame displacements. Time varying volumetric flow rates are estimated for individual non-branching vascular segments based on the estimated 2D flow fields and a 3D vessel segmentation from a 3D Rotational Angiography (3DRA) acquisition. The novelty of the approach lies in the use of a vessel aligned coordinate system for the problem formulation. The coordinate functions are generated using the Schwarz-Christoffel1(SC) map that yields a solution with coordinate lines aligned with the vessel boundaries. The use of vessel aligned coordinates enables the easy and accurate handling of boundary conditions in the irregular domain of a vessel lumen while only requiring slight modifications to the used finite difference approach. Unlike traditional coarse to fine methods we use an anisotropic scaling strategy that enables the estimation of flows with larger inter frame displacements. The evaluation of our method is based on highly realistic synthetic DSA datasets for a number of cases. Ground truth volumetric flow rate values are compared against the measurements and a high degree of fidelity is observed. Performance measures are obtained with varying flow velocities and acquisition rates. © 2014 SPIE.},
author = {Maday, Peter and Brosig, Richard and Endres, Jürgen and Kowarschik, Markus and Navab, Nassir},
booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
date = {2014-02-16/2014-02-18},
doi = {10.1117/12.2043408},
faupublication = {no},
isbn = {9780819498274},
note = {CRIS-Team Scopus Importer:2023-03-08},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{Blood} flow quantification using optical flow methods in a body fitted coordinate system},
venue = {USA},
volume = {9034},
year = {2014}
}
@inproceedings{faucris.118009364,
abstract = {In this paper we present a new method for automatic object detection in images and video sequences. As a classifier the popular AdaBoost algorithm is used, that combines several weak classifiers into one strong classifier. To create a detector based on this classifier, the weak classifiers are set into relation during boosting by using a geometric model. All votes of the weak detectors are evaluated in a voting space. The voting space allows a detection with combinations of different object features. We trained and tested the proposed method with SIFT and kAS features and combinations of these. The learned detector is then used to localize objects in images and video sequences. The performance of the algorithm is examined based on selected image data. © 2011 IEE},
author = {Quast, Katharina and Seeger, Christoph and Trivedi, Mohan and Kaup, André},
booktitle = {2011 18th IEEE International Conference on Image Processing, ICIP 2011},
date = {2011-09-11/2011-09-14},
doi = {10.1109/ICIP.2011.6116487},
faupublication = {yes},
isbn = {9781457713033},
keywords = {boosting; object detection; Object recognition},
pages = {3630-3633},
peerreviewed = {Yes},
title = {{Boosting} based object detection using a geometric model},
venue = {Brussels},
year = {2011}
}
@phdthesis{faucris.116766144,
abstract = {Over the past decades, huge progress has been made in treatment of cancer, decreasing fatality rates despite a growing number of cases. Technical achievements had a big share in this development.
With modern image acquisition techniques, most types of tumors can be made visible.
Automatic processing of these images to support diagnosis and therapy, on the other hand, is still very basic. Marking lesions for volume measurements, intervention planning or tracking over time requires a lot of manual interaction, which is both tedious and error prone.
The work at hand therefore aims at providing tools for the automatic segmentation of
liver lesions. A system is presented that receives a contrast enhanced CT image of the liver as input and, after several preprocessing steps, decides for each image voxel inside the liver whether it belongs to a tumor or not. That way, tumors are not only detected in the image but also precisely delineated in three dimensions. For the decision step, which is the main target of this thesis, we adopted the recently proposed Probabilistic Boosting Tree. In an offline learning phase, this classifier is trained using a number of example images. After training, it can process new and previously unseen images.
Such automatic segmentation systems are particularly valuable when it comes to monitoring tumors of a patient over a longer period of time. Therefore, we propose a method for
learning a prior model to improve segmentation accuracy for such follow-up examinations.
It is learned from a number of series of CT images, where each series contains images of
one patient. Two different ways of incorporating the model into the segmentation system are investigated. When acquiring an image of a patient, the system can use the model to calculate a patient specific lesion prior from images of the same patient acquired earlier
and thus guide the segmentation in the current image.
The validity of this approach is shown in a set of experiments on clinical images. When comparing the points of 90% sensitivity in these experiments, incorporating the prior improved the precision of the segmentation from 82.7% to 91.9%. This corresponds to a
reduction of the number of false positive voxels per true positive voxel by 57.8%.
Finally, we address the issue of long processing times of classification based segmentation systems. During training, the Probabilistic Boosting Tree builds up a hierarchy of AdaBoost classifiers. In order to speed up classification during application phase, we modify this hierarchy so that simpler and thus faster AdaBoost classifiers are used in higher levels. To this end, we introduce a cost term into AdaBoost training that trades off discriminative
power and computational complexity during feature selection. That way the
optimization process can be guided to build less complex classifiers for higher levels of the tree and more complex and thus stronger ones for deeper levels. Results of an experimental evaluation on clinical images are presented, which show that this mechanism can reduce
the overall cost during application phase by up to 76% without degrading classification accuracy.
It is also shown that this mechanism could be used to optimize arbitrary secondary
conditions during AdaBoost training.
Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after laryngectomy. TE speech often shows low intelligibility. An objective means to determine and quantify the intelligibility does not exist until now and an automation of this procedure is desirable. We used a speech recognizer trained on normal, non–pathologic voices. We compared intelligibility scores for TE speech from five experienced raters with the word accuracy (WA) of our speech recognizer. A correlation coefficient of -.84 shows that WA can be a good indicator of intelligibility for pathologic voices. An outlook for future work is presented.
},
author = {Schuster, Maria and Nöth, Elmar and Haderlein, Tino and Steidl, Stefan and Batliner, Anton and Rosanowski, Frank},
booktitle = {Proceedings of ICASSP 2005 - International Conference on Acoustics, Speech, and Signal Processing},
date = {2005-03-18/2005-03-23},
editor = {IEEE},
faupublication = {yes},
pages = {61-64},
peerreviewed = {Yes},
title = {{Can} you {Understand} him? {Let}'s {Look} at his {Word} {Accuracy} - {Automatic} {Evaluation} of {Tracheoesophageal} {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Schuster05-CYU.pdf},
venue = {Philadelphia},
year = {2005}
}
@inproceedings{faucris.121218504,
abstract = {The combination of real-time fluoroscopy and 3D cardiac imaging on the same C-arm system is a promising technique that might improve therapy planning, guiding, and monitoring in the interventional suite. In principal, to reconstruct a 3D image of the beating heart at a particular cardiac phase, a complete set of X-ray projection data representing that phase is required. One approximate approach is the retrospectively ECG-gated FDK reconstruction (RG-FDK). From the acquired data set of N multiple C-arm sweeps, those projection images which are acquired closest in time to the desired cardiac phase are retrospectively selected. However, this approach uses only 1/N of the obtained data. Our goal is to utilize data from other cardiac phases as well. In order to minimize blurring and motion artifacts, cardiac motion has to be compensated for, which can be achieved using a temporally dependent spatial 3D warping of the filtered-backprojections. In this work we investigate the computation of the 4D heart motion based on prior reconstructions of several cardiac phases using RG-FDK. A 4D motion estimation framework is presented using standard fast non-rigid registration. A smooth 4D motion vector field (MVF) represents the relative deformation compared to a reference cardiac phase. A 4D deformation regridding by adaptive supersampling allows selecting any reference phase independently of the set of phases used in the RG-FDK for a motion corrected reconstruction. Initial promising results from in vivo experiments are shown. The subjects individual 4D cardiac MVF could be computed from only three RG-FDK image volumes. In addition, all acquired projection data were motion corrected and subsequently used for image reconstruction to improve the signal-to-noise ratio compared to RG-FDK.},
author = {Prümmer, Marcus and Fahrig, Rebecca and Wigström, Lars and Boese, Jan and Lauritsch, Günter and Strobel, Norbert and Hornegger, Joachim},
booktitle = {Medical Imaging 2007: Physics of Medical Imaging},
doi = {10.1117/12.708151},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Cardiac} {C}-arm {CT}: {4D} non-model based heart motion estimation and its application},
venue = {San Diego, CA},
volume = {6510},
year = {2007}
}
@article{faucris.121198924,
abstract = {Generating 3-D images of the heart during interventional procedures is a significant challenge. In addition to real time fluoroscopy, angiographic C-arm systems can also now be used to generate 3-D/4-D CT images on the same system. One protocol for cardiac CT uses ECG triggered multisweep scans. A 3-D volume of the heart at a particular cardiac phase is then reconstructed by applying Feldkamp (FDK) reconstruction to the projection images with retrospective ECG gating. In this work we introduce a unified framework for heart motion estimation and dynamic cone-beam reconstruction using motion corrections. The benefits of motion correction are 1) increased temporal and spatial resolution by removing cardiac motion which may still exist in the ECG gated data sets and 2) increased signal-to-noise ratio (SNR) by using more projection data than is used in standard ECG gated methods. Three signal-enhanced reconstruction methods are introduced that make use of all of the acquired projection data to generate a 3-D reconstruction of the desired cardiac phase. The first averages all motion corrected back-projections; the second and third perform a weighted averaging according to 1) intensity variations and 2) temporal distance relative to a time resolved and motion corrected reference FDK reconstruction. In a comparison study seven methods are compared: nongated FDK, ECG-gated FDK, ECG-gated, and motion corrected FDK, the three signal-enhanced approaches, and temporally aligned and averaged ECG-gated FDK reconstructions. The quality measures used for comparison are spatial resolution and SNR. Evaluation is performed using phantom data and animal models. We show that data driven and subject-specific motion estimation combined with motion correction can decrease motion-related blurring substantially. Furthermore, SNR can be increased by up to 70% while maintaining spatial resolution at the same level as is provided by the ECG-gated FDK. The presented framework provides excellent image quality for cardiac C-arm CT. © 2009 IEEE.},
author = {Prümmer, Marcus and Hornegger, Joachim and Lauritsch, Günter and Wigstroem, Lars and Girard-Hughes, Erin and Fahrig, Rebecca},
doi = {10.1109/TMI.2009.2025499},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
pages = {1836-1849},
peerreviewed = {Yes},
title = {{Cardiac} c-arm {CT}: {A} unified framework for motion estimation and dynamic {CT}},
volume = {28},
year = {2009}
}
@inproceedings{faucris.120203864,
abstract = {Cardiac C-arm CT is a promising technique that enables 3D cardiac image acquisition and real-time fluoroscopy on the same system. The goal is to bring 3D imaging to the interventional suite for improved therapy planning, guidance, and monitoring. For the reconstruction of 3D cardiac image data, a complete set of projections from a specific heart phase is required. One approach to reduce motion blurring caused by the beating heart is to acquire multiple sweeps using the Carm and retrospectively select the projections that are closest to the desired cardiac phase. In order to further improve the temporal resolution, novel image processing algorithms that utilize retrospective motion correction were investigated in this study. The main focus of this work is to extend the well established FDK algorithm to incorporate motion correction during the backprojection step using a subject specific computed motion field. In a simulation study we show that motion blurring can be decreased significantly using the subjects' individual estimated heart motion based on a time series of retrospectively gated FDK reconstructions. In our experiments using an animal model we investigated the following two scenarios: (I) Can the image quality from a single sweep be improved given a subjects' individual prior computed motion field? (II) Can improved image quality be achieved using the full temporal resolution of a multi-sweep scan for motion estimation in combination with motion correction? Our results show that increasing temporal resolution using an first order estimated 4D motion vector field of the subjects' individual heart motion in the FDK-4D algorithm can decrease motion blurring substantially for both investigated scenarios. © 2006 IEEE.},
author = {Prümmer, Marcus and Wigström, Lars and Hornegger, Joachim and Boese, Jan and Lauritsch, Günter and Strobel, Norbert and Fahrig, Rebecca},
booktitle = {2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD},
doi = {10.1109/NSSMIC.2006.354444},
faupublication = {yes},
pages = {2620-2628},
peerreviewed = {unknown},
title = {{Cardiac} {C}-arm {CT}: {Efficient} motion correction for {4D}-{FBP}},
venue = {San Diego, CA},
volume = {4},
year = {2007}
}
@inproceedings{faucris.121208824,
abstract = {Image guidance during cardiac interventional procedures (IP) using cardiac C-arm CT systems is desirable for many procedures. Applying the concept of retrospective electrocardiogram gating (ECG) to the acquisition of multiple, ECG-triggered rotational acquisitions using a C-arm system allows the 3D+t reconstruction of the heart. The process of retrospective gating is a crucial component of 3-D reconstruction. The gold-standard in gating is still ECG based. However, the ECG signal does not directly reflect the mechanical situation of the heart. Therefore an alternative gating method, based on the acquired projection data is required. Our goal is to provide an image-based gating (IBG) method without ECG such that already acquired projection data from a multi-sweep acquisition can still be used for reconstruction. We formulate the gating problem as a shortest-path optimization problem. All acquired projection images build a directed graph and the path costs are defined by projection image similarities that are based on image metrics to measure the heart phase similarity. The optimization is additionally regularized to prefer solutions where the path segment of consecutive selected projections acquired along a particular forward or backward C-arm sweep is short. This regularization depends on an estimated average heart rate that is also estimated using an image-based method. First promising results using in-vivo data are presented and compared to standard ECG gating. We conclude that the presented IBG method provides a reliable gating.},
author = {Rohkohl, Christopher and Prümmer, Marcus and Fahrig, Rebecca and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Medical Imaging 2008 - Physics of Medical Imaging},
doi = {10.1117/12.770124},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Cardiac} {C}-arm {CT}: {Image}-based gating},
venue = {San Diego, CA},
volume = {6913},
year = {2008}
}
@inproceedings{faucris.108037644,
address = {Berlin},
author = {Prümmer, Marcus and Wigström, Lars and Fahrig, Rebecca and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2007},
date = {2007-03-25/2007-03-27},
editor = {Horsch Alexander, Deserno Thomas M., Handels Heinz, Meinzer Hans-Peter, Tolxdorff Thomas},
faupublication = {yes},
pages = {222-226},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Cardiac} {C}-{Arm} {CT}: {SNR} {Enhancement} by {Combining} {Multiple} {Retrospectively} {Motion} {Corrected} {FDK}-like {Reconstructions}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Pruemmer07-CCC.pdf},
venue = {München},
year = {2007}
}
@article{faucris.280339473,
abstract = {Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, compared with the other sequences LGE CMR images with gold standard labels are particularly limited. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation focusing on myocardial wall of the left ventricle and blood cavity of the two ventricles. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the ventricle segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised domain adaptation (UDA) methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. Particularly, the top-ranking algorithms from both the supervised and UDA methods could generate reliable and robust segmentation results. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks. The challenge continues as an ongoing resource, and the gold standard segmentation as well as the MS-CMR images of both the training and test data are available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mscmrseg/).},
author = {Zhuang, Xiahai and Xu, Jiahang and Luo, Xinzhe and Chen, Chen and Ouyang, Cheng and Rueckert, Daniel and Campello, Victor M. and Lekadir, Karim and Vesal, Sulaiman and Ravikumar, Nishant and Liu, Yashu and Luo, Gongning and Chen, Jingkun and Li, Hongwei and Ly, Buntheng and Sermesant, Maxime and Roth, Holger and Zhu, Wentao and Wang, Jiexiang and Ding, Xinghao and Wang, Xinyue and Yang, Sen and Li, Lei},
doi = {10.1016/j.media.2022.102528},
faupublication = {yes},
journal = {Medical Image Analysis},
keywords = {Benchmark; Cardiac MRI segmentation; Challenge; Multi-sequence},
note = {CRIS-Team Scopus Importer:2022-08-12},
peerreviewed = {Yes},
title = {{Cardiac} segmentation on late gadolinium enhancement {MRI}: {A} benchmark study from multi-sequence cardiac {MR} segmentation challenge},
volume = {81},
year = {2022}
}
@phdthesis{faucris.115827624,
abstract = {C-arm computed tomography (CT) is an innovative imaging technique in the interventional room that enables a C-arm system to generate 3D images like a CT system. Clinical reports demonstrate that this technique can help reduce treatment-related complications and may improve interventional efficacy and safety. However, currently, C-arm CT is only capable of imaging axially-short object, because it employs a single circular data acquisition geometry. This shortcoming can be a problem in some intraoperative cases when imaging a long object, e.g., the entire spine, is crucial. A new technique, C-arm CT for axially-long objects, namely extended-volume C-arm CT, has to be developed. This thesis aims at achieving this development. In particular, this thesis designs and analyzes data acquisition geometries as well as develops and implements reconstruction algorithms for
extended-volume C-arm CT.
The thesis consists of three parts. In the first part, we studied three data acquisition
geometries and invented two thereof. For these geometries, we investigated their feasibility on a C-arm system and analyzed their possibility for efficient, theoretically-exact and -stable (TES) reconstruction algorithms. We observed that the reverse helical trajectory is a good start for real data test and the novel ellipse-line-ellipse trajectory is a good candidate for efficient TES image reconstruction. In the second part, we developed and implemented geometry-specific reconstruction algorithms. For the reverse helix, we designed three Feldkamp-Davis-Kress (FDK)-type reconstruction methods. Among the three methods, the Fusion-RFDK and Fusion-HFDK methods are preferred as they are more practical and produce acceptable images for extended-volume C-arm CT. For the ellipse-line-ellipse trajectory, we established an efficient TES reconstruction scheme, which makes proficient
use of the geometry of this trajectory. In the third part, we conducted the first experiment for extended-volume C-arm CT on a laboratorial Artis zeego system. In this experiment, cone-beam data were reliably acquired using the reverse helical trajectory and 3D images were successfully reconstructed by the Fusion-RFDK method. The consistency among theoretical understanding, simulation results and achieved image quality from a real system strongly demonstrate feasibility of extended-volume C-arm CT in the interventional room.
},
author = {Schröter, Hendrik and Rosenkranz, Tobias and Escalante Banuelos, Alberto and Aubreville, Marc and Maier, Andreas},
booktitle = {ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
date = {2020-05-04/2020-05-08},
doi = {10.1109/icassp40776.2020.9053563},
faupublication = {yes},
keywords = {noise reduction, speech enhancement, LPC, hearing aid signal processing, deep learning},
peerreviewed = {Yes},
title = {{CLCNet}: {Deep} learning-based noise reduction for hearing aids using complex linear coding},
url = {https://rikorose.github.io/CLCNet-audio-samples.github.io/},
venue = {Barcelona},
year = {2020}
}
@inproceedings{faucris.121133804,
author = {Schwemmer, Chris and Lauritsch, Günter and Kleinfeld, Albrecht and Rohkohl, Christopher and Müller, Kerstin and Hornegger, Joachim},
booktitle = {Proceedings of the third international conference on image formation in x-ray computed tomography},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.clinic{\_}7},
pages = {60-63},
title = {{Clinical} {Data} {Evaluation} of {C}-arm-based {Motion} {Compensated} {Coronary} {Artery} {Reconstruction}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Schwemmer14-CDE.pdf},
venue = {Salt Lake City, Utah, USA},
year = {2014}
}
@inproceedings{faucris.120198584,
abstract = {Providing a stable horizon on endoscopic images especially in non-rigid endoscopic surgery (particularly NOTES) is still an open issue. Image rectification can be realized with a tiny MEMS tri-axial inertial sensor that is placed on the tip of an endoscope. By measuring the impact of gravity on each of the three orthogonal axes the rotation angle can be estimated with some calculations out of these three acceleration values. Achievable repetition rate for angle termination has to be above the usual endoscopic video frame rate of 25-30Hz. The accelerometer frame rate can be set up to 400 Hz. Accuracy has to be less than one degree even within periods of high movement and superposed acceleration. Therefore an intelligent downsampling algorithm has to be found. The image rotation is performed by rotating digitally a capture of the endoscopic analog video signal. Improvements and benefits have been evaluated in a clinical evaluation: For different peritoneoscopic tasks time was taken and instrument position was tracked and recorded.},
author = {Höller, Kurt Emmerich and Penne, Jochen and Hornegger, Joachim and Schneider, Armin and Gillen, Sonja and Feußner, Hubertus and Jahn, Jasper and Gutierrez, Javier and Wittenberg, Thomas},
booktitle = {6th International Symposium on Image and Signal Processing and Analysis, ISPA 2009},
faupublication = {yes},
pages = {713-717},
peerreviewed = {unknown},
title = {{Clinical} {Evaluation} of {Endorientation}:{Gravity} related rectification for endoscopic images},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-70450273232&origin=inward},
venue = {Salzburg},
volume = {null},
year = {2009}
}
@inproceedings{faucris.224174240,
address = {CHAM},
author = {Hajek, Jonas and Unberath, Mathias and Fotouhi, Javad and Bier, Bastian and Lee, Sing Chun and Osgood, Greg and Maier, Andreas and Armand, Mehran and Navab, Nassir},
booktitle = {MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT IV},
date = {2018-09-16/2018-09-20},
doi = {10.1007/978-3-030-00937-3{\_}35},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-08-09},
pages = {299-306},
peerreviewed = {unknown},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {{Closing} the {Calibration} {Loop}: {An} {Inside}-{Out}-{Tracking} {Paradigm} for {Augmented} {Reality} in {Orthopedic} {Surgery}},
venue = {Granada},
year = {2018}
}
@inproceedings{faucris.229592241,
address = {AMSTERDAM},
author = {Javied, Tallal and Huprich, Sven and Franke, Jörg},
booktitle = {IFAC PAPERSONLINE},
date = {2019-08-12/2019-08-14},
doi = {10.1016/j.ifacol.2019.10.018},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-11-22},
pages = {171-175},
peerreviewed = {unknown},
publisher = {ELSEVIER},
title = {{Cloud} based {Energy} {Management} {System} {Compatible} with the {Industry} 4.0 {Requirements}},
venue = {Oshawa, CANADA},
year = {2019}
}
@article{faucris.108169864,
author = {Michelson, Georg and Wärntges, Simone and Engelhorn, Tobias and El-Rafei, Ahmed Mohamed Ibrahim and Hornegger, Joachim and Dörfler, Arnd},
doi = {10.4172/2155-9570.S4-001},
faupublication = {yes},
journal = {Clinical and Experimental Ophthalmology},
pages = {1-6},
peerreviewed = {Yes},
title = {{Cluster} {Analysis} of {Glaucoma} {Patients} {Using} the {Retinal} {Nerve} {Fiber} {Layer} {Thickness} of the {Optic} {Nerve} and {DTI} {Parameters} of the {Optic} {Radiation}},
volume = {S4:001},
year = {2011}
}
@article{faucris.215696843,
abstract = {BackgroundMost current algorithms for automatic glaucoma assessment using fundus images rely on handcrafted features based on segmentation, which are affected by the performance of the chosen segmentation method and the extracted features. Among other characteristics, convolutional neural networks (CNNs) are known because of their ability to learn highly discriminative features from raw pixel intensities.MethodsIn this paper, we employed five different ImageNet-trained models (VGG16, VGG19, InceptionV3, ResNet50 and Xception) for automatic glaucoma assessment using fundus images. Results from an extensive validation using cross-validation and cross-testing strategies were compared with previous works in the literature.ResultsUsing five public databases (1707 images), an average AUC of 0.9605 with a 95% confidence interval of 95.92-97.07%, an average specificity of 0.8580 and an average sensitivity of 0.9346 were obtained after using the Xception architecture, significantly improving the performance of other state-of-the-art works. Moreover, a new clinical database, ACRIMA, has been made publicly available, containing 705 labelled images. It is composed of 396 glaucomatous images and 309 normal images, which means, the largest public database for glaucoma diagnosis. The high specificity and sensitivity obtained from the proposed approach are supported by an extensive validation using not only the cross-validation strategy but also the cross-testing validation on, to the best of the authors' knowledge, all publicly available glaucoma-labelled databases.ConclusionsThese results suggest that using ImageNet-trained models is a robust alternative for automatic glaucoma screening system. All images, CNN weights and software used to fine-tune and test the five CNNs are publicly available, which could be used as a testbed for further comparisons.},
author = {Diaz-Pinto, Andres and Morales, Sandra and Naranjo, Valery and Köhler, Thomas and Mossi, Jose M. and Navea, Amparo},
doi = {10.1186/s12938-019-0649-y},
faupublication = {yes},
journal = {Biomedical Engineering Online},
note = {CRIS-Team WoS Importer:2019-04-09},
peerreviewed = {Yes},
title = {{CNNs} for automatic glaucoma assessment using fundus images: an extensive validation},
volume = {18},
year = {2019}
}
@inproceedings{faucris.284135355,
abstract = {Hearing loss can affect children's language, speech, and social skills development. Hearing problems can result from impaired auditory feedback due to various reasons such as trauma, a clinical condition, genetic alterations, and infections, among others. Early treatment is the key to successful hearing and speech rehabilitation if the hearing loss occurs before or during spoken language acquisition. In this work, we present CoachLea, an Android application to support the clinical evaluation and therapy of the speech production and perception of children with hearing loss. The app includes numerous daily exercises to capture speech and hearing data continuously and longitudinally using a game-like user interface. Speech exercises include the “Snail race”, “Animal Sounds”, and “Image identification”, whereas the hearing exercise consists of a word identification game based on minimal pairs with speech-in-noise recordings. In the long term, CoachLea aims to be a tool that supports the therapy of children with hearing loss.},
author = {Schäfer, Paula and Pérez Toro, Paula Andrea and Klumpp, Philipp and Orozco Arroyave, Juan Rafael and Nöth, Elmar and Maier, Andreas and Abad, A. and Schuster, M. and Arias Vergara, Tomás},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2022-09-18/2022-09-22},
faupublication = {yes},
keywords = {Cochlear implant; Hearing aid; Hearing loss; Smartphone application; Speech production},
note = {CRIS-Team Scopus Importer:2022-10-28},
pages = {1959-1960},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{CoachLea}: an {Android} {Application} to {Evaluate} the {Speech} {Production} and {Perception} of {Children} with {Hearing} {Loss}},
venue = {Incheon, KOR},
volume = {2022-September},
year = {2022}
}
@inproceedings{faucris.285836654,
author = {Schäfer, Paula and Pérez Toro, Paula Andrea and Klumpp, Philipp and Orozco-Arroyave, Juan Rafael and Nöth, Elmar and Maier, Andreas and Abad, Alberto and Schuster, Maria and Arias Vergara, Tomás},
booktitle = {23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022},
faupublication = {yes},
keywords = {Cochlear implant; Smartphone application; Speech production; Hearing aid; Hearing loss},
pages = {1959-1960},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{CoachLea}: an {Android} {Application} to {Evaluate} the {Speech} {Production} and {Perception} of {Children} with {Hearing} {Loss}},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-85140086069∨igin=inward},
year = {2022}
}
@article{faucris.263269760,
abstract = {Background Dysarthric symptoms in Parkinson's disease (PD) vary greatly across cohorts. Abundant research suggests that such heterogeneity could reflect subject-level and task-related cognitive factors. However, the interplay of these variables during motor speech remains underexplored, let alone by administering validated materials to carefully matched samples with varying cognitive profiles and combining automated tools with machine learning methods. Objective We aimed to identify which speech dimensions best identify patients with PD in cognitively heterogeneous, cognitively preserved, and cognitively impaired groups through tasks with low (reading) and high (retelling) processing demands. Methods We used support vector machines to analyze prosodic, articulatory, and phonemic identifiability features. Patient groups were compared with healthy control subjects and against each other in both tasks, using each measure separately and in combination. Results Relative to control subjects, patients in cognitively heterogeneous and cognitively preserved groups were best discriminated by combined dysarthric signs during reading (accuracy = 84% and 80.2%). Conversely, patients with cognitive impairment were maximally discriminated from control subjects when considering phonemic identifiability during retelling (accuracy = 86.9%). This same pattern maximally distinguished between cognitively spared and impaired patients (accuracy = 72.1%). Also, cognitive (executive) symptom severity was predicted by prosody in cognitively preserved patients and by phonemic identifiability in cognitively heterogeneous and impaired groups. No measure predicted overall motor dysfunction in any group. Conclusions Predominant dysarthric symptoms appear to be best captured through undemanding tasks in cognitively heterogeneous and preserved cohorts and through cognitively loaded tasks in patients with cognitive impairment. Further applications of this framework could enhance dysarthria assessments in PD. (c) 2021 International Parkinson and Movement Disorder Society},
author = {Garcia, Adolfo M. and Arias-Vergara, Tomas and C. Vasquez-Correa, Juan and Nöth, Elmar and Schuster, Maria and Welch, Ariane E. and Bocanegra, Yamile and Baena, Ana and Orozco-Arroyave, Juan R.},
doi = {10.1002/mds.28751},
faupublication = {yes},
journal = {Movement Disorders},
note = {CRIS-Team WoS Importer:2021-08-27},
peerreviewed = {Yes},
title = {{Cognitive} {Determinants} of {Dysarthria} in {Parkinson}'s {Disease}: {An} {Automated} {Machine} {Learning} {Approach}},
year = {2021}
}
@article{faucris.315848128,
abstract = {Recently, the interest in spiking neural networks (SNNs) remarkably increased, as up to now some key advances of biological neural networks are still out of reach. Thus, the energy efficiency and the ability to dynamically react and adapt to input stimuli as observed in biological neurons is still difficult to achieve. One neuron model commonly used in SNNs is the leaky-integrate-and-fire (LIF) neuron. LIF neurons already show interesting dynamics and can be run in two operation modes: coincidence detectors for low and integrators for high membrane decay times, respectively. However, the emergence of these modes in SNNs and the consequence on network performance and information processing ability is still elusive. In this study, we examine the effect of different decay times in SNNs trained with a surrogate-gradient-based approach. We propose two measures that allow to determine the operation mode of LIF neurons: the number of contributing input spikes and the effective integration interval. We show that coincidence detection is characterized by a low number of input spikes as well as short integration intervals, whereas integration behavior is related to many input spikes over long integration intervals. We find the two measures to linearly correlate via a correlation factor that depends on the decay time. Thus, the correlation factor as function of the decay time shows a powerlaw behavior, which could be an intrinsic property of LIF networks. We argue that our work could be a starting point to further explore the operation modes in SNNs to boost efficiency and biological plausibility.},
author = {Stoll, Andreas and Maier, Andreas and Krauß, Patrick and Gerum, Richard and Schilling, Achim},
doi = {10.1007/s11571-023-10038-0},
faupublication = {yes},
journal = {Cognitive Neurodynamics},
keywords = {Artificial intelligence; Coincidence detection; Computational modeling; Leaky-integrate-and-fire neuron; Neural networks},
note = {CRIS-Team Scopus Importer:2023-12-22},
peerreviewed = {Yes},
title = {{Coincidence} detection and integration behavior in spiking neural networks},
year = {2023}
}
@article{faucris.203840738,
abstract = {Purpose: The aim of the study was to address the reported inconsistencies in the relationship between objective acoustic measures and perceptual ratings of vocal quality. Method: This tutorial moves away from the more widely examined problems related to obtaining the perceptual ratings and the acoustic measures and centers in less scrutinized issues regarding the procedure to establish the correspondence. Expressions for the most common measure of association between perceptual and acoustic measures (Pearson’s r) are derived using a multiple linear regression model. The particular case where the multiple linear regression involves only roughness and breathiness is discussed to illustrate the issues. Results: Most problems reported regarding inconsistent findings in the relationship between given acoustic measures and particular perceptual ratings could be linked to sample properties not directly related to the actual relationship. The influential sample properties are the collinearity between the regressors in the multiple linear regression and their relative variances. Recommendations on how to rule out this possible cause of inconsistency are given, varying in scope from data collection, reporting, manipulation, and results interpretation. Conclusions: The problems described can be extended to more general cases than the exemplified roughness and breathiness sample’s coverage. Ruling out this possible cause of inconsistency would increase the validity of the results reported.},
author = {Ferrer Riesgo, Carlos Ariel and Haderlein, Tino and Maryn, Youri and de Bodt, Marc and Nöth, Elmar},
doi = {10.1044/2017{\_}JSLHR-S-17-0136},
faupublication = {yes},
journal = {Journal of Speech Language and Hearing Research},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.collin},
pages = {1-24},
peerreviewed = {Yes},
title = {{Collinearity} and {Sample} {Coverage} {Issues} in the {Objective} {Measurement} of {Vocal} {Quality}: {The} {Case} of {Roughness} and {Breathiness}},
volume = {61},
year = {2018}
}
@article{faucris.224002676,
abstract = {Purpose: Image-guided percutaneous interventions are safer alternatives to conventional orthopedic and trauma surgeries. To advance surgical tools in complex bony structures during these procedures with confidence, a large number of images is acquired. While image-guidance is the de facto standard to guarantee acceptable outcome, when these images are presented on monitors far from the surgical site the information content cannot be associated easily with the 3D patient anatomy. Methods: In this article, we propose a collaborative augmented reality (AR) surgical ecosystem to jointly co-localize the C-arm X-ray and surgeon viewer. The technical contributions of this work include (1) joint calibration of a visual tracker on a C-arm scanner and its X-ray source via a hand-eye calibration strategy, and (2) inside-out co-localization of human and X-ray observers in shared tracking and augmentation environments using vision-based simultaneous localization and mapping. Results: We present a thorough evaluation of the hand-eye calibration procedure. Results suggest convergence when using 50 pose pairs or more. The mean translation and rotation errors at convergence are 5.7 mm and 0. 26 ∘, respectively. Further, user-in-the-loop studies were conducted to estimate the end-to-end target augmentation error. The mean distance between landmarks in real and virtual environment was 10.8 mm. Conclusions: The proposed AR solution provides a shared augmented experience between the human and X-ray viewer. The collaborative surgical AR system has the potential to simplify hand-eye coordination for surgeons or intuitively inform C-arm technologists for prospective X-ray view-point planning.},
author = {Fotouhi, Javad and Unberath, Mathias and Song, Tianyu and Hajek, Jonas and Lee, Sing Chun and Bier, Bastian and Maier, Andreas and Osgood, Greg and Armand, Mehran and Navab, Nassir},
doi = {10.1007/s11548-019-02035-8},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Augmented reality; C-arm; Calibration; Surgery; X-ray},
note = {CRIS-Team Scopus Importer:2019-08-06},
peerreviewed = {Yes},
title = {{Co}-localized augmented human and {X}-ray observers in collaborative surgical ecosystem},
year = {2019}
}
@inproceedings{faucris.276080236,
address = {NEW YORK},
author = {Escobar-Grisales, D. and Rios-Urrego, C. D. and Lopez-Santander, D. A. and Gallo-Aristizabal, J. D. and Vasquez-Correa, J. C. and Nöth, Elmar and Orozco-Arroyave, J. R.},
booktitle = {2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU)},
doi = {10.1109/ASRU51503.2021.9687890},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2022-05-27},
pages = {556-563},
peerreviewed = {unknown},
publisher = {IEEE},
title = {{COLOMBIAN} {DIALECT} {RECOGNITION} {BASED} {ON} {INFORMATION} {EXTRACTED} {FROM} {SPEECH} {AND} {TEXT} {SIGNALS}},
year = {2021}
}
@inproceedings{faucris.289691068,
address = {CHAM},
author = {Escobar-Grisales, D. and Rios-Urrego, C. D. and Gallo-Aristizabal, J. D. and Lopez-Santander, D. A. and Calvo-Ariza, N. R. and Nöth, Elmar and Orozco-Arroyave, J. R.},
booktitle = {APPLIED COMPUTER SCIENCES IN ENGINEERING, WEA 2022},
doi = {10.1007/978-3-031-20611-5{\_}5},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2023-02-24},
pages = {54-65},
peerreviewed = {unknown},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {{Colombian} {Dialect} {Recognition} from {Call}-{Center} {Conversations} {Using} {Fusion} {Strategies}},
venue = {Bogota, COLOMBIA},
year = {2022}
}
@inproceedings{faucris.118010464,
abstract = {The color and distribution of illuminants can significantly alter the appearance of a scene. The goal of color constancy (CC) is to remove the color bias introduced by the illuminants. Most existing CC algorithms assume a uniformly illuminated scene. However, more often than not, this assumption is an insufficient approximation of real-world illumination conditions (multiple light sources, shadows, interreflections, etc.). Thus, illumination should be locally determined, taking under consideration that multiple illuminants may be present. In this paper we investigate the suitability of adapting 5 state-of-the-art color constancy methods so that they can be used for local illuminant estimation. Given an arbitrary image, we segment it into superpixels of approximately similar color. Each of the methods is applied independently on every superpixel. For improved accuracy, these independent estimates are combined into a single illuminant-color value per superpixel. We evaluated different fusion methodologies. Our experiments indicate that the best performance is obtained by fusion strategies that combine the outputs of the estimators using regression. © 2011 IEE},
author = {Bleier, Michael and Riess, Christian and Beigpour, S. and Eibenberger, E. and Angelopoulou, E. and Tröger, Tobias and Kaup, André},
booktitle = {2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011},
date = {2011-11-06/2011-11-13},
doi = {10.1109/ICCVW.2011.6130331},
faupublication = {yes},
isbn = {9781467300629},
pages = {774-781},
peerreviewed = {Yes},
title = {{Color} constancy and non-uniform illumination: {Can} existing algorithms work?},
venue = {Barcelona},
year = {2011}
}
@inproceedings{faucris.207561863,
author = {Meyer, Manuel and Riess, Christian and Angelopoulou, Elli and Evangelopoulos, Georgios and Kakadiaris, Ioannis},
booktitle = {Biometric and Surveillance Technology for Human and Activity Identification},
date = {2013-05-02/2013-05-02},
doi = {10.1117/12.2018758},
editor = {SPIE},
faupublication = {yes},
isbn = {9780819495037},
keywords = {Face recognition; Color constancy; Illumination normalization; Illumination invariance},
pages = {8712-17},
peerreviewed = {Yes},
title = {{Color} {Constancy} in {3D}-{2D} {Face} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Meyer13-CCI.pdf},
venue = {Baltimore, MD},
volume = {8712},
year = {2013}
}
@inproceedings{faucris.111120724,
author = {Geimer, Tobias and Unberath, Mathias and Taubmann, Oliver and Bert, Christoph and Maier, Andreas},
booktitle = {Computer Assisted Radiology and Surgery (CARS) 2016: Proceedings of the 30th International Congress and Exhibition},
date = {2016-06-22/2016-06-25},
doi = {10.1007/s11548-016-1412-5},
faupublication = {yes},
keywords = {Motion Modeling; X-ray; Range Imaging; Dimensionality Reduction; Regression},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.combin{\_}2},
pages = {59-60},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Combination} of {Markerless} {Surrogates} for {Motion} {Estimation} in {Radiation} {Therapy}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Geimer16-COM.pdf},
venue = {Heidelberg},
year = {2016}
}
@inproceedings{faucris.122951444,
author = {Haji Ghassemi, Nooshin and Marxreiter, Franz and Pasluosta, Cristian Federico and Schlachetzki, Johannes and Schramm, A and Eskofier, Björn and Klucken, Jochen},
booktitle = {38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society of the IEEE Engineering in Medicine and Biology Society EMBC'16},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Combined} {Accelerometer} and {EMG} {Analysis} to {Differentiate} {Essential} {Tremor} from {Parkinson}’s {Disease}},
venue = {Orlando},
year = {2016}
}
@inproceedings{faucris.106275224,
abstract = {Objective and rater independent analysis of movement impairment is one of the most challenging tasks in medical engineering. Especially assessment of motor symptoms defines the clinical diagnosis in Parkinson's disease (PD). A sensor-based system to measure the movement of the upper and lower extremities would therefore complement the clinical evaluation of PD. In this study two different sensor-based systems were combined to assess movement of 18 PD patients and 17 healthy controls. First, hand motor function was evaluated using a sensor pen with integrated accelerometers and pressure sensors, and second, gait function was assessed using a sports shoe with attached inertial sensors (gyroscopes, accelerometers). Subjects performed standardized tests for both extremities. Features were calculated from sensor signals to differentiate between patients and controls. For the latter, pattern recognition methods were used and the performance of four classifiers was compared. In a first step classification was done for every single system and in a second step for combined features of both systems. Combination of both motor task assessments substantially improved classification rates to 97% using the AdaBoost classifier for the experiment patients vs. controls. The combination of two different analysis systems led to enhanced, more stable, objective, and rater independent recognition of motor impairment. The method can be used as a complementary diagnostic tool for movement disorders.},
author = {Barth, Jens and Sünkel, Michael and Bergner, Katharina and Schickhuber, Gerald and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn},
booktitle = {Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE},
date = {2012-08-28/2012-09-01},
doi = {10.1109/EMBC.2012.6347146},
faupublication = {yes},
pages = {5122-5125},
title = {{Combined} analysis of sensor data from hand and gait motor function improves automatic recognition of {Parkinson}'s disease},
venue = {San Diego, CA},
year = {2012}
}
@article{faucris.121120824,
abstract = {Catheter ablation of atrial fibrillation has become an accepted treatment option if a patient no longer responds to or tolerates drug therapy. A main goal is the electrical isolation of the pulmonary veins attached to the left atrium. Catheter ablation may be performed under fluoroscopic image guidance. Due to the rather low soft-tissue contrast of X-ray imaging, the heart is not visible in these images. To overcome this problem, overlay images from pre-operative 3-D volumetric data can be used to add anatomical detail. Unfortunately, this overlay is compromised by respiratory and cardiac motion. In the past, two methods have been proposed to perform motion compensation. The first approach involves tracking of a circumferential mapping catheter placed at an ostium of a pulmonary vein. The second method relies on a motion estimate obtained by localizing an electrode of the coronary sinus (CS) catheter. We propose a new motion compensation scheme which combines these two methods. The effectiveness of the proposed method is verified using 19 real clinical data sets. The motion in the fluoroscopic images was estimated with an overall average error of 0.55 mm by tracking the circumferential mapping catheter. By applying an algorithm involving both the CS catheter and the circumferential mapping catheter, we were able to detect motion of the mapping catheter from one pulmonary vein to another with a false positive rate of 5.8 %.},
author = {Brost, Alexander and Wu, Wen and Koch, Martin and Wimmer, Andreas and Chen, Terrence and Liao, Rui and Hornegger, Joachim and Strobel, Norbert},
doi = {10.1007/978-3-642-23623-5{\_}68},
faupublication = {yes},
journal = {Lecture Notes in Computer Science},
note = {UnivIS-Import:2015-04-16:Pub.2011.tech.IMMD.IMMD5.combin{\_}3},
pages = {540-547},
peerreviewed = {Yes},
title = {{Combined} {Cardiac} and {Respiratory} {Motion} {Compensation} for {Atrial} {Fibrillation} {Ablation} {Procedures}},
volume = {14},
year = {2011}
}
@inproceedings{faucris.237574346,
abstract = {Osteoarthritis is a joint disease that commonly affects the hands, feet, spine, as well as the large weight-bearing joints, i. e., the hip, and knees. Worldwide, about 3.6% of the population suffer from osteoarthritis of the knee. If the symptoms are too severe to be treated with medication, the solution is often a total replacement. The precise preoperative planning of implants is a crucial task to achieve a good patient outcome. For planning, usually hybrid 2-D/3-D approaches are used. The main drawback of theses hybrid methods is the different patient positions during the acquisition, namely lying for the 3-D scan and standing for the 2-D scan. We proposed a method that allows acquiring both images in standing positions under natural weight-bearing without having to reposition the patient. To show the feasibility, we provide images from an anthropomorphic leg phantom. A preliminary study with medical experts has shown that the results are promising.},
author = {Luckner, Christoph and Herbst, Magdalena and Fuhrmann, Michael and Ritschl, Ludwig and Kappler, Steffen and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}74},
editor = {Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm},
faupublication = {yes},
isbn = {9783658292669},
note = {CRIS-Team Scopus Importer:2020-04-21},
pages = {335-340},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Combining} 2-{D} and 3-{D} weight-bearing x-ray images: {Application} to preoperative implant planning in the knee},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.107870004,
abstract = {
Classification performance of emotional user states found in realistic, spontaneous speech is not very high, compared to the performance reported for acted speech in the literature. This might be partly due to the difficulty of providing reliable annotations, partly due to suboptimal feature vectors used for classification, and partly due to the difficulty of the task. In this paper, we present a co-operation between several sites, using a thoroughly processed emotional database. For the four-class problem motherese/neutral/emphatic/angry, we first report classification performance computed independently at each site. Then we show that by using all the best features from each site in a combined classification, and by combining classifier outputs within the ROVER framework, classification results can be improved; all feature types and features from all sites contributed.
},
address = {Ljubljana, Slovenia},
author = {Batliner, Anton and Steidl, Stefan and Schuller, Björn and Seppi, Dino and Laskowski, Kornel and Vogt, Thurid and Devillers, Laurence and Vidrascu, Laurence and Amir, Noam and Kessous, Loic and Aharonson, Vered},
booktitle = {Language Technologies, IS-LTC 2006},
date = {2006-10-09/2006-10-10},
editor = {Erjavec Tomaz, Gros Jerneja Zganec},
faupublication = {yes},
pages = {240-245},
peerreviewed = {Yes},
publisher = {Infornacijska Druzba (Information Society)},
title = {{Combining} {Efforts} for {Improving} {Automatic} {Classification} of {Emotional} {User} {States}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Batliner06-CEF.pdf},
venue = {Ljubljana},
year = {2006}
}
@inproceedings{faucris.121322784,
author = {Middag, Catherine and Bocklet, Tobias and Martens, Jean-Pierre and Nöth, Elmar},
booktitle = {Proceedings of the 12th Annual Conference of the International Speech Communication Association},
date = {2011-08-27/2011-08-31},
editor = {ISCA},
faupublication = {yes},
pages = {3005-3008},
title = {{Combining} phonological and acoustic {ASR}-free features for pathological speech intelligibility assessment},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Middag11-CPA.pdf},
venue = {Florence},
year = {2011}
}
@inproceedings{faucris.221673357,
abstract = {Out-of-vocabulary words (OOVs) are often the main reason for the failure of tasks like automated voice searches or human-machine dialogs. This is especially true if rare but task-relevant content words, e.g. person or location names, are not in the recognizer's vocabulary. Since applications like spoken dialog systems use the result of the speech recognizer to extract a semantic representation of a user utterance, the detection of OOVs as well as their (semantic) word class can support to manage a dialog successfully. In this paper we suggest to combine two well-known approaches in the context of OOV detection: semantic word classes and OOV models based on sub-word units. With our system, which builds upon the widely used Kaldi speech recognition toolkit, we show on two different data sets that - compared to other methods - such a combination improves OOV detection performance for open word classes at a given false alarm rate. Another result of our approach is a reduction of the word error rate (WER).
},
author = {Horndasch, Axel and Batliner, Anton and Kaufhold, Caroline and Nöth, Elmar},
booktitle = {17th Annual Conference of the International Speech Communication Association (INTERSPEECH 2016): Understanding Speech Processing in Humans and Machines},
date = {2016-09-08/2016-09-12},
doi = {10.21437/Interspeech.2016-1250},
faupublication = {yes},
isbn = {978-1-5108-3313-5},
keywords = {OOV detection and classification; Kaldi; Sub-word unit speech recognition; Semantic word classes},
pages = {1335-1339},
peerreviewed = {Yes},
publisher = {International Speech and Communication Association},
title = {{Combining} semantic word classes and sub-word unit speech recognition for robust {OOV} detection},
url = {https://pdfs.semanticscholar.org/70f1/4384711a26d2f38c855da729c03c8066bf16.pdf},
venue = {San Francisco, CA, USA},
year = {2016}
}
@inproceedings{faucris.217470828,
abstract = {This study aims at the combination of 3D breast ultrasound and 2D mammography images to improve the accuracy of diagnosis of breast cancer. It was shown that ultrasound breast imaging has advantages for differentiating cysts and solid masses which are not visible in an X-ray image. Moreover, the specificity in X-ray imaging decreases with an increasing breast thickness, so that ultrasound is usually used as an adjunct to X-ray breast imaging. A fully automatic system to obtain both 2D mammography and 3D ultrasound images is used. The alignment of a 2D mammography image in the cone-beam coordinate system and 3D ultrasound image in a Cartesian coordinate system is the essential task in this study. We have shown that deviations up to 23 mm caused by the cone-beam system can be calculated and corrected utilizing the geometry information of the hardware. The multimodal image reading tool is presented in a GUI for clinical diagnosis. The presented setup might lead to a distinct improvement in efficiency and add diagnostic value to the acquisition.},
author = {Li, Qiuting and Luckner, Christoph and Hertel, Madeleine and Radicke, Marcus and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}55},
editor = {Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2019-05-14},
pages = {245-250},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Combining} {Ultrasound} and {X}-{Ray} {Imaging} for {Mammography}: {A} {Prototype} {Design}},
venue = {Lübeck},
year = {2019}
}
@incollection{faucris.213690130,
author = {Li, Qiuting and Luckner, Christoph and Hertel, Madeleine and Radicke, Marcus and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2019},
doi = {10.1007/978-3-658-25326-4{\_}55},
faupublication = {yes},
pages = {245--250},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Combining} {Ultrasound} and {X}-{Ray} {Imaging} for {Mammography}},
year = {2019}
}
@inproceedings{faucris.276690551,
abstract = {Automatically extracting targeted information from historical documents is an important task in the field of document analysis and eases the work of historians when dealing with huge corpora. In this work, we investigate the idea of retrieving the recipient transcriptions from the Nuremberg letterbooks of the 15th century. This task can be solved with fundamentally different ways of approaching it. First, detecting recipient lines solely based on visual features and without any explicit linguistic feedback. Here, we use a vanilla U-Net and an attention-based U-Net as representatives. Second, linguistic feedback can be used to classify each line accordingly. This is done on the one hand with handwritten text recognition (HTR) for predicting the transcriptions and on top of it a light-wight natural language processing (NLP) model distinguishing whether the line is a recipient line or not. On the other hand, we adapt a named entity recognition transformer model. The system jointly performs the line transcription and the recipient line recognition. For improving the performance, we investigated all the possible combinations with the different methods. In most cases the combined output probabilities outperformed the single approaches. The best combination achieved on the hard test set an F1 score of 80% and recipient line recognition accuracy of about 96% while the best single approach only reached about 74% and 94%, respectively.},
author = {Mayr, Martin and Felker, Alex and Maier, Andreas and Christlein, Vincent},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2022-05-22/2022-05-25},
doi = {10.1007/978-3-031-06555-2{\_}40},
editor = {Seiichi Uchida, Elisa Barney, Véronique Eglin},
faupublication = {yes},
isbn = {9783031065545},
keywords = {Handwritten text recognition; Natural language processing; Recipient recognition; Semantic image segmentation},
note = {CRIS-Team Scopus Importer:2022-06-10},
pages = {598-612},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Combining} {Visual} and {Linguistic} {Models} for a {Robust} {Recipient} {Line} {Recognition} in {Historical} {Documents}},
venue = {La Rochelle, FRA},
volume = {13237 LNCS},
year = {2022}
}
@inproceedings{faucris.289690093,
address = {PARIS},
author = {Klumpp, Philipp and Arias-Vergara, Tomas and Perez-Toro, Paula-Andrea and Nöth, Elmar and Orozco-Arroyave, Juan Rafael},
booktitle = {LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION},
doi = {10.5281/zenodo.5846137},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2023-02-24},
pages = {763-768},
peerreviewed = {unknown},
publisher = {EUROPEAN LANGUAGE RESOURCES ASSOC-ELRA},
title = {{Common} {Phone}: {A} {Multilingual} {Dataset} for {Robust} {Acoustic} {Modelling}},
venue = {Marseille, FRANCE},
year = {2022}
}
@inproceedings{faucris.276491575,
abstract = {Accurate segmentation of breast lesions is a crucial step in evaluating the characteristics of tumors. However, this is a challenging task, since breast lesions have sophisticated shape, topological structure, and variation in the intensity distribution. In this paper, we evaluated the performance of three unsupervised algorithms for the task of breast Magnetic Resonance (MRI) lesion segmentation, namely, Gaussian Mixture Model clustering, K-means clustering and a markercontrolled Watershed transformation based method. All methods were applied on breast MRI slices following selection of regions of interest (ROIs) by an expert radiologist and evaluated on 106 subject’s images, which include 59 malignant and 47 benign lesions. Segmentation accuracy was evaluated by comparing our results with ground truth masks, using the Dice similarity coefficient (DSC), Jaccard index (JI), Hausdorff distance and precision-recall metrics. The results indicate that the marker-controlled Watershed transformation outperformed all other algorithms investigated.},
author = {Vesal, Sulaiman and Ravikumar, Nishant and Ellmann, Stephan and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2018-03-11/2018-03-13},
doi = {10.1007/978-3-662-56537-7{\_}68},
editor = {Heinz Handels, Thomas Tolxdorff, Thomas M. Deserno, Klaus H. Maier-Hein, Andreas Maier, Christoph Palm},
faupublication = {yes},
note = {CRIS-Team Scopus Importer:2022-06-05},
pages = {257-262},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Comparative} analysis of unsupervised algorithms for breast {MRI} lesion segmentation},
venue = {Erlangen, DEU},
year = {2018}
}
@inproceedings{faucris.203706811,
abstract = {Image
segmentation is a key technique in image processing with the goal to
extract important objects from the image. This evaluation study focuses
on the segmentation quality of three different interactive segmentation
techniques, namely Region Growing, Watershed and the cellular automaton
based GrowCut algorithm.
Three different evaluation measures are
computed to compare the segmentation quality of each algorithm: Rand
Index, Mutual Information, and the Dice Coefficient. For the images in
the publicly available ground truth data base utilized for the
evaluation, the GrowCut method has a slight advantage over the other
two.
The presented results provide insight into the performance
and the characteristics with respect to the image quality of each tested
algorithm.
},
address = {Berlin Heidelberg},
author = {Amrehn, Mario and Glasbrenner, Jens and Steidl, Stefan and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2016},
date = {2016-03-13/2016-03-15},
doi = {10.1007/978-3-662-49465-3},
faupublication = {yes},
isbn = {978-3-662-49465-3},
keywords = {medical; image segmentation; 3-D; lesion; tumor; liver; hepatic; cancer},
note = {UnivIS-Import:2018-09-06:Pub.2016.tech.IMMD.IMMD5.compar{\_}6},
pages = {68-73},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Comparative} {Evaluation} of {Interactive} {Segmentation} {Approaches}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Amrehn16-CEO.pdf},
venue = {Charité - Universitätsmedizin Berlin},
year = {2016}
}
@inproceedings{faucris.121152504,
abstract = {The forward projection operator is a key component of every iterative reconstruction method in X-ray computed tomography (CT). Besides the choices being made in the definition of the objective function and associated constraints, the forward projection model affects both bias and noise properties of the reconstruction. In this work, we compare three important forward projection models that rely on linear interpolation: the Joseph method, the distance-driven method, and the image representation using B-splines of order n = 1. The comparison focuses on bias and noise in the image as a function of the resolution. X-ray CT data that are simulated in fan-beam geometry with two different magnification factors are used. © 2013 SPIE.},
author = {Schmitt, Katharina and Schöndube, Harald and Stiersdorfer, Karl and Hornegger, Joachim and Noo, Frédéric},
booktitle = {Medical Imaging 2013: Physics of Medical Imaging},
doi = {10.1117/12.2008175},
faupublication = {yes},
pages = {-},
title = {{Comparative} evaluation of linear interpolation models for iterative reconstruction in {X}-ray {CT}},
venue = {Lake Buena Vista, FL},
volume = {8668},
year = {2013}
}
@inproceedings{faucris.111045044,
author = {Unberath, Mathias and Maier, Andreas and Fleischmann, Dominik and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Proceedings of the GRC},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.compar},
pages = {5-8},
peerreviewed = {unknown},
title = {{Comparative} {Evaluation} of {Two} {Registration}-based {Segmentation} {Algorithms}: {Application} to {Whole} {Heart} {Segmentation} in {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Unberath15-CEO.pdf},
venue = {Aachen, Germany},
year = {2015}
}
@article{faucris.235049616,
abstract = {Optical coherence tomography angiography (OCTA) is a promising imaging
modality for microvasculature studies. Meanwhile, deep learning has
achieved rapid development in image-to-image translation tasks. Some
studies have proposed applying deep learning models to OCTA
reconstruction and have obtained preliminary results. However, current
studies are mostly limited to a few specific deep neural networks. In
this paper, we conducted a comparative study to investigate OCTA
reconstruction using deep learning models. Four representative network
architectures including single-path models, U-shaped models, generative
adversarial network (GAN)-based models and multi-path models were
investigated on a dataset of OCTA images acquired from rat brains. Three
potential solutions were also investigated to study the feasibility of
improving performance. The results showed that U-shaped models and
multi-path models are two suitable architectures for OCTA
reconstruction. Furthermore, merging phase information should be the
potential improving direction in further research.
in-vivo. Currently, there is no standard method agreed upon that defines a distance measure in articular cartilage. In this work, we present a comparison of different methods commonly used in literature. These methods are based on nearest neighbors, surface normal vectors, local thickness and potential field lines. All approaches were applied to manual segmentations of tibia and lateral and medial tibial cartilage performed by experienced raters. The underlying data were contrast agent-enhanced cone-beam C-arm CT reconstructions of one healthy subject’s knee. The subject was scanned three times, once in supine position and two times in a standing weight-bearing position. A comparison of the resulting thickness maps shows similar distributions and high correlation coefficients between the approaches above 0.90. The nearest neighbor method results on average in the lowest cartilage thickness values, while the local thickness approach assigns the highest values. We showed that the different methods agree in their thickness distribution. The results will be used for a future evaluation of cartilage change under weight-bearing conditions.},
author = {Maier, Jennifer and Black, Marianne and Bonaretti, Serena and Bier, Bastian and Eskofier, Björn and Choi, Jang-Hwan and Levenston, Marc and Gold, Garry and Fahrig, Rebecca and Maier, Andreas},
doi = {10.1515/jib-2017-0015},
faupublication = {yes},
journal = {Journal of integrative bioinformatics},
keywords = {Cartilage strain; Cone-beam C-arm CT; Weight-bearing; Local thickness; Potential field lines},
peerreviewed = {Yes},
title = {{Comparison} of {Different} {Approaches} for {Measuring} {Tibial} {Cartilage} {Thickness}},
volume = {14},
year = {2017}
}
@inproceedings{faucris.121449724,
address = {Karlsruh},
author = {Weinlich, Andreas and Keck, Benjamin and Scherl, Holger and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {Proceedings of the First International Workshop on New Frontiers in High-performance and Hardware-aware Computing (HipHaC'08)},
date = {2008-11-08},
editor = {Buchty Rainer, Weiß Jan-Philipp},
faupublication = {yes},
pages = {25-30},
peerreviewed = {unknown},
publisher = {Universitätsverlag Karlsruhe},
title = {{Comparison} of {High}-{Speed} {Ray} {Casting} on {GPU} using {CUDA} and {OpenGL}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Weinlich08-COH.pdf},
venue = {Lake Como},
year = {2008}
}
@inproceedings{faucris.108124984,
author = {Aksoy, Murat and Forman, Christoph and Straka, Matus and Holdsworth, Samantha and Skare, Stefan and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the ISMRM Workshop on Current Concepts of Motion Correction for MRI & MRS},
date = {2010-02-24/2010-02-28},
editor = {International Society for Magnetic Resonance in Medicine (ISMRM)},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Comparison} of {Image}-{Based} {Retrospective} and {Optical} {Prospective} {Motion} {Correction} for {Diffusion} {Tensor} {Imaging}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Aksoy10-COI.pdf},
venue = {Kitzbühel},
year = {2010}
}
@article{faucris.264061770,
abstract = {Purpose: In Talbot–Lau X-ray phase contrast imaging, the measured phase value depends on the position of the object in the measurement setup. When imaging large objects, this may lead to inhomogeneous phase contributions within the object. These inhomogeneities introduce artifacts in tomographic reconstructions of the object. Methods: In this work, we compare recently proposed approaches to correct such reconstruction artifacts. We compare an iterative reconstruction algorithm, a known operator network and a U-net. The methods are qualitatively and quantitatively compared on the Shepp–Logan phantom and on the anatomy of a human abdomen. We also perform a dedicated experiment on the noise behavior of the methods. Results: All methods were able to reduce the specific artifacts in the reconstructions for the simulated and virtual real anatomy data. The results show method-specific residual errors that are indicative for the inherently different correction approaches. While all methods were able to correct the artifacts, we report a different noise behavior. Conclusion: The iterative reconstruction performs very well, but at the cost of a high runtime. The known operator network shows consistently a very competitive performance. The U-net performs slightly worse, but has the benefit that it is a general-purpose network that does not require special application knowledge.},
author = {Felsner, Lina and Roser, Philipp and Maier, Andreas and Riess, Christian},
doi = {10.1007/s11548-021-02487-x},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {computed tomography; known operator learning; sensitivity correction; Talbot–Lau interferometer; X-ray phase contrast imaging},
note = {CRIS-Team Scopus Importer:2021-09-17},
peerreviewed = {Yes},
title = {{Comparison} of methods for sensitivity correction in {Talbot}–{Lau} computed tomography},
year = {2021}
}
@inproceedings{faucris.289692810,
address = {CHAM},
author = {Moreno-Acevedo, S. A. and Escobar-Grisales, D. and Vasquez-Correa, J. C. and Orozco Arroyave, Juan Rafael},
booktitle = {APPLIED COMPUTER SCIENCES IN ENGINEERING, WEA 2022},
doi = {10.1007/978-3-031-20611-5{\_}4},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2023-02-24},
pages = {41-53},
peerreviewed = {unknown},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {{Comparison} of {Named} {Entity} {Recognition} {Methods} on {Real}-{World} and {Highly} {Imbalanced} {Business} {Document} {Datasets}},
venue = {Bogota},
year = {2022}
}
@article{faucris.120204744,
abstract = {Object: This retrospective study compares the anatomical accuracy of automated rigid and non-rigid registration software for aligning data from separately performed X-ray computed tomography (CT) and positron emission tomography with F-18-deoxyglucose (PET). Materials and methods: Analyses were performed on independently acquired PET and CT data from 40 tumor patients. Rigid as well as non-rigid automated fusion was carried out using the commercially available Mirada 7D platform (MIR and MINR, respectively) as well as a second automated non-rigid registration based on a variational image registration approach (VIR). Distances between lesion representation on PET and CT of 105 malignant lesions were measured in X-, Y-, and Z-directions. Statistical evaluation was performed using mixed effect analysis, comparing separately MIR with MINR and VIR with MINR. Results: The percentage of lesions misregistered by less than 15 mm varied from 70% for MIR and MINR in Z-direction to 93% for VIR in X-direction. The average X-, Y- and Z-distances ranged between 5.9 ± 5.7 mm for VIR in X-direction and 12.8 ± 9.7 mm for MIR in Z-direction. MINR was significantly more accurate than MIR in Y-direction. Furthermore, VIR aligned thoracic lesions in the X- direction significantly better than MINR. Conclusion: The accuracy of rigid and non-rigid automated image registration can be expected to be better than 15 mm for the majority of lesions. Alignment tended to be more accurate with non-rigid registration. © CARS 2007.},
author = {Wolz, Gabriele and Nömayr, Anton and Hothorn, Torsten and Hornegger, Joachim and Römer, Wolfgang and Bautz, Werner and Kuwert, Torsten},
doi = {10.1007/s11548-007-0128-y},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
pages = {183-190},
peerreviewed = {unknown},
title = {{Comparison} of performance between rigid and non-rigid software registering {CT} to {FDG}-{PET}},
volume = {2},
year = {2007}
}
@inproceedings{faucris.118030924,
address = {Erlangen},
author = {Bauer, Martin and Kuschel, Christian and Ritter, Daniel and Sembritzki, Klaus},
booktitle = {PARS Mitteilungen},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2013.tech.IMMD.lsinfs.compar{\_}0},
pages = {58-69},
publisher = {GI},
title = {{Comparison} of {PGAS} {Languages} on a {Linked} {Cell} {Algorithm}},
url = {https://www10.informatik.uni-erlangen.de/Publications/Papers/2013/Bauer{\_}PARS.pdf},
venue = {Erlangen},
volume = {30},
year = {2013}
}
@inproceedings{faucris.106933904,
abstract = {Laser Metal Deposition (LMD) with Blown Powder and Laser Beam Melting (LBM) in Powder Bed are two Additive Manufacturing technologies that can produce high-quality metal parts in principle. Both technologies are based on melting of fine metal powders employing highintensity laser radiation. Apart from the obvious differences defined by system technology, LMD and LBM differ largely in fundamental boundary conditions of laser-materialinteraction. Process conditions in LMD and LBM and corresponding microstructures were compared on the example of martensitic aging steel 1.2709. This material has been one of the most popular ones in industrial use with LBM for about a decade, typically processed with laser powers below 400 W in continuous wave (cw) mode. With
LMD, 1.2709 has not been commonly used so far. LMD typically engages higher cw laser powers of around 1000 W, larger laser spot diameters and smaller feed rates than LBM. Increased laser power kindles hopes for increased productivity, which is a key factor for economic viability. For a more comprehensive comparison, 1.2709 processed by LBM with 1000 W was also considered. Samples were analyzed metallographically, by computed x-ray tomography, hardness testing before and after heat treatment. Chemical compositions of powder and built samples were compared.
},
address = {Ljubljana},
author = {Karg, Michael and Hentschel, Oliver and Ahuja, Bhrigu and Junker, Daniel and Haßler, Ulf and Schäperkötter, Claus and Haimerl, Andreas and Arnet, Horst and Merklein, Marion and Schmidt, Michael},
booktitle = {6th International Conference on Additive Technologies},
date = {2016-11-29/2016-11-30},
editor = {Igor Drstvenšek, Dietmar Drummer, Michael Schmidt},
faupublication = {yes},
isbn = {978-961-285-537-6},
keywords = {Maraging Steel; 1.2709; microstructure; Laser Beam Melting; Laser Metal Deposition;},
pages = {39-50},
peerreviewed = {Yes},
publisher = {Interesansa - zavod},
title = {{Comparison} of process characteristics and resulting microstructures of maraging steel 1.2709 in {Additive} {Manufacturing} via {Laser} {Metal} {Deposition} and {Laser} {Beam} {Melting} in {Powder} {Bed}},
venue = {Nürnberg},
year = {2016}
}
@inproceedings{faucris.122937584,
author = {Leutheuser, Heike and Gradl, Stefan and Kugler, Patrick and Anneken, Lars and Achenbach, Stephan and Eskofier, Björn and Arnold, Martin},
booktitle = {IEEE EMBC 2014},
faupublication = {yes},
pages = {2690-2693},
peerreviewed = {unknown},
title = {{Comparison} of {Real}-{Time} {Classification} {Systems} for {Arrhythmia} {Detection} on {Android}-based {Mobile} {Devices}},
venue = {Chicago, Illinois, USA},
year = {2014}
}
@inproceedings{faucris.203706478,
address = {Springer},
author = {Schaffert, Roman and Wang, Jian and Borsdorf, Anja and Hornegger, Joachim and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin},
doi = {10.1007/978-3-662-49465-3{\_}26},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2016.tech.IMMD.IMMD5.compar{\_}0},
pages = {140-145},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Comparison} of {Rigid} {Gradient}-{Based} {2D}/{3D} {Registration} {Using} {Projection} and {Back}-{Projection} {Strategies}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Schaffer16-COR.pdf},
venue = {Berlin},
year = {2016}
}
@inproceedings{faucris.111444124,
abstract = {In this work, we present a method to increase the lateral field-of-view
of a C-arm CT system by rotating the detector such that the diagonal of
the detector lies on the u-axis of the detector's coordinate system. We
investigated three different 3-D scan trajectories for liver imaging of
an obese patient (waist circumference 130 cm) — a Short Scan, a Large
Volume Scan and a Helical Large Volume Scan. We reconstructed a data set
of the Visible Human Project with the SART and the eTV algorithm. Tests
revealed that the coverage was increased with the presented method by
25.3 % for the Short Scan and 28.5 % for the Large Volume Scan.
Performing helical scans compensated the axial data loss. The two
implemented iterative approaches both provide acceptable results, with
the eTV algorithm reducing the RMSE compared to SART by about 29 %.
Given a liver imaging task, the rotated detector is able to image the
entire liver section of the abdomen with a single Large Volume Sca},
author = {Stromer, Daniel and Amrehn, Mario and Huang, Yixing and Kugler, Patrick and Bauer, Sebastian and Lauritsch, Günter and Maier, Andreas},
booktitle = {Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro},
date = {2016-04-13/2016-04-16},
doi = {10.1109/ISBI.2016.7493337},
faupublication = {yes},
isbn = {9781479923502},
keywords = {Diamond Scan; eTV; Field-of-View Enlargement; Iterative Reconstruction; iTV; SART},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.compar{\_}1},
pages = {589-592},
peerreviewed = {Yes},
publisher = {IEEE Computer Society},
title = {{Comparison} of {SART} and {eTV} {Reconstruction} for increased {C}-arm {CT} {Volume} {Coverage} by proper {Detector} {Rotation} in {Liver} {Imaging}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Stromer16-COS.pdf},
venue = {Prague},
volume = {2016-June},
year = {2016}
}
@inproceedings{faucris.120330364,
author = {Leutheuser, Heike and Gabsteiger, Florian and Hebenstreit, Felix and Reis, Pedro and Lochmann, Matthias and Eskofier, Björn},
booktitle = {IEEE EMBC 2013},
date = {2013-07-03/2013-07-07},
editor = {Engineering in Medicine and Biology Society},
faupublication = {yes},
pages = {6804-6807},
title = {{Comparison} of the {AMICA} and the {InfoMax} {Algorithm} for the {Reduction} of {Electromyogenic} {Artifacts} in {EEG} {Data}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Leutheuser13-COT.pdf},
venue = {Osaka},
year = {2013}
}
@inproceedings{faucris.238554763,
abstract = {Parkinson’s disease is a neurodegenerative disorder characterized by the presence of different motor impairments. Information from speech, handwriting, and gait signals have been considered to evaluate the neurological state of the patients. On the other hand, user models based on Gaussian mixture models - universal background models (GMMUBM) and i-vectors are considered the state-of-the-art in biometric applications like speaker verification because they are able to model specific speaker traits. This study introduces the use of GMM-UBM and i-vectors to evaluate the neurological state of Parkinson’s patients using information from speech, handwriting, and gait. The results show the importance of different feature sets from each type of signal in the assessment of the neurological state of the patients.
To that end, in this thesis a computer-aided diagnosis (CAD) system, comprised of multiple computational steps, is developed specifically for MGCE images. The first part of this work focuses on the segmentation of bubbles, particles and other debris, which frequently appear in MGCE images, and interfere with the CAD process. The developed approach is capable of segmenting image areas with such content with an average accuracy of 87.8% and is, therefore, providing an image region of interest for further processing.
In the second part of this thesis a novel system for semantic and topological classification of MGCE images is presented. Based on a series of processing steps and extracted features, images are grouped into different categories. These categories are, for example, the anatomical location of the acquisition, or the image pose relative to anatomical structures in the upper gastrointestinal tract. An average accuracy of over 80% for all classification stages could be achieved. Such information facilitates the post-procedure review process or provides strong a priori knowledge for CAD algorithms.
In the third part of this work a CAD method is developed that can automatically detect two different pathologies in MGCE images. The objective of this technique is to operate during the intervention. It indicates in real time the presence of pathological structures to the physician, who can then decide whether to more closely examine the indicated area. The presented approach yields a 95% average sensitivity.
The last part of this work focuses on the detection of pre-cancerous signs. To that end, a staining technique, so-called chromoendoscopy, is applied to MGCE and is evaluated in order to highlight pathologies that are barely visible for the human observer. This work charts a path for the application of chromoendoscopy on MGCE via an ex-vivo animal study, in order to improve the visibility of pre-cancerous changes in cells and tissues.
In summary for my thesis, I designed a diverse set of tools for computer-aided diagnosis in MGCE. The developed CAD system offers both real time interventional support, as well as facilitation of off-line processing.
In the course of this thesis, various algorithms are proposed to deal with data insufficiency in limited angle tomography. The first category of algorithms are to restore missing data based on data consistency conditions. Specifically, iterative Papoulis-Gerchberg algorithms based on the well known Helgason-Ludwig consistency condition (HLCC) and Fourier consistency conditions of sinograms and a regression-filtering-fusion method based on HLCC are proposed. These algorithms are able to reduce most artifacts for the Shepp-Logan phantom and a clinical image. However, it is suited for parallel-beam limited angle tomography only since HLCC is derived in parallel-beam computed tomography.
The second category of algorithms are to use compressed sensing technologies. The iterative reweighted total variation (wTV) algorithm is adapted for the use in limited angle tomography. While it is able to reduce small streaks well, it is rather inept at reducing large streaks due to scale limitation. Therefore, two implementations of scale-space anisotropic total variation (ssaTV) are proposed to overcome the limitations of wTV. Both ssaTV implementations take the advantage of scale-space optimization and the anisotropic distribution of streak orientations in limited angle tomography. Therefore, they both reduce streak artifacts more effectively and efficiently than wTV.
The last category of algorithms are using machine learning techniques, including traditional machine learning and deep learning. In the traditional machine learning part, reduced error-pruning tree (REPTree) is proposed to predict artifacts from extracted mean-variance-median, Hessian, and shift variant data loss features. Although REPTree achieves very good performance on the validation Shepp-Logan data, it still requires further improvement for clinical applications. Instead, deep learning, particularly the U-Net, achieves very impressive results in 120-degree cone-beam limited angle tomography on clinical data. However, its robustness is still a concern. Our experiments demonstrate that the U-Net is sensitive to Poisson noise and adversarial examples. The robustness to Poisson noise can be improved by retraining on data with noise. However, the retrained U-Net model is still susceptible to adversarial examples. To make the U-Net robust, data consistency deep learning reconstruction is proposed, which utilizes deep learning reconstructions as prior images and further constrains them consistent to measured projection data to improve image qualit},
author = {Huang, Yixing},
faupublication = {yes},
keywords = {limited angle tomography; consistency conditions; compressed sensing; machine learning; deep learning},
peerreviewed = {automatic},
school = {Friedrich-Alexander-Universität Erlangen-Nürnberg},
title = {{Consistency} {Conditions}, {Compressed} {Sensing} and {Machine} {Learning} for {Limited} {Angle} {Tomography}},
url = {https://opus4.kobv.de/opus4-fau/frontdoor/index/index/docId/13203},
year = {2020}
}
@inproceedings{faucris.229603055,
abstract = {People with postlingual onset of deafness often present speech production problems even after hearing rehabilitation by cochlear implantation. In this paper, the speech of 20 postlingual (aged between 33 and 78 years old) and 20 healthy control (aged between 31 and 62 years old) German native speakers is analyzed considering acoustic features extracted from Consonant-to-Vowel (CV) and Vowel-to-Consonant (VC) transitions. The transitions are analyzed with reference to the manner of articulation of consonants according to 5 groups: nasals, sibilants, fricatives, voiced stops, and voiceless stops. Automatic classification between cochlear implant (CI) users and healthy speakers shows accuracies of up to 93%. Considering CV transitions, it is possible to detect specific features of altered speech of CI users. More features are to be evaluated in the future. A comprehensive evaluation of speech changes of CI users will help in the rehabilitation after deafenin},
author = {Arias Vergara, Tomás and Gollwitzer, Sandra and Orozco Arroyave, Juan Rafael and Schuster, Maria and Nöth, Elmar},
booktitle = {Lecture Notes in Computer Science},
date = {2019-09-11/2019-09-13},
doi = {10.1007/978-3-030-27947-9{\_}25},
editor = {Kamil Ekštein},
faupublication = {yes},
isbn = {978-3-030-27946-2},
keywords = {Hearing loss, Acoustic analysis, automatic classification, Cochlear implant},
note = {CRIS-Team Scopus Importer:2019-10-15},
pages = {299-306},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Consonant}-to-{Vowel}/{Vowel}-to-{Consonant} {Transitions} to {Analyze} the {Speech} of {Cochlear} {Implant} {Users}.},
venue = {Ljubljana},
year = {2019}
}
@book{faucris.121176044,
abstract = {Fluoroscopic overlay images rendered from pre-operative volumetric data can provide additional guidance for physicians during catheter ablation procedures for treatment of atrial fibrillation (AFib). As these overlay images are compromised by cardiac and respiratory motion, motion compensation methods have been proposed. The approaches so far either require simultaneous biplane imaging for 3-D motion compensation or, in case of mono-plane X-ray imaging, provide only a limited 2-D functionality. To overcome the downsides of the previously suggested methods, we propose a new approach that facilitates full 3-D motion compensation even if only mono-plane X-ray views are available. To this end, we use constrained model-based 2-D/3-D registration to track a circumferential mapping catheter which is commonly used during AFib catheter ablation procedures. Our approach yields an average 2-D tracking error of 0.6 mm and an average 3-D tracking error of 2.1 mm. © 2011 Springer-Verlag.},
address = {Berlin / Heidelberg},
author = {Brost, Alexander and Wimmer, Andreas and Liao, Rui and Hornegger, Joachim and Strobel, Norbert},
doi = {10.1007/978-3-642-21504-9{\_}13},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2011.tech.IMMD.IMMD5.constr{\_}6},
pages = {133-144},
peerreviewed = {Yes},
publisher = {Springer-verlag},
series = {Lecture Notes in Computer Science},
title = {{Constrained} 2-{D}/3-{D} registration for motion compensation in {AFib} ablation procedures},
volume = {6689},
year = {2011}
}
@article{faucris.120185604,
abstract = {Fluoroscopic overlay images rendered from preoperative volumetric data can provide additional anatomical details to guide physicians during catheter ablation procedures for treatment of atrial fibrillation (AFib). As these overlay images are often compromised by cardiac and respiratory motion, motion compensation methods are needed to keep the overlay images in sync with the fluoroscopic images. So far, these approaches have either required simultaneous biplane imaging for 3-D motion compensation, or in case of monoplane X-ray imaging, provided only a limited 2-D functionality. To overcome the downsides of the previously suggested methods, we propose an approach that facilitates a full 3-D motion compensation even if only monoplane X-ray images are available. To this end, we use a training phase that employs a biplane sequence to establish a patient specific motion model. Afterwards, a constrained model-based 2-D/3-D registration method is used to track a circumferential mapping catheter. This device is commonly used for AFib catheter ablation procedures. Based on the experiments on real patient data, we found that our constrained monoplane 2-D/3-D registration outperformed the unconstrained counterpart and yielded an average 2-D tracking error of 0.6 mm and an average 3-D tracking error of 1.6 mm. The unconstrained 2-D/3-D registration technique yielded a similar 2-D performance, but the 3-D tracking error increased to 3.2 mm mostly due to wrongly estimated 3-D motion components in X-ray view direction. Compared to the conventional 2-D monoplane method, the proposed method provides a more seamless workflow by removing the need for catheter model re-initialization otherwise required when the C-arm view orientation changes. In addition, the proposed method can be straightforwardly combined with the previously introduced biplane motion compensation technique to obtain a good trade-off between accuracy and radiation dose reduction. © 2011 IEEE.},
author = {Brost, Alexander and Wimmer, Andreas and Liao, Rui and Bourier, Felix and Koch, Martin and Strobel, Norbert and Kurzidim, Klaus and Hornegger, Joachim},
doi = {10.1109/TMI.2011.2181184},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
pages = {870-881},
peerreviewed = {Yes},
title = {{Constrained} registration for motion compensation in atrial fibrillation ablation procedures},
volume = {31},
year = {2012}
}
@article{faucris.224238282,
author = {Müller, Meinard and Hedwig, Helmut and Zalkow, Frank and Popescu, Stefan},
doi = {10.3390/app8030436},
faupublication = {yes},
journal = {Applied Sciences},
peerreviewed = {Yes},
title = {{Constraint}-{Based} {Time}-{Scale} {Modification} of {Music} {Recordings} for {Noise} {Beautification}},
url = {http://www.mdpi.com/2076-3417/8/3/436},
volume = {8},
year = {2018}
}
@inproceedings{faucris.121215644,
abstract = {We introduce a novel approach for 3D image reconstruction from CB data acquired along a full circular trajectory. Our approach, which we refer to as the Z-smart reconstruction method, follows the scheme of 1D filtering and 3D backprojection, while providing flexibility in the choice of the filtering directions. This flexibility allows us to modify the appearance of CB artifacts in the reconstruction results, so that, for certain imaging tasks, the Z-smart method can yield image quality that is significantly superior to that achievable with most other reconstruction algorithms for the full-scan circular trajectory. In particular, when imaging objects that have strong but localized heterogeneities in the axial direction, the Z-smart method can outperform both, the popular filtered-backprojection approach of Feldkamp et al., and also ART, i.e. a fully 3D iterative reconstruction method. We provide a numerical evaluation of our algorithm using simulated CB data of an analytically defined tube phantom, with and without added noise. © 2007 IEEE.},
author = {Dennerlein, Frank and Noo, Frédéric and Härer, Wolfgang and Hornegger, Joachim and Lauritsch, Günter},
booktitle = {2007 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS-MIC},
doi = {10.1109/NSSMIC.2007.4437024},
faupublication = {yes},
pages = {4090-4096},
peerreviewed = {unknown},
title = {{Constriction} of cone-beam artifacts by the {Z}-smart reconstruction method},
venue = {Honolulu, HI},
volume = {6},
year = {2007}
}
@inproceedings{faucris.117771764,
abstract = {
In this paper we propose a content-dependent spatio-temporal watermarking scheme for digital videos. Content dependency is achieved by incorporating the hash of the video sequence into the watermark. The video sequence is treated as a 3-dimensional spatio-temporal signal for the purposes of video hash computation and watermark embedding and detection. Our experiments show that the video hash algorithm has good discriminating power and robustness against various attacks. The watermark is also shown in the experiments to have good robustness against a variety of attacks, in particular when the watermark is copied from one video sequence to another.
},
author = {Setyawan, Iwan and Timotius, Ivanna},
booktitle = {The 5th International Conference on Information Technology and Electrical Engineering (ICITEE 2013)},
doi = {10.1109/ICITEED.2013.6676215},
faupublication = {no},
isbn = {978-1-4799-0423-5},
keywords = {digital video watermarking; content-dependent watermarking; copy attack; video hashing},
pages = {79 - 83},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Content}-{Dependent} {Spatio}-{Temporal} {Video} {Watermarking} using 3-{Dimensional} {Discrete} {Cosine} {Transform}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6676215},
venue = {Yogyakarta},
year = {2013}
}
@inproceedings{faucris.113240644,
address = {-},
author = {Levit, Michael and Alshawi, H. and Gorin, Allen and Nöth, Elmar},
booktitle = {Proc. European Conf. on Speech Communication and Technology},
date = {2003-09-01/2003-09-04},
editor = {Eurospeech},
faupublication = {yes},
pages = {925-928},
publisher = {-},
title = {{Context}-{Sensitive} {Evaluation} and {Correction} of {Phone} {Recognition} {Output}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Levit03-CEA.pdf},
venue = {Geneva},
year = {2003}
}
@article{faucris.208854185,
author = {Bernecker, David and Riess, Christian and Angelopoulou, Elli and Hornegger, Joachim},
doi = {10.1016/j.solener.2014.09.005},
faupublication = {yes},
journal = {Solar Energy},
pages = {303-315},
peerreviewed = {Yes},
title = {{Continuous} {Short}-term {Irradiance} {Forecasts} using {Sky} {Images}},
volume = {110},
year = {2014}
}
@article{faucris.121545864,
abstract = {For augmented fluoroscopy during cardiac ablation, a preoperatively acquired 3D model of a patient's left atrium (LA) can be registered to X-ray images recorded during a contrast agent (CA) injection. An automatic registration method that works also for small amounts of CA is desired. We propose two similarity measures: The first focuses on edges of the patient anatomy. The second computes a contrast agent distribution estimate (CADE) inside the 3D model and rates its consistency with the CA as seen in biplane fluoroscopic images. Moreover, temporal filtering on the obtained registration results of a sequence is applied using a Markov chain framework. Evaluation was performed on 11 well-contrasted clinical angiographic sequences and 10 additional sequences with less CA. For well-contrasted sequences, the error for all 73 frames was 7.9 ± 6.3 mm and it dropped to 4.6 ± 4.0 mm when registering to an automatically selected, well enhanced frame in each sequence. Temporal filtering reduced the error for all frames from 7.9 ± 6.3 mm to 5.7 ± 4.6 mm. The error was typically higher if less CA was used. A combination of both similarity measures outperforms a previously proposed similarity measure. The mean accuracy for well contrasted sequences is in the range of other proposed manual registration methods.},
author = {Hoffmann, Matthias and Kowalewski, Christopher and Maier, Andreas and Kurzidim, Klaus and Strobel, Norbert and Hornegger, Joachim},
doi = {10.1155/2016/7690391},
faupublication = {yes},
journal = {International Journal of Biomedical Imaging},
peerreviewed = {unknown},
title = {{Contrast}-based {3D}/{2D} registration of the left atrium: {Fast} versus consistent},
volume = {2016},
year = {2016}
}
@article{faucris.203670598,
author = {Hoffmann, Matthias and Kowalewski, Christopher and Maier, Andreas and Kurzidim, Klaus and Strobel, Norbert and Hornegger, Joachim},
doi = {10.1155/2016/7690391},
faupublication = {yes},
journal = {International Journal of Biomedical Imaging},
note = {UnivIS-Import:2018-09-05:Pub.2016.tech.IMMD.IMMD5.contra{\_}0},
pages = {1-15},
peerreviewed = {unknown},
title = {{Contrast}-based 3-{D}/2-{D} {Registration} of the {Left} {Atrium}: {Fast} vs. {Consistent}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Hoffmann16-C3R.pdf},
volume = {2016},
year = {2016}
}
@inproceedings{faucris.121853204,
author = {Hoffmann, Matthias and Strobel, Norbert and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro},
faupublication = {yes},
note = {UnivIS-Import:2016-06-01:Pub.2016.tech.IMMD.IMMD5.contra},
pages = {n/a},
peerreviewed = {unknown},
title = {{Contrast}-{Based} {Registration} {Of} {Left} {Atria} {To} {Fluoroscopic} {Image} {Sequences} {By} {Temporal} {Markow} {Filtering} {And} {Motion} {Regularization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Hoffmann16-CRO.pdf},
venue = {Prague},
year = {2016}
}
@inproceedings{faucris.120335204,
address = {Braunschweig und Berlin},
author = {Höller, Kurt Emmerich and Schaller, Christian and Tacke, Dominik and Höpfl, Florian and Hornegger, Joachim},
booktitle = {Innovationen bei der Erfassung und Analyse bioelektrischer und biomagnetischer Signale},
date = {2008-07-16/2008-07-18},
editor = {Deutsche Gesellschaft für Biomedizinische Technik},
faupublication = {yes},
pages = {180-183},
publisher = {Physikalisch-Technische Bundesanstalt},
title = {{Contributions} of {Time}-of-{Flight} cameras for biomedical applications},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Hoeller08-COT.pdf},
venue = {Potsdam},
year = {2008}
}
@inproceedings{faucris.106729304,
author = {Taubmann, Oliver and Lauritsch, Günter and Krings, Gregor and Maier, Andreas},
booktitle = {Proceedings of the 4th International Conference on Image Formation in X-ray Computed Tomography},
faupublication = {yes},
note = {UnivIS-Import:2017-01-09:Pub.2016.tech.IMMD.IMMD5.convex{\_}0},
pages = {545-548},
peerreviewed = {unknown},
title = {{Convex} {Temporal} {Regularizers} in {Cardiac} {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Taubmann16-CTR.pdf},
venue = {Bamberg, Germany},
year = {2016}
}
@incollection{faucris.229405115,
author = {Vasquez Correa, Juan and Arias Vergara, Tomás and Rios-Urrego, Cristian D. and Schuster, Maria and Rusz, Jan and Orozco Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
doi = {10.1007/978-3-030-33904-3{\_}66},
editor = {Ingela Nyström, Yanio Hernández Heredia, Vladimir Milián Núñez},
faupublication = {yes},
isbn = {9783030339036},
pages = {697-706},
peerreviewed = {unknown},
series = {Image Processing, Computer Vision, Pattern Recognition, and Graphics},
title = {{Convolutional} {Neural} {Networks} and a {Transfer} {Learning} {Strategy} to {Classify} {Parkinson}’s {Disease} from {Speech} in {Three} {Different} {Languages}},
volume = {11896},
year = {2019}
}
@inproceedings{faucris.208420500,
author = {Vasquez Correa, Juan and Orozco Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017},
doi = {10.21437/Interspeech.2017-1078},
faupublication = {yes},
keywords = {Articulation; Parkinson's disease; Convolutional neural network; Wavelet transform; Time-frequency representations},
pages = {314-318},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{Convolutional} neural network to model articulation impairments in patients with {Parkinson}'s disease},
year = {2017}
}
@inproceedings{faucris.113149784,
address = {Berlin Heidelberg},
author = {Bier, Bastian and Schwemmer, Chris and Maier, Andreas and Hofmann, Hannes and Xia, Yan and Hornegger, Joachim and Struffert, Tobias},
booktitle = {Bildverarbeitung für die Medizin 2013},
date = {2013-03-03/2013-03-05},
doi = {10.1007/978-3-642-36480-8{\_}59},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {338-343},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Convolution}-{Based} {Truncation} {Correction} for {C}-{Arm} {CT} {Using} {Scattered} {Radiation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Bier13-CTC.pdf},
venue = {Heidelberg},
year = {2013}
}
@inproceedings{faucris.237577137,
abstract = {Chronic obstructive pulmonary disease (COPD) is a lung disease that is not fully reversible and one of the leading causes of morbidity and mortality in the world. Early detection and diagnosis of COPD can increase the survival rate and reduce the risk of COPD progression in patients. Currently, the primary examination tool to diagnose COPD is spirometry. However, computed tomography (CT) is used for detecting symptoms and sub-type classification of COPD. Using different imaging modalities is a diffcult and tedious task even for physicians and is subjective to inter-and intra-observer variations. Hence, developing methods that can automatically classify COPD versus healthy patients is of great interest. In this paper, we propose a 3D deep learning approach to classify COPD and emphysema using volume-wise annotations only. We also demonstrate the impact of transfer learning on the classification of emphysema using knowledge transfer from a pre-trained COPD classification model.},
author = {Ahmed, Jalil and Vesal, Sulaiman and Durlak, Felix and Kaergel, Rainer and Ravikumar, Nishant and Rémy-Jardin, Martine and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}8},
editor = {Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm},
faupublication = {yes},
isbn = {9783658292669},
note = {CRIS-Team Scopus Importer:2020-04-21},
pages = {39-45},
peerreviewed = {unknown},
publisher = {Springer},
title = {{COPD} classification in {CT} images using a {3D} convolutional neural network},
venue = {Berlin},
year = {2020}
}
@article{faucris.114469344,
author = {Taubmann, Oliver and Maier, Andreas and Hornegger, Joachim and Lauritsch, Günter and Fahrig, Rebecca},
doi = {10.1118/1.4939878},
faupublication = {yes},
journal = {Medical Physics},
keywords = {Artifact Reduction; Motion-Compensated Reconstruction; 4-D Imaging; Cardiac C-arm CT},
note = {UnivIS-Import:2016-02-10:Pub.2016.tech.IMMD.IMMD5.coping},
pages = {883-893},
peerreviewed = {Yes},
title = {{Coping} with {Real} {World} {Data}: {Artifact} {Reduction} and {Denoising} for {Motion}-{Compensated} {Cardiac} {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Taubmann16-CWR.pdf},
volume = {43},
year = {2016}
}
@article{faucris.113992164,
abstract = {With default settings, measurements are taken at 1 mm intervals along the vessel centreline and from 10 different angles at each measurement point. This allows for outlier detection and noise-robust measurements without the burden and subjectivity a manual measurement process would incur. Graphical measurement results can be directly exported to vector or bitmap graphics for integration into scientific publications. Centreline and lumen segmentations can be exported as point clouds and in various mesh formats. We evaluated the diameter measurement process using three phantom datasets. An average deviation of 0.03 +/- 0.03 mm was found.},
author = {Schwemmer, Chris and Forman, Christoph and Wetzl, Jens and Maier, Andreas and Hornegger, Joachim},
doi = {10.1088/0031-9155/59/17/5163},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
keywords = {medical imaging;coronary vessels;evaluation;software},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.coroev},
pages = {5163-5174},
peerreviewed = {Yes},
title = {{CoroEval}: a multi-platform, multi-modality tool for the evaluation of {3D} coronary vessel reconstructions},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Schwemmer14-CA.pdf},
volume = {59},
year = {2014}
}
@inproceedings{faucris.276489009,
abstract = {CoronARe ranks state-of-the-art methods in symbolic and tomographic coronary artery reconstruction from interventional C-arm rotational angiography. Specifically, we benchmark the performance of the methods using accurately pre-processed data, and study the effects of imperfect pre-processing conditions (segmentation and background subtraction errors). In this first iteration of the challenge, evaluation is performed in a controlled environment using digital phantom images, where accurate 3D ground truth is known.},
author = {Cimen, Serkan and Unberath, Mathias and Frangi, Alejandro and Maier, Andreas},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2017-09-14/2017-09-14},
doi = {10.1007/978-3-319-67564-0{\_}10},
editor = {M. Jorge Cardoso, Tal Arbel},
faupublication = {yes},
isbn = {9783319675633},
keywords = {3D reconstruction; Angiography; C-arm Cone-beam CT; Motion compensation},
note = {CRIS-Team Scopus Importer:2022-06-05},
pages = {96-104},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{CoronARe}: {A} coronary artery reconstruction challenge},
venue = {Quebec City, QC, CAN},
volume = {10555 LNCS},
year = {2017}
}
@inproceedings{faucris.228667465,
abstract = {Assessing coronary artery plaque segments in coronary CT angiography scans is an important task to improve patient management and clinical outcomes, as it can help to decide whether invasive investigation and treatment are necessary. In this work, we present three machine learning approaches capable of performing this task. The first approach is based on radiomics, where a plaque segmentation is used to calculate various shape-, intensity- and texture-based features under different image transformations. A second approach is based on deep learning and relies on centerline extraction as sole prerequisite. In the third approach, we fuse the deep learning approach with radiomic features. On our data the methods reached similar scores as simulated fractional flow reserve (FFR) measurements, which - in contrast to our methods - requires an exact segmentation of the whole coronary tree and often time-consuming manual interaction. In literature, the performance of simulated FFR reaches an AUC between 0.79–0.93 predicting an abnormal invasive FFR that demands revascularization. The radiomics approach achieves an AUC of 0.84, the deep learning approach 0.86 and the combined method 0.88 for predicting the revascularization decision directly. While all three proposed methods can be determined within seconds, the FFR simulation typically takes several minutes. Provided representative training data in sufficient quantities, we believe that the presented methods can be used to create systems for fully automatic non-invasive risk assessment for a variety of adverse cardiac events.
We use four speech databases with realistic, non-prompted emotions, and a large state-of-the-art acoustic feature vector, for cross-corpus classifications, in turn employing three databases for training and the fourth for testing. Categorical and continuous (dimensional) annotation is mapped onto a representation of valence with the three classes positive, neutral, and negative. This cross-corpus classification is compared with within corpus classifications. We interpret performance and most important features.
},
author = {Eyben, Florian and Batliner, Anton and Schuller, Björn and Seppi, Dino and Steidl, Stefan},
booktitle = {Proc. of theThird International Workshop on EMOTION (satellite of LREC): CORPORA FOR RESEARCH ON EMOTION AND AFFECT},
date = {2010-05-23},
editor = {LREC},
faupublication = {yes},
pages = {77-82},
peerreviewed = {Yes},
title = {{Cross}-{Corpus} {Classification} of {Realistic} {Emotions} - {Some} {Pilot} {Experiments}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Eyben10-CCO.pdf},
venue = {Valetta},
year = {2010}
}
@inproceedings{faucris.282904026,
abstract = {State-of-the-art automatic speech recognition (ASR) systems perform well on healthy speech. However, the performance on impaired speech still remains an issue. The current study explores the usefulness of using Wav2Vec self-supervised speech representations as features for training an ASR system for dysarthric speech. Dysarthric speech recognition is particularly difficult as several aspects of speech such as articulation, prosody and phonation can be impaired. Specifically, we train an acoustic model with features extracted from Wav2Vec, Hubert, and the cross-lingual XLSR model. Results suggest that speech representations pretrained on large unlabelled data can improve word error rate (WER) performance. In particular, features from the multilingual model led to lower WERs than Fbanks or models trained on a single language. Improvements were seen in English speakers with cerebral palsy caused dysarthria (UASpeech corpus), Spanish speakers with Parkinsonian dysarthria (PC-GITA corpus) and Italian speakers with paralysis-based dysarthria (EasyCall corpus). Compared to using Fbank features, XLSR-based features reduced WERs by 6.8%, 22.0%, and 7.0% for the UASpeech, PC-GITA, and EasyCall corpus, respectively.
},
address = {Cham},
author = {Huang, Yixing and Preuhs, Alexander and Lauritsch, Guenter and Manhart, Michael and Huang, Xiaolin and Maier, Andreas},
booktitle = {Machine Learning for Medical Image Reconstruction},
date = {2019-10-17/2019-10-17},
doi = {10.1007/978-3-030-33843-5{\_}10},
editor = {Knoll, Florian and Maier, Andreas and Rueckert, Daniel and Ye, Jong Chul},
faupublication = {yes},
isbn = {978-3-030-33842-8},
keywords = {Deep learning; Limited angle tomography; Data consistency; Poisson noise; Robustness; Generalization ability},
pages = {101-112},
peerreviewed = {Yes},
publisher = {Springer International Publishing},
title = {{Data} {Consistent} {Artifact} {Reduction} for {Limited} {Angle} {Tomography} with {Deep} {Learning} {Prior}},
url = {https://link.springer.com/chapter/10.1007/978-3-030-33843-5{\_}10},
venue = {Shenzhen, China},
year = {2019}
}
@inproceedings{faucris.121339284,
author = {Hahn, Dieter and Daum, Volker and Hornegger, Joachim and Kuwert, Torsten},
booktitle = {Proceedings of the MICCAI Workshop on Probabilistic Models For Medical Image Analysis},
date = {2009-09-20},
editor = {Wells William, Joshi Sarang, Pohl Kilian},
faupublication = {yes},
pages = {115-126},
peerreviewed = {unknown},
title = {{Data}-{Driven} {Density} {Estimation} applied to {SPECT} {Subtraction} {Imaging} for {Epilepsy} {Diagnosis}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Hahn09-DDE.pdf},
venue = {London},
year = {2009}
}
@article{faucris.255196433,
abstract = {Data truncation is a common problem in computed tomography (CT). Truncation causes cupping artifacts inside the field-of-view (FOV) and anatomical structures missing outside the FOV. Deep learning has achieved impressive results in CT reconstruction from limited data. However, its robustness is still a concern for clinical applications. Although the image quality of learning-based compensation schemes may be inadequate for clinical diagnosis, they can provide prior information for more accurate extrapolation than conventional heuristic extrapolation methods. With extrapolated projection, a conventional image reconstruction algorithm can be applied to obtain a final reconstruction. In this work, a general plug-and-play (PnP) method for truncation correction is proposed based on this idea, where various deep learning methods and conventional reconstruction algorithms can be plugged in. Such a PnP method integrates data consistency for measured data and learned prior image information for truncated data. This shows to have better robustness and interpretability than deep learning only. To demonstrate the efficacy of the proposed PnP method, two state-of-the-art deep learning methods, FBPConvNet and Pix2pixGAN, are investigated for truncation correction in cone-beam CT in noise-free and noisy cases. Their robustness is evaluated by showing false negative and false positive lesion cases. With our proposed PnP method, false lesion structures are corrected for both deep learning methods. For FBPConvNet, the root-mean-square error (RMSE) inside the FOV can be improved from 92HU to around 30HU by PnP in the noisy case. Pix2pixGAN solely achieves better image quality than FBPConvNet solely for truncation correction in general. PnP further improves the RMSE inside the FOV from 42HU to around 27HU for Pix2pixGAN. The efficacy of PnP is also demonstrated on real clinical head data.
Aim/Introduction: Single Photon Emitted Computed Tomography (SPECT) images are characterized
by a high degree of image noise, which is due to the low photon count at the detector. Recently,
several deep learning-based approaches for image denoising have been proposed for low-dose
Computed Tomography (CT). We investigate their suitability for SPECT denoising.
Materials and Methods: In order to have a groundtruth for training the networks, a Monte Carlo
Simulation was set up with the SIMIND software, where in total 24 SPECT acquisitions of brains,
lungs, livers and skeleton were simulated with the XCAT phantom. Pairs of noisy and clean SPECT
images were then used for training the neural networks. The networks tested were the U-Net as
proposed by Heinrich et al. [1], the convolutional denoising autoencoder (CNN DAE) proposed by
Gondara et al. [2] and a custom U-Net that had a depth of 4 layers with 2 convolutions, Batch
Normalization and ReLU in each layer. Training of the networks was done with the hyperparameters
as described in the original publications.
Results: The best denoising performance of the neural networks was achieved by either the CNN DAE
when measured with the Structural Similarity (SSIM) index of 0.933 or by the custom U-Net with a
Peak Signal to Noise Ratio (PSNR) of 30.03 dB. This corresponded to a signal quality improvement of
0.09 compared to the noisy input when measured with the SSIM, or 5.9 dB when measured with the
PSNR. The denoised SPECT images showed improved visual appearance, however, gain in image
quality was not as distinct as on low-dose CT data. We assume this was due to the image
characteristics of SPECT images, which are characterized by few distinct image values and a more
heterogeneous pixel intensity distribution compared to CT data.
Conclusion: Image characteristics in SPECT pose a special challenge to deep learning-based image
denoising methods, as the signal is sparse and contains a high degree of noise. We believe this, in
conjunction with the limited number of samples explains the weaker benefit in performance in SPECT
when compared to low-dose CT data. We assume that with a more diverse training set and
specialized loss function suitable for SPECT data , we can further increase performanc},
address = {Berlin, Heidelberg},
author = {Reymann, Maximilian and Würfl, Tobias and Ritt, Philipp and Cachovan, Michal and Stimpel, Bernhard and Maier, Andreas},
booktitle = {European Journal of Nuclear Medicine and Molecular Imaging (2019) 46 (Suppl 1): S1–S952, 10.1007/s00259-019-04486-2},
date = {2019-10-12/2019-10-16},
doi = {10.1007/s00259-019-04486-2},
editor = {Springer-Verlag GmbH Germany, part of Springer Nature 2019},
faupublication = {yes},
keywords = {Deep Learning; SPECT; Denoising; Monte Carlo Simulation; XCAT; Phantom},
pages = {219-219},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Deep} {Image} {Denoising} in {SPECT}},
url = {https://link.springer.com/article/10.1007/s00259-019-04486-2},
venue = {Barcelona},
year = {2019}
}
@inproceedings{faucris.230612281,
abstract = {Analysing coronary artery plaque segments with respect to their functional significance and therefore their influence to patient management in a non-invasive setup is an important subject of current research. In this work we compare and improve three deep learning algorithms for this task: A 3D recurrent convolutional neural network (RCNN), a 2D multi-view ensemble approach based on texture analysis, and a newly proposed 2.5D approach. Current state of the art methods utilising fluid dynamics based fractional flow reserve (FFR) simulation reach an AUC of up to 0.93 for the task of predicting an abnormal invasive FFR value. For the comparable task of predicting revascularisation decision, we are able to improve the performance in terms of AUC of both existing approaches with the proposed modifications, specifically from 0.80 to 0.90 for the 3D-RCNN, and from 0.85 to 0.90 for the multi-view texture-based ensemble. The newly proposed 2.5D approach achieves comparable results with an AUC of 0.90.
98% on previously unseen subjects, and a well comparable image quality with the state-of-the-art ECG-based reconstruction. Our method enables an ECG-free workflow for continuous cardiac scans with simultaneous anatomic and functional imaging with multiple contrasts. It can be potentially integrated without adapting the sampling scheme to other continuous sequences by using the imaging data for navigation and reconstructio},
author = {Hoppe, Elisabeth and Wetzl, Jens and Yoon, Seung Su and Bacher, Mario and Roser, Philipp and Stimpel, Bernhard and Preuhs, Alexander and Maier, Andreas},
doi = {10.1109/tmi.2021.3073091},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
peerreviewed = {Yes},
title = {{Deep} learning-based {ECG}-free {Cardiac} {Navigation} for {Multi}-{Dimensional} and {Motion}-{Resolved} {Continuous} {Magnetic} {Resonance} {Imaging}},
year = {2021}
}
@article{faucris.267718577,
abstract = {The problem of data truncation in Computed Tomography (CT) is caused
by the missing data when the patient exceeds the Scan Field of View (SFOV) of a CT
scanner. The reconstruction of a truncated scan produces severe truncation artifacts
both inside and outside the SFOV. We have employed a deep learning-based approach
to extend the field of view and suppress truncation artifacts. Thereby, our aim is
to generate a good estimate of the real patient data and not to provide a perfect
and diagnostic image even in regions beyond the SFOV of the CT scanner. This
estimate could then be used as an input to higher order reconstruction algorithms
[1]. To evaluate the influence of the network structure and layout on the results,
three convolutional neural networks (CNNs), in particular a general CNN called
ConvNet, an autoencoder, and the U-Net architecture have been investigated in this
paper. Additionally, the impact of L1, L2, structural dissimilarity and perceptual
loss functions on the neural network’s learning have been assessed and evaluated.
The evaluation of data set comprising 12 truncated test patients demonstrated that
the U-Net in combination with the structural dissimilarity loss showed the best
performance in terms of image restoration in regions beyond the SFOV of the CT
scanner. Moreover, this network produced the best mean absolute error, L1, L2, and
structural dissimilarity evaluation measures on the test set compared to other applied
networks. Therefore, it is possible to achieve truncation artifact removal using deep
learning techniques.
},
author = {Bergler, Christian and Schmitt, Manuel and Cheng, Rachael Xi and Maier, Andreas and Barth, Volker and Nöth, Elmar},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH},
date = {2019-09-15/2019-09-19},
doi = {10.21437/Interspeech.2019-1857},
editor = {Gernot Kubin, Thomas Hain, Bjorn Schuller, Dina El Zarka, Petra Hodl},
faupublication = {yes},
keywords = {orca; call type; unsupervised; deep learning, clustering},
note = {CRIS-Team Scopus Importer:2019-11-19},
pages = {3357-3361},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{Deep} {Learning} for {Orca} {Call} {Type} {Identification} – {A} {Fully} {Unsupervised} {Approach}},
venue = {Graz},
year = {2019}
}
@article{faucris.308292202,
author = {Huang, Yixing and Maier, Andreas and Fan, Fuxin and Kreher, Björn W. and Huang, Xiaolin and Fietkau, Rainer and Bert, Christoph and Putz, Florian},
doi = {10.1016/S0167-8140(23)66608-3},
faupublication = {yes},
journal = {Radiotherapy and Oncology},
keywords = {Deep learning; perspective deformation; X-ray imaging},
pages = {S1404},
peerreviewed = {Yes},
title = {{Deep} learning for perspective deformation correction in {X}-ray imaging},
volume = {182},
year = {2023}
}
@article{faucris.287241217,
abstract = {Historical documents contain essential information about the past, including places, people, or events. Many of these valuable cultural artifacts cannot be further examined due to aging or external influences, as they are too fragile to be opened or turned over, so their rich contents remain hidden. Terahertz (THz) imaging is a nondestructive 3D imaging technique that can be used to reveal the hidden contents without damaging the documents. As noise or imaging artifacts are predominantly present in reconstructed images processed by standard THz reconstruction algorithms, this work intends to improve THz image quality with deep learning. To overcome the data scarcity problem in training a supervised deep learning model, an unsupervised deep learning network (CycleGAN) is first applied to generate paired noisy THz images from clean images (clean images are generated by a handwriting generator). With such synthetic noisy-to-clean paired images, a supervised deep learning model using Pix2pixGAN is trained, which is effective to enhance real noisy THz images. After Pix2pixGAN denoising, 99% characters written on one-side of the Xuan paper can be clearly recognized, while 61% characters written on one-side of the standard paper are sufficiently recognized. The average perceptual indices of Pix2pixGAN processed images are 16,83, which is very close to the average perceptual index 16.19 of clean handwriting images. Our work has important value for THz-imaging-based nondestructive historical document analysis.
Monitoring fetal wellbeing is key in modern obstetrics. While fetal movement is routinely used as a proxy to fetal wellbeing, accurate, noninvasive, long-term monitoring of fetal movement is challenging. A few accelerometers-based systems have been developed in the past few years , to tackle common issues in ultrasound, monitoring and monitoring, self-administered monitoring of fetal exercise during preg- nancy. HOWEVER, many questions remain unanswered to date on the optimal setup in terms of body-worn accelerometers as well as signal processing and machine learning techniques used to detect fetal movement. In this paper, we investigate the trade-offs between sensor and positioning, the presence of reference accelerometers. Using a dataset of 15 measurements collected Employing 6 Three- axial accelerometers we show did Including a reference ac celerometer on the back of the participant consistently Improves fetal movement detection performance Regardless of the number of sensors Utilized. We also have two accelerometers plus a reference accelerometer.
},
address = {Orlando, USA},
author = {Gradl, Stefan and Altini, Marco and Grieten, Lars and Eskofier, Björn and Geusens, Nele and Mullan, Patrick and Penders, Julien and Rooijakkers, Michiel},
booktitle = {Proceedings of the 38th IEEE Engineering in Medicine and Biology Society Conference (EMBC 2016)},
date = {2016-08-16/2016-08-20},
editor = {IEEE Engineering in Medicine and Biology Society},
faupublication = {yes},
pages = {5319-5322},
peerreviewed = {unknown},
title = {{Detection} of {Fetal} {Kicks} {Using} {Body}-{Worn} {Accelerometers} {During} {Pregnancy}: {Trade}-offs {Between} {Sensors} {Number} and {Positioning}},
venue = {Orlando, USA},
year = {2016}
}
@inproceedings{faucris.266917759,
abstract = {Computed Tomography Angiography is a key modality providing insights into the cerebrovascular vessel tree that are crucial for the diagnosis and treatment of ischemic strokes, in particular in cases of large vessel occlusions (LVO). Thus, the clinical workflow greatly benefits from an automated detection of patients suffering from LVOs. This work uses convolutional neural networks for case-level classification trained with elastic deformation of the vessel tree segmentation masks to artificially augment training data. Using only masks as the input to our model uniquely allows us to apply such deformations much more aggressively than one could with conventional image volumes while retaining sample realism. The neural network classifies the presence of an LVO and the affected hemisphere. In a 5-fold cross validated ablation study, we demonstrate that the use of the suggested augmentation enables us to train robust models even from few data sets. Training the EfficientNetB1 architecture on 100 data sets, the proposed augmentation scheme was able to raise the ROC AUC to 0.85 from a baseline value of 0.57 using no augmentation. The best performance was achieved using a 3D-DenseNet yielding an AUC of 0.88. The augmentation had positive impact in classification of the affected hemisphere as well, where the 3D-DenseNet reached an AUC of 0.93 on both sides.
The usage of tracking technology in sports became standard in most major team sports like soccer, basketball or American football. Official tracking in soccer is done by video tracking and is currently limited to physical assessments of the players. New high rate tracking technologies for players and balls could also enable a detailed technical assessment of athletes. This work investigates the detection of single ball contacts, distinguishing left and right foot, using a radio based real-time tracking system. Ball tracking is done at 2000 Hz and player tracking at 200 Hz. Miniaturized transmitters were attached to the shins, enabling the distinction between left and right contacts with the ball. Data acquisition was done in an indoor environment. Six small sided games (749 contacts) and 25 repetitions of training exercises (195 contacts) were recorded. The ground truth of 941 single ball contacts was assessed by video annotation. Detection in the training scenario shows a precision of 97-100 % and a recall of 87-100 %. For the game scenario, precision is 89 % and recall reaches 93 %. Detection errors mainly affect non crucial contacts during longer dribblings, which are not the main interest of many analyses. The high precision and recall rates indicate a solid base for higher level technical assessments in automatic match (statistics) and training analysis (skill evaluation).},
author = {Witt, Nicolas and Völker, Matthias and Eskofier, Björn},
booktitle = {icSports 2016},
date = {2016-11-07/2016-11-09},
editor = {SCITEPRESS},
faupublication = {yes},
keywords = {soccer;tracking data;ball contacts; actions},
pages = {35-35},
peerreviewed = {Yes},
title = {{Detection} of {Single} {Ball} {Contacts} using a {Radio}-based {Tracking} {System} - {A} {Basis} for {Technical} {Performance} {Analysis}},
venue = {Porto},
year = {2016}
}
@inproceedings{faucris.217467622,
abstract = {Automatic task-based image quality assessment has been of importance in various clinical and research applications. In this paper, we propose a neural network model observer, a novel concept which has recently been investigated. It is trained and tested on simulated images with different contrast levels, with the aim of trying to distinguish images based on their quality/contrast. Our model shows promising properties that its output is sensitive to image contrast, and generalizes well to unseen low-contrast signals. We also compare the results of the proposed approach with those of a channelized hotelling observer (CHO), on the same simulated dataset.},
author = {Xu, Yang and Schebesch, Frank and Ravikumar, Nishant and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}47},
editor = {Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2019-05-14},
pages = {212-217},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Detection} of {Unseen} {Low}-{Contrast} {Signals} {Using} {Classic} and {Novel} {Model} {Observers}},
venue = {Lübeck},
year = {2019}
}
@article{faucris.217016729,
abstract = {The forming limit curve (FLC) is used to model the onset of sheet metal instability during forming processes e.g., in the area of finite element analysis, and is usually determined by evaluation of strain distributions, derived with optical measurement systems during Nakajima tests. Current methods comprise of the standardized DIN EN ISO 12004-2 or time-dependent approaches that heuristically limit the evaluation area to a fraction of the available information and show weaknesses in the context of brittle materials without a pronounced necking phase. To address these limitations, supervised and unsupervised pattern recognition methods were introduced recently. However, these approaches are still dependent on prior knowledge, time, and localization information. This study overcomes these limitations by adopting a Siamese convolutional neural network (CNN), as a feature extractor. Suitable features are automatically learned using the extreme cases of the homogeneous and inhomogeneous forming phase in a supervised setup. Using robust Student's t mixture models, the learned features are clustered into three distributions in an unsupervised manner that cover the complete forming process. Due to the location and time independency of the method, the knowledge learned from formed specimen up until fracture can be transferred on to other forming processes that were prematurely stopped and assessed using metallographic examinations, enabling probabilistic cluster membership assignments for each frame of the forming sequence. The generalization of the method to unseen materials is evaluated in multiple experiments, and additionally tested on an aluminum alloy AA5182, which is characterized by Portevin-LE Chatlier effects.},
author = {Jaremenko, Christian and Ravikumar, Nishant and Affronti, Emanuela and Merklein, Marion and Maier, Andreas},
doi = {10.3390/ma12071051},
faupublication = {yes},
journal = {Materials},
note = {CRIS-Team WoS Importer:2019-05-07},
peerreviewed = {Yes},
title = {{Determination} of {Forming} {Limits} in {Sheet} {Metal} {Forming} {Using} {Deep} {Learning}},
volume = {12},
year = {2019}
}
@inproceedings{faucris.121458304,
address = {Berlin/Offenbach},
author = {Hönig, Florian Thomas and Hacker, Christian and Warnke, Volker and Nöth, Elmar and Hornegger, Joachim and Kornhuber, Johannes},
booktitle = {Tagungsband zum 1. deutschen AAL-Kongress},
date = {2008-01-30/2008-02-01},
editor = {BMBF (Bundesministerium für Bildung und Forschung), VDE (Verband der Elektrotechnik Elektronik Informationstechnik e.V.)},
faupublication = {yes},
pages = {371-375},
publisher = {VDE Verlag GMBH},
title = {{Developing} {Enabling} {Technologies} for {Ambient} {Assisted} {Living}: {Natural} {Language} {Interfaces}, {Automatic} {Focus} {Detection} and {User} {State} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Hoenig08-DET.pdf},
venue = {Berlin},
year = {2008}
}
@inproceedings{faucris.113252744,
author = {Giese, Katrin and Hönig, Florian Thomas and Erzigkeit, Andreas and Soutschek, Stefan and Hornegger, Joachim and Kornhuber, Johannes},
booktitle = {Proceedings of the 5th Russian Bavarian Conference on Bio-Medical Engineering (RBC)},
date = {2009-07-01/2009-07-04},
editor = {Feußner Hubertus},
faupublication = {yes},
pages = {157-160},
peerreviewed = {unknown},
title = {{Development} of a {Computerized} {Diagnostic} {System} for {Elderly} {Drivers}: {A} {Feasibility} {Study}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Giese09-DOA.pdf},
venue = {München},
year = {2009}
}
@inproceedings{faucris.111781604,
abstract = {Advances in reconstruction techniques and instrumentation improve image quality. Improved image quality could either improve confidence and diagnostic ability, or increase throughput, and lower injected dose. Current imaging guidelines give insufflent consideration to advances in iterative reconstruction methods that include collimator modeling, attenuation, and scatter correction, and best matched acquisitions. Thus advanced reconstruction is often sub-optimally used in a clinical setting. In this work, we first characterize the effects of various acquisition and reconstruction protocols with the explicit aim to reduce scan time without adverse affects as compared to FBP driven protocols. For this we characterize image features, such as nonuniformity and wall thickness of the cardiac insert inside the large anthropomorphic torso phantom (Data Spectrum) and correlate them with human observer ROC results. When reconstructing the data with OSEM with 3D collimator and detector response compensation ("Flash3D") we found that the detection ability is not impacted when using 6° angular steps, and thus reducing the acquisition time by 50%, as compared to the current method. A further reduction can be achieved if the rest study is scanned in the continuous instead of the step-and-shoot mode (10%). Dwell time can also be reduced slightly; however the myocardial count density should not be below at least 1 cnt/mm for rest and summed stress. Clinical trials need to confirm the findings. © 2006 IEEE.},
author = {Zeintl, Johannes and Hornegger, Joachim and et al.},
author_hint = {Vija A., Zeintl J., Chapman J., Hawman E., Hornegger J.},
booktitle = {2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD},
doi = {10.1109/NSSMIC.2006.354246},
faupublication = {yes},
pages = {1811-1816},
peerreviewed = {unknown},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Development} of rapid {SPECT} acquisition protocol for myocardial perfusion imaging},
venue = {San Diego, CA},
volume = {3},
year = {2007}
}
@inproceedings{faucris.121016104,
address = {Salt Lake City, Utah, USA},
author = {Bögel, Marco and Maier, Andreas and Hofmann, Hannes and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Proceedings of the second international conference on image formation in x-ray computed tomography},
date = {2012-06-24/2012-06-27},
editor = {Noo Frederic},
faupublication = {yes},
pages = {13-16},
peerreviewed = {unknown},
publisher = {University of Utah},
title = {{Diaphragm} {Tracking} for {Respiratory} {Motion} {Compensated} {Cardiac} {C}-{Arm} {CT}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Boegel12-DTF.pdf},
venue = {Salt Lake City, UT},
year = {2012}
}
@inproceedings{faucris.120326404,
address = {Berlin},
author = {Bögel, Marco and Maier, Andreas and Hofmann, Hannes and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Bildverarbeitung für die Medizin 2011},
date = {2011-03-20/2011-03-22},
editor = {Handels Heinz},
faupublication = {yes},
pages = {33-38},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Diaphragm} {Tracking} in {Cardiac} {C}-{Arm} {Projection} {Data}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Boegel12-DTI.pdf},
venue = {Lübeck},
year = {2012}
}
@incollection{faucris.107954264,
address = {Heidelberg},
author = {Michelson, Georg and Hornegger, Joachim and Lausen, Berthold},
booktitle = {Glaukom 2007},
doi = {10.1007/978-3-540-74919-6{\_}11},
faupublication = {yes},
isbn = {978-3-540-74918-9},
pages = {137-148},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Die} {Papille} als {Screening}-{Parameter} auf {Glaukom} - {Die} {Papille} beim {Glaukom}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Michelson08-DPA.pdf},
year = {2008}
}
@article{faucris.107889144,
author = {Michelson, Georg and Hornegger, Joachim and Wärntges, Simone and Lausen, Berthold},
faupublication = {yes},
journal = {Deutsches Ärzteblatt},
pages = {585-589},
peerreviewed = {unknown},
title = {{Die} {Papille} als {Screening}-{Parameter} für die {Früherkennung} des {Glaukoms} - {The} papilla as screening parameter for early diagnosis of glaucoma},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Michelson08-DPAS.pdf},
year = {2008}
}
@inproceedings{faucris.121412764,
address = {Norderstedt},
author = {Riedhammer, Korbinian Thomas and Haderlein, Tino and Nöth, Elmar and Toy, Hikmet and Eysholdt, Ulrich and Rosanowski, Frank},
booktitle = {Aktuelle phoniatrisch-pädaudiologische Aspekte 2006},
date = {2006-09-15/2006-09-17},
editor = {Gross Manfred, Kruse Eberhard},
faupublication = {yes},
pages = {51-53},
publisher = {Books on Demand GmbH},
title = {{Die} tracheoösophageale {Ersatzstimme}: {Automatische} {Verständlichkeitsbewertung} über das {Telefon}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Riedhammer06-DTE.pdf},
venue = {Heidelberg},
year = {2006}
}
@inproceedings{faucris.120928104,
address = {Norderstedt},
author = {Bellanova, Martina and Schuster, Maria and Haderlein, Tino and Nöth, Elmar and Eysholdt, Ulrich and Rosanowski, Frank},
booktitle = {Aktuelle phoniatrisch-pädaudiologische Aspekte 2006},
date = {2006-09-15/2006-09-17},
editor = {Gross Manfred, Kruse Eberhard},
faupublication = {yes},
pages = {48-50},
publisher = {Books on Demand GmbH},
title = {{Die} tracheoösophageale {Ersatzstimme}: {Evaluation} durch {Experten}, naive {Hörer} und automatische {Spracherkennung}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Bellanova06-DTE.pdf},
venue = {Heidelberg},
year = {2006}
}
@inproceedings{faucris.118291624,
address = {Norderstedt},
author = {Haderlein, Tino and Zorn, Dominik and Nöth, Elmar and Toy, Hikmet and Eysholdt, Ulrich and Rosanowski, Frank},
booktitle = {Aktuelle phoniatrisch-pädaudiologische Aspekte 2006},
date = {2006-09-15/2006-09-17},
editor = {Gross Manfred, Kruse Eberhard},
faupublication = {yes},
pages = {56-58},
peerreviewed = {Yes},
publisher = {Books on Demand GmbH},
title = {{Die} tracheoösophageale {Ersatzstimme}: {Grafische} {Darstellung} von {Sprechstörungen} mithilfe der {Sammon}-{Transformation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Haderlein06-DTE.pdf},
venue = {Heidelberg},
year = {2006}
}
@inproceedings{faucris.120204304,
abstract = {The comparison of inter- with intra-ictal SPECT images plays an important role during the diagnosis and treatment of epilepsy patients. Although there is already commercial software available to address this problem using complex clinical workflows, this article describes a different way of looking at this issue. During the examination various issues arise from differing tracer concentrations, patient movement between the acquisitions at different times and also the lack of morphological information. The goal of the presented work is therefore to present an approach that is on the one hand easy to use for the physician and on the other hand both reliable and robust enough to cope with the previously mentioned challenges. The proposed algorithm introduces methods that have already been applied successfully in digital subtraction angiography (DSA). The work comprises of several steps for the intensity normalization, image registration, difference imaging and the incorporation of an MR image for the spatial localization. As a result, information is provided about differences within the cerebral blood flow (CBF) and active brain areas between the intra- and inter-ictal states. Very new to the field of SPECT brain imaging is the application of non-rigid registration techniques. This helps to drastically reduce the artifacts within the difference images due to a bias of the standard rigid registration. Acquired results from a collective of 11 patients show that this additional feature helps to further improve the image quality. © 2007 IEEE.},
author = {Hahn, Dieter and Daum, Volker and Hornegger, Joachim and Bautz, Werner and Kuwert, Torsten},
booktitle = {2007 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS-MIC},
doi = {10.1109/NSSMIC.2007.4437074},
faupublication = {yes},
pages = {4331-4335},
peerreviewed = {unknown},
title = {{Difference} imaging of inter- and intra-ictal {SPECT} images for the localization of seizure onset in epilepsy},
venue = {Honolulu, HI},
volume = {6},
year = {2007}
}
@inproceedings{faucris.203344578,
author = {Käppler, Sebastian and Maier, Andreas and Riess, Christian},
booktitle = {Proceedings of the 5th International Conference on Image Formation in X-ray Computed Tomography (CT-Meeting)},
faupublication = {yes},
keywords = {X-ray Phase Contrast; Tomography; Noise; Grating orientation},
pages = {119-122},
peerreviewed = {Yes},
title = {{Differential} {Tomography}: {Influence} of {Sensitivity} {Direction} and {Noise}-suppressing {Windows}},
year = {2018}
}
@inproceedings{faucris.124239764,
abstract = {The ease with which digital images can be manipulated without severe degradation of quality makes it necessary to be able to verify the authenticity of digital images. One way to establish the image authenticity is by computing a hash sequence from an image. This hash sequence must be robust against non content-altering manipulations, but must be able to show if the content of the image has been tampered with. Furthermore, the hash has to have enough differentiating power such that the hash sequences from two different images are not similar. This paper presents an image hashing system based on local Histogram of Oriented Gradients. The system is shown to have good differentiating power, robust against non content-altering manipulations such as filtering and JPEG compression and is sensitive to content-altering attacks.},
author = {Setyawan, Iwan and Timotius, Ivanna},
booktitle = {The 6th International Conference on Information Technology and Electrical Engineering (ICITEE 2014)},
doi = {10.1109/ICITEED.2014.7007903},
faupublication = {no},
isbn = {978-1-4799-5302-8},
keywords = {Histogram of Oriented Gradients; image hashing; image authentication},
pages = {1 - 4},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Digital} {Image} {Hashing} using {Local} {Histogram} of {Oriented} {Gradients}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7007903},
venue = {Yogyakarta},
year = {2014}
}
@inproceedings{faucris.216840589,
abstract = {Segmentation of the left atrial chamber and assessing its morphology, are essential for improving our understanding of atrial fibrillation, the most common type of cardiac arrhythmia. Automation of this process in 3D gadolinium enhanced-MRI (GE-MRI) data is desirable, as manual delineation is time-consuming, challenging and observer-dependent. Recently, deep convolutional neural networks (CNNs) have gained tremendous traction and achieved state-of-the-art results in medical image segmentation. However, it is difficult to incorporate local and global information without using contracting (pooling) layers, which in turn reduces segmentation accuracy for smaller structures. In this paper, we propose a 3D CNN for volumetric segmentation of the left atrial chamber in LGE-MRI. Our network is based on the well known U-Net architecture. We employ a 3D fully convolutional network, with dilated convolutions in the lowest level of the network, and residual connections between encoder blocks to incorporate local and global knowledge. The results show that including global context through the use of dilated convolutions, helps in domain adaptation, and the overall segmentation accuracy is improved in comparison to a 3D U-Net.},
author = {Vesal, Sulaiman and Ravikumar, Nishant and Maier, Andreas},
booktitle = {STACOM 2018: Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges},
doi = {10.1007/978-3-030-12029-0{\_}35},
faupublication = {yes},
note = {CRIS-Team Scopus Importer:2019-05-02},
pages = {319-328},
peerreviewed = {Yes},
publisher = {Springer Verlag},
title = {{Dilated} {Convolutions} in {Neural} {Networks} for {Left} {Atrial} {Segmentation} in {3D} {Gadolinium} {Enhanced}-{MRI}},
volume = {11395 LNCS},
year = {2019}
}
@inproceedings{faucris.217468844,
abstract = {Tissue loss in the hippocampi has been heavily correlated with the progression of Alzheimer�s Disease (AD). The shape and structure of the hippocampus are important factors in terms of early AD diagnosis and prognosis by clinicians. However, manual segmentation of such subcortical structures in MR studies is a challenging and subjective task. In this paper, we investigate variants of the well known 3D U-Net, a type of convolution neural network (CNN) for semantic segmentation tasks.We propose an alternative form of the 3D U-Net, which uses dilated convolutions and deep supervision to incorporate multi-scale information into the model. The proposed method is evaluated on the task of hippocampus head and body segmentation in an MRI dataset, provided as part of the MICCAI 2018 segmentation decathlon challenge. The experimental results show that our approach outperforms other conventional methods in terms of different segmentation accuracy metrics.},
author = {Folle, Lukas and Vesal, Sulaiman and Ravikumar, Nishant and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}18},
editor = {Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2019-05-14},
pages = {68-73},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Dilated} deeply supervised networks for hippocampus segmentation in {MRI}},
venue = {Lübeck},
year = {2019}
}
@inproceedings{faucris.121807664,
address = {Berlin, Heidelberg},
author = {Maier, Andreas and Kugler, Patrick and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2015},
edition = {1},
faupublication = {yes},
isbn = {978-3-662-46223-2},
keywords = {Data Completeness; Computed Tomography; Tuy's Condition},
note = {UnivIS-Import:2015-04-17:Pub.2015.tech.IMMD.IMMD5.discre{\_}2},
pages = {47-52},
publisher = {Springer},
title = {{Discrete} {Estimation} of {Data} {Completeness} for {3D} {Scan} {Trajectories} with {Detector} {Offset}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Maier15-DEO.pdf},
venue = {Lübeck},
year = {2015}
}
@article{faucris.120208044,
abstract = {We present a novel approach to the tomographic reconstruction of binary objects from few projection directions within a limited range of angles. A quadratic objective functional over binary variables comprising the squared projection error and a prior penalizing non-homogeneous regions, is supplemented with a concave functional enforcing binary solutions. Application of a primal-dual subgradient algorithm to a suitable decomposition of the objective functional into the difference of two convex functions leads to an algorithm which provably converges with parallel updates to binary solutions. Numerical results demonstrate robustness against local minima and excellent reconstruction performance using five projections within a range of 90°. Our approach is applicable to quite general objective functions over binary variables with constraints and thus applicable to a wide range of problems within and beyond the field of discrete tomography. © 2005 Elsevier B.V. All rights reserved.},
author = {Schüle, Thomas and Schnörr, Christoph and Weber, Stefan and Hornegger, Joachim},
doi = {10.1016/j.dam.2005.02.028},
faupublication = {yes},
journal = {Discrete Applied Mathematics},
pages = {229-243},
peerreviewed = {Yes},
title = {{Discrete} tomography by convex-concave regularization and {D}.{C}. programming},
volume = {151},
year = {2005}
}
@inproceedings{faucris.283366941,
abstract = {Speech intelligibility assessment plays an important role in the therapy of patients suffering from pathological speech disorders. Automatic and objective measures are desirable to assist therapists in their traditionally subjective and labor-intensive assessments. In this work, we investigate a novel approach for obtaining such a measure using the divergence in disentangled latent speech representations of a parallel utterance pair, obtained from a healthy reference and a pathological speaker. Experiments on an English database of Cerebral Palsy patients, using all available utterances per speaker, show high and significant correlation values (R = −0.9) with subjective intelligibility measures, while having only minimal deviation (±0.01) across four different reference speaker pairs. We also demonstrate the robustness of the proposed method (R = −0.89 deviating ±0.02 over 1000 iterations) by considering a significantly smaller amount of utterances per speaker. Our results are among the first to show that disentangled speech representations can be used for automatic pathological speech intelligibility assessment, resulting in a reference speaker pair invariant method, applicable in scenarios with only few utterances available.
1 score of 0.7183. The corresponding network weights and code for implementing the network are made publicly available.},
author = {Wilm, Frauke and Marzahl, Christian and Breininger, Katharina and Aubreville, Marc},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2021-09-27/2021-10-01},
doi = {10.1007/978-3-030-97281-3{\_}1},
editor = {Marc Aubreville, David Zimmerer, Mattias Heinrich},
faupublication = {yes},
isbn = {9783030972806},
keywords = {Domain Shift; Histopathology; MIDOG; Mitotic Count; Object Detection},
note = {CRIS-Team Scopus Importer:2022-03-25},
pages = {5-13},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Domain} {Adversarial} {RetinaNet} as a {Reference} {Algorithm} for the {MItosis} {DOmain} {Generalization} {Challenge}},
venue = {Strasbourg, FRA},
volume = {13166 LNCS},
year = {2022}
}
@inproceedings{faucris.119845264,
abstract = {In X-ray computed tomography (CT), short-scan acquisition that acquires data only over a range of π plus the fan angle, rather than a full range of 2π, is commonly used in circular fan-beam and cone-beam geometry. Such scan aims to reduce acquisition time and radiation dose during data acquisition. However, during a partial circle scan some data are measured once, while other measurements are observed twice. Traditionally, the redundant data are weighted by a smooth function (e.g. the Parker weights) before filtering. In this paper, we present an algorithmic setup that employs dynamic collimation to shield the redundant rays and propose two algorithms to correct the resulting truncation. This approach is able to potentially decrease the dose of 10% for a C-arm CT with fan angle of 10° and of 23% for a diagnostic CT with fan angle of 50°. Evaluation shows that the reconstruction results are of comparable accuracy to the one from standard short-scan FDK, with less dose to the patient. © 2013 IEE},
author = {Xia, Yan and Berger, Martin and Riess, Christian and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the IEEE NSS/MIC 2013},
date = {2013-10-27/2013-11-02},
doi = {10.1109/NSSMIC.2013.6829341},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2013.tech.IMMD.IMMD5.dosere{\_}7},
pages = {1-4},
title = {{Dose} {Reduction} {Achieved} by {Dynamically} {Collimating} the {Redundant} {Rays} in {Fan}-beam and {Cone}-beam {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Xia13-DRA.pdf},
venue = {Seoul},
year = {2013}
}
@inproceedings{faucris.111661484,
author = {Stromer, Daniel and Christlein, Vincent and Huang, Yixing and Zippert, Patrick and Helmecke, Eric and Hausotte, Tino and Maier, Andreas},
booktitle = {Proceedings of 8th Conference on Industrial Computed Tomography (iCT 2018)},
faupublication = {yes},
note = {UnivIS-Import:2018-02-22:Pub.2018.tech.IMMD.IMMD5.dosere{\_}1},
pages = {63-64},
peerreviewed = {Yes},
title = {{Dose} {Reduction} for {Historical} {Books} {Digitization} by 3-{D} {X}-{Ray} {CT}},
venue = {Wels, Austria},
year = {2018}
}
@inproceedings{faucris.217472809,
author = {Preuhs, Alexander and Maier, Andreas and Manhart, Michael and Fotouhi, Javad and Navab, Nassir and Unberath, Mathias},
booktitle = {Medical Image Computing and Computer Assisted Intervention},
faupublication = {yes},
note = {CRIS-Team Scopus Importer:2019-05-14},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Double} {Your} {Views}: {Exploiting} {Symmetry} in {Transmission} {Imaging}},
url = {https://arxiv.org/pdf/1803.10650.pdf},
venue = {Granada, Spain},
year = {2018}
}
@inproceedings{faucris.107929404,
address = {-},
author = {Buckow, Jan-Constantin and Batliner, Anton and Gallwitz, Florian and Huber, Richard and Nöth, Elmar and Warnke, Volker and Niemann, Heinrich},
booktitle = {Proc. Int. Conf. on Spoken Language Processing},
date = {1998-11-30/1998-12-04},
editor = {-},
faupublication = {yes},
pages = {571-574},
publisher = {-},
title = {{Dovetailing} of {Acoustics} and {Prosody} in {Spontaneous} {Speech} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1998/Buckow98-DOA.pdf},
venue = {Sydney},
year = {1998}
}
@inproceedings{faucris.108165244,
author = {Bocklet, Tobias and Riedhammer, Korbinian Thomas and Nöth, Elmar},
booktitle = {Proceedings of the 12th Annual Conference of the International Speech Communication Association},
date = {2011-08-27/2011-08-31},
editor = {ISCA},
faupublication = {yes},
pages = {3213-3216},
title = {{Drink} and {Speak}: {On} the automatic classification of alcohol intoxication by acoustic, prosodic and text-based features},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Bocklet11-DAS.pdf},
venue = {Florence},
year = {2011}
}
@article{faucris.120174384,
author = {Michelson, Georg and Engelhorn, Tobias and Wärntges, Simone and El-Rafei, Ahmed Mohamed Ibrahim and Hornegger, Joachim and Dörfler, Arnd},
doi = {10.1007/s00417-011-1887-2},
faupublication = {yes},
journal = {Graefes Archive For Clinical and Experimental Ophthalmology},
note = {EVALuna2:21070},
pages = {243-253},
peerreviewed = {Yes},
title = {{DTI} parameters of axonal integrity and demyelination of the optic radiation correlate with glaucoma indices},
volume = {251},
year = {2013}
}
@article{faucris.110814704,
abstract = {In image-guided interventional procedures, live 2-D X-ray images can be augmented with preoperative 3-D computed tomography or MRI images to provide planning landmarks and enhanced spatial perception. An accurate alignment between the 3-D and 2-D images is a prerequisite for fusion applications. This paper presents a dynamic rigid 2-D/3-D registration framework, which measures the local 3-D-to-2-D misalignment and efficiently constrains the update of both planar and non-planar 3-D rigid transformations using a novel point-to-plane correspondence model. In the simulation evaluation, the proposed method achieved a mean 3-D accuracy of 0.07 mm for the head phantom and 0.05 mm for the thorax phantom using single-view X-ray images. In the evaluation on dynamic motion compensation, our method significantly increases the accuracy comparing with the baseline method. The proposed method is also evaluated on a publicly-available clinical angiogram data set with 'gold-standard' registrations. The proposed method achieved a mean 3-D accuracy below 0.8 mm and a mean 2-D accuracy below 0.3 mm using single-view X-ray images. It outperformed the state-of-the-art methods in both accuracy and robustness in single-view registration. The proposed method is intuitive, generic, and suitable for both initial and dynamic registration scenarios.},
author = {Wang, Jian and Schaffert, Roman and Borsdorf, Anja and Heigl, Benno and Huang, Xiaolin and Hornegger, Joachim and Maier, Andreas},
doi = {10.1109/TMI.2017.2702100},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
keywords = {dynamic registration; point-to-plane correspondence model; Rigid 2-D/3-D registration},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.dynami},
pages = {1939-1954},
peerreviewed = {Yes},
title = {{Dynamic} 2-{D}/3-{D} {Rigid} {Registration} {Framework} {Using} {Point}-{To}-{Plane} {Correspondence} {Model}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Wang17-D2R.pdf},
volume = {36},
year = {2017}
}
@phdthesis{faucris.203755742,
abstract = {Cardiovascular diseases, i.e. disorders pertaining to the heart and blood vessels, are a major cause of mortality in developed countries. Many of these disorders, such as stenoses and some cases of valvular dysfunction, can be diagnosed and treated minimally invasively in percutaneous, catheter-based interventions. Navigation of the catheters as well as assessment and guidance of these procedures rely on interventional X-ray projection imaging performed using an angiographic C-arm device.
From rotational angiography acquisitions, during which the C-arm rotates on a circular trajectory around the patient, volumetric images can be reconstructed similarly to conventional computed tomography (CT). A three-dimensional representation of the beating heart allowing for a comprehensive functional analysis during the intervention would be useful for clinicians. However, due to the slow rotational speed of the C-arm and the resulting inconsistency of the raw data, imaging dynamic objects is challenging. More precisely, only small, substantially undersampled subsets of the data, which correspond to the same cardiac phases, are approximately consistent. This causes severe undersampling artifacts in the images unless sophisticated reconstruction algorithms are employed. The goal of this thesis is to develop and evaluate such methods in order to improve the quality of dynamic imaging of cardiac chambers in C-arm CT.
One of the two approaches that is investigated in this work aims to mitigate raw data inconsistencies by compensating for the heart motion. It relies on a non-rigid motion estimate obtained from a preliminary reconstruction by means of image registration. We develop a pipeline for artifact reduction and denoising of these preliminary images that increases the robustness of motion estimation and thus removes artificial motion patterns in the final images. We also propose an iterative scheme alternating motion estimation and compensation combined with spatio-temporal smoothing to further improve both image quality and accuracy of motion estimation. Furthermore, we design an open-source tool for comparing motion-compensated reconstruction methods in terms of edge sharpness.
The other approach formulates reconstruction as an optimization problem and introduces prior models of the image appearance in order to find a suitable solution. In particular, sparsity-based regularization as suggested by compressed sensing theory proves beneficial. We investigate and compare temporal regularizers, which yield considerable image quality improvements. In a task-based evaluation concerned with functional analysis of the left ventricle, we study how spatio-temporally regularized reconstruction, carried out with a state-of-the-art proximal algorithm, degrades when the number of projection views is reduced. Finally, we devise a correction scheme that enables dynamic reconstruction of a volume of interest in order to reduce computational effort.
Compared to one another, the approaches exhibit differences with regard to the appearance of the reconstructed images in general and the cardiac motion in particular. A straightforward combination of the methods yields a trade-off between these properties. All in all, both the hybrid and the individual approaches are able to reconstruct dynamic cardiac images with good quality in light of the challenges of rotational angiography.
Background
Sway is a crucial gait characteristic tightly correlated with the risk of falling in patients with Parkinson´s disease (PD). So far, the swaying pattern during locomotion has not been investigated in rodent models using the analysis of dynamic footprint recording obtained from the CatWalk gait recording and analysis system.
New Methods
We present three methods for describing locomotion sway and apply them to footprint recordings taken from C57BL6/N wild-type mice and two different α-synuclein transgenic PD-relevant mouse models (α-synm-ko, α-synm-koxα-synh-tg). Individual locomotion data were subjected to three different signal processing analytical approaches: the first two methods are based on Fast Fourier Transform (FFT), while the third method uses Low Pass Filters (LPF). These methods use the information associated with the locomotion sway and generate sway-related parameters.
Results
The three proposed methods were successfully applied to the footprint recordings taken from all paws as well as from front/hind-paws separately. Nine resulting sway-related parameters were generated and successfully applied to differentiate between the mouse models under study. Namely, α-synucleinopathic mice revealed higher sway and sway itself was significantly higher in the α-synm-koxα-synh-tg mice compared to their wild-type littermates in eight of the nine sway-related parameters.
Comparison with Existing Method
Previous locomotion sway index computation is based on the estimated center of mass position of mice.
Conclusions
The methods presented in this study provide a sway-related gait characterization. Their application is straightforward and may lead to the identification of gait pattern derived biomarkers in rodent models of P},
author = {Timotius, Ivanna and Canneva, Fabio and Minakaki, Georgia and Pasluosta, Cristian Federico and Moceri, Sandra and Casadei, Nicolas and Riess, Olaf and Winkler, Jürgen and Klucken, Jochen and von Hörsten, Stephan and Eskofier, Björn},
doi = {10.1016/j.jneumeth.2017.12.004},
faupublication = {yes},
journal = {Journal of Neuroscience Methods},
keywords = {Locomotion; sway; gait analysis; CatWalk system; Parkinson's disease; alpha-synuclein transgenic},
note = {EVALuna2:32788},
pages = {1-11},
peerreviewed = {Yes},
title = {{Dynamic} footprint based locomotion sway assessment in α-synucleinopathic mice using {Fast} {Fourier} {Transform} and {Low} {Pass} {Filter}},
url = {http://www.sciencedirect.com/science/article/pii/S0165027017304211},
volume = {296},
year = {2018}
}
@article{faucris.119909504,
abstract = {Characterizing gait is important in the study of movement disorders, also in clinical mouse models. Gait data are therefore necessary for the development of gait analysis methods and the study of diseases. This article presents gait data of two α-synucleinopathic transgenic mouse models and their non-transgenic littermate, backcrossed into the C57BL/6N genetic background. The animal gait was recorded using CatWalk system, which provides the information for each run about the paw positions, paw print sizes, and paw intensities as a function of time or video frame. A total of 90 run data files are provided in this article.},
author = {Timotius, Ivanna and Canneva, Fabio and Minakaki, Georgia and Pasluosta, Cristian Federico and Moceri, Sandra and Casadei, Nicolas and Riess, Olaf and Winkler, Jürgen and Klucken, Jochen and von Hörsten, Stephan and Eskofier, Björn},
doi = {10.1016/j.dib.2017.12.067},
faupublication = {yes},
journal = {Data in Brief},
keywords = {Data; gait analysis; CatWalk system; Parkinson's disease; alpha-synuclein transgenic.},
pages = {189-193},
peerreviewed = {unknown},
title = {{Dynamic} footprints of α-synucleinopathic mice recorded by {CatWalk} gait analysis},
url = {https://www.sciencedirect.com/science/article/pii/S2352340918300015},
volume = {17},
year = {2018}
}
@phdthesis{faucris.116765704,
abstract = {Acute ischaemic stroke is a major cause for death and disabilities with increasing prevalence in aging societies. Novel interventional stroke treatment procedures have the potential to improve the clinical outcome of certain stroke-affected patients. Certainly, prompt diagnosis and treatment are required. Brain perfusion imaging with computed tomography (CT) or magnetic resonance imaging (MRI) is a routine method for stroke diagnosis. However, in the interventional room usually only CT imaging with flat detector C-arm systems is available, which do not support dynamic perfusion imaging yet. Enabling flat detector CT perfusion (FD-CTP) in clinical practice could support optimized stroke management. By stroke diagnosis in the interventional room precious time until the start of treatment could be saved.
Recently, first promising clinical results for FD-CTP imaging under laboratory conditions have been presented. Based on this work, this dissertation introduces and evaluates novel technical contributions for noise reduction, artifact reduction and dynamic reconstruction in FD-CTP. Furthermore, the feasibility of FD-CTP imaging in clinical practice is demonstrated for the first time using data acquired during interventional stroke treatments.
CT perfusion imaging requires measurement of dynamic contrast agent attenuation over time. The contrast agent signal in the brain tissue is very low and noise is a major problem. Thus a novel computationally fast noise reduction technique for perfusion data is introduced.
Currently available C-arm systems have a comparably low rotation speed, which makes it challenging to reconstruct the dynamic change of contrast agent concentration over time. Therefore, a dynamic iterative reconstruction algorithm is proposed to utilize the high temporal resolution in the projection data for improved reconstruction of the contrast agent dynamics.
Novel robotic C-arm systems (Artis zeego, Siemens Healthcare, Germany) provide a high speed rotation protocol (HSP) to improve the temporal acquisition of the contrast agent dynamics. However, the HSP suffers from angular under-sampling, which can lead to severe streak artifacts in the reconstructed perfusion maps. Thus a novel, computationally fast noise and streak artifact reduction approach for FD-CTP data is proposed. The feasibility of FD-CTP using the HSP is demonstrated with clinical data acquired during interventional treatment of two stroke cases.
Furthermore, the design of a digital brain perfusion phantom for the thorough numerical evaluation of the proposed techniques is discussed.
The quality of the perfusion maps acquired and reconstructed using the introduced novel approaches suggests that FD-CTP could be clinically available in the near future.
This paper investigates the use of speech-to-text methods for assigning an emotion class to a given speech utterance. Previous work shows that an emotion extracted from text can convey complementary evidence to the information extracted by classifiers based on spectral, or other non-linguistic features. As speech-to-text usually presents significantly more computational effort, in this study we investigate the degree of speech-to-text accuracy needed for reliable detection of emotions from an automatically generated transcription of an utterance. We evaluate the use of hypotheses in both training and testing, and compare several classification approaches on the same task. Our results show that emotion recognition performance stays roughly constant as long as word accuracy doesn’t fall below a reasonable value, making the use of speech-to-text viable for training of emotion classifiers based on linguistics.
},
author = {Metze, Florian and Batliner, Anton and Eyben, Florian and Polzehl, Tim and Schuller, Björn and Steidl, Stefan},
booktitle = {Proceedings of Interspeech},
date = {2010-09-26/2010-09-30},
editor = {ISCA},
faupublication = {yes},
keywords = {speech-to-text; emotion detection; meta-data extraction; rich transcription; children’s speech},
pages = {478-481},
peerreviewed = {Yes},
title = {{Emotion} {Recognition} {Using} {Imperfect} {Speech} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Metze10-ERU.pdf},
venue = {Makuhari},
year = {2010}
}
@article{faucris.267495345,
abstract = {Empirical Mode Decomposition (EMD) was designed to analyze nonlinear and non-stationary signals. EMD voice analysis had been applied to Parkinson's sustained vowels, but very limited studies have been done on highly dynamic Diadochokinesia (DDK) utterances. This paper applies the EMD's dyadic filterbank characteristics to extract DDK features and an in-depth study on the efficacy of two segmentation strategies. The EMD analysis on DDK looks at the spectrum characteristics of Intrinsic Mode Functions (IMF) and the handling of mode mixing conditions. DDK recordings of Healthy Control (HC) subjects and patients with Parkinson's disease (PD) were segmented using various fixed frame sizes compared to dynamic segmentation based on/pa-ta-ka/ triad length, and also the signal envelope as a whole. An overlapping windowing of 2/3 was used in the fixed frame size segmentation to augment and to capture the redundant and transition information. No overlapping was used in the/pa-ta-ka/ triad segmentation. For the fixed frame size segmentation, we found that there is a region of consistency. Within this region, the IMF center frequencies and bandwidths maintained the same but varied outside the region. The segmentation comparisons used a basic set of EMD features with and without DeltaEMD features that capture segment-to-segment deviations. Using the basic EMD dyadic features, fixed frame size segmentation out-performed/pa-ta-ka/ triad segmentation. When DeltaEMD features were added to provide segment deviation information,/pa-ta-ka/ triad out-performed fixed frame segmentation. Additional segment-magnitude amplification factor and segment length were found to improve the performance of the/pa-ta-ka/ triad segmentation. With the added features,/pa-ta-ka/ triad out-performed the others and had an improved accuracy of 78%. Additional features have also increased the envelope discrimination to 76%. The results also indicated the potentials of using voice envelopes for PD analysis.},
author = {Rueda, Alice and Vasquez Correa, Juan and Orozco Arroyave, Juan Rafael and Nöth, Elmar and Krishnan, Sridhar},
doi = {10.1016/j.csl.2021.101322},
faupublication = {yes},
journal = {Computer Speech and Language},
note = {CRIS-Team WoS Importer:2021-12-24},
peerreviewed = {Yes},
title = {{Empirical} {Mode} {Decomposition} articulation feature extraction on {Parkinson}'s {Diadochokinesia}},
volume = {72},
year = {2022}
}
@inproceedings{faucris.203853370,
abstract = {Scatter affects every computed tomography (CT) image. Calibration-free software scatter reduction methods have not been used extensively in practice. Recently, consistency conditions have been applied successfully to other artifact reduction problems in CT imaging. We propose a scatter reduction method, that uses an epipolar consistency condition (ECC) to estimate parameters of an additive scatter model. We evaluate our approach by comparing it with an image-based empirical scatter correction method (ESC) that uses the same scatter model. We show that it performs equally well onsimulated data. Further, ECC outperforms ESC regarding the computational load for the determination of the parameters, because ECC is formulated in projection domain such that no image reconstruction is necessary. While some restrictions might apply for the stability of ECC on measured data, no prior information needs to be formulated regarding the reconstructed image, like it is required with ES},
author = {Hoffmann, Mathis and Würfl, Tobias and Maass, Nicole and Dennerlein, Frank and Aichert, André and Maier, Andreas},
booktitle = {Proceedings of the Fifth International Conference on Image Formation in X-Ray Computed Tomography (CT-Meeting)},
faupublication = {yes},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.empiri},
pages = {193-197},
peerreviewed = {unknown},
title = {{Empirical} {Scatter} {Correction} using the {Epipolar} {Consistency} {Condition}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Hoffmann18-ESC.pdf},
venue = {Salt Lake City, USA},
year = {2018}
}
@inproceedings{faucris.120321344,
address = {-},
author = {Fischer, Julia and Haas, Jürgen and Nöth, Elmar and Niemann, Heinrich and Deinzer, Frank},
booktitle = {Proc. Int. Conf. on Spoken Language Processing},
date = {1998-11-30/1998-12-04},
editor = {ICSLP'98},
faupublication = {yes},
pages = {2231-2235},
publisher = {-},
title = {{Empowering} {Knowledge} {Based} {Speech} {Understanding} through {Statistics}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1998/Fischer98-EKB.pdf},
venue = {Sydney},
year = {1998}
}
@inproceedings{faucris.261184746,
author = {Vasquez Correa, Juan and Arias Vergara, Tomás and Klumpp, Philipp and Pérez Toro, Paula Andrea and Orozco-Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP39728.2021.9414729},
faupublication = {yes},
keywords = {Smartphones; Speech analysis; Gait analysis; Parkinson's disease; Deep learning},
pages = {7298-7302},
peerreviewed = {unknown},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
title = {{End}-2-{End} {Modeling} of {Speech} and {Gait} from {Patients} with {Parkinson}’s {Disease}: {Comparison} {Between} {High} {Quality} {Vs}. {Smartphone} {Data}},
url = {https://ieeexplore.ieee.org/abstract/document/9414729},
year = {2021}
}
@article{faucris.121428824,
author = {Höller, Kurt Emmerich and Schneider, Armin and Jahn, Jasper and Gutierrez, Javier and Wittenberg, Thomas and Feußner, Hubertus and Hornegger, Joachim},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
pages = {S247-S248},
peerreviewed = {unknown},
title = {{Endoscopic} image rectification using gravity},
url = {http://www.zimt.uni-erlangen.de/publikationen/hoeller10-EIR.pdf},
volume = {5 Suppl. 1},
year = {2010}
}
@book{faucris.121195624,
abstract = {An open problem in endoscopic surgery (especially with flexible endoscopes) is the absence of a stable horizon in endoscopic images. With our "Endorientation" approach image rotation correction, even in non-rigid endoscopic surgery (particularly NOTES), can be realized with a tiny MEMS tri-axial inertial sensor placed on the tip of an endoscope. It measures the impact of gravity on each of the three orthogonal accelerometer axes. After an initial calibration and filtering of these three values the rotation angle is estimated directly. Achievable repetition rate is above the usual endoscopic video frame rate of 30Hz; accuracy is about one degree. The image rotation is performed in real-time by digitally rotating the analog endoscopic video signal. Improvements and benefits have been evaluated in animal studies: Coordination of different instruments and estimation of tissue behavior regarding gravity related deformation and movement was rated to be much more intuitive with a stable horizon on endoscopic images. © 2009 Springer-Verlag.},
address = {Heidelberg},
author = {Höller, Kurt Emmerich and Penne, Jochen and Schneider, Armin and Jahn, Jasper and Guttierrez, Javier and Wittenberg, Thomas and Feußner, Hubertus and Hornegger, Joachim},
doi = {10.1007/978-3-642-04268-3{\_}57},
faupublication = {yes},
isbn = {978-3-642-04267-6},
keywords = {EndoSens; Endorientation; Endoscopic Image Rectification; MEMS; NOTES; Natural Orifice Transluminal Endoscopic Surgery},
note = {UnivIS-Import:2015-04-16:Pub.2009.tech.IMMD.IMMD5.endosc{\_}6},
pages = {459-466},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Endoscopic} orientation correction},
volume = {null},
year = {2009}
}
@book{faucris.214098751,
address = {Cham},
author = {Haase, Sven and Maier, Andreas},
doi = {10.1007/978-3-319-96520-8{\_}4},
faupublication = {yes},
isbn = {978-3-319-96519-2},
note = {UnivIS-Import:2019-03-21:Pub.2018.tech.IMMD.IMMD5.endosc},
pages = {57-68},
peerreviewed = {unknown},
publisher = {Springer},
series = {Lecture Notes in Computer Science(LNCS)},
title = {{Endoscopy}},
volume = {11111},
year = {2018}
}
@inproceedings{faucris.283167156,
abstract = {Deep Learning (DL) has enabled the development of accurate computational models to evaluate and monitor the neurological state of different disorders including Parkinson’s Disease (PD). Although researchers have used different DL architectures including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) units, fully connected networks, combinations of them, and others, but few works have correctly analyzed and optimized the input size of the network and how the network processes the information. This study proposes the classification of patients suffering from PD vs. healthy subjects using a 1D CNN followed by an LSTM. We show how the network behaves when its input and the kernel size in different layers are modified. In addition, we evaluate how the network discriminates between PD patients and healthy controls based on several speech tasks. The fusion of tasks yielded the best results in the classification experiments and showed promising results when classifying patients in different stages of the disease, which suggests the introduced approach is suitable to monitor the disease progression.},
author = {Rios-Urrego, Cristian David and Moreno-Acevedo, Santiago Andres and Nöth, Elmar and Orozco Arroyave, Juan Rafael},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2022-09-06/2022-09-09},
doi = {10.1007/978-3-031-16270-1{\_}27},
editor = {Petr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala},
faupublication = {yes},
isbn = {9783031162695},
keywords = {Convolutional Neural Networks; Long Short-Term Memory; Parkinson’s Disease; Speech Processing},
note = {CRIS-Team Scopus Importer:2022-10-14},
pages = {326-338},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{End}-to-{End} {Parkinson}’s {Disease} {Detection} {Using} a {Deep} {Convolutional} {Recurrent} {Network}},
venue = {Brno},
volume = {13502 LNAI},
year = {2022}
}
@article{faucris.123790084,
abstract = {CONCLUSIONS: En face SS OCT provides an in vivo tool to visualize the pathologic features and the choroidal vasculature in PCV. (C) 2015 by Elsevier Inc. All rights reserved.},
author = {Alasil, Tarek and Ferrara, Daniela and Adhi, Mehreen and Brewer, Erika and Kraus, Martin and Baumal, Caroline R. and Hornegger, Joachim and Fujimoto, James G. and Witkin, Andre J. and Reichel, Elis and Duker, Jay S. and Waheed, Nadia K.},
doi = {10.1016/j.ajo.2014.12.012},
faupublication = {yes},
journal = {American Journal of Ophthalmology},
pages = {634-643},
peerreviewed = {Yes},
title = {{En} {Face} {Imaging} of the {Choroid} in {Polypoidal} {Choroidal} {Vasculopathy} {Using} {Swept}-{Source} {Optical} {Coherence} {Tomography}},
volume = {159},
year = {2015}
}
@article{faucris.217019142,
abstract = {The annually produced quantity of solar modules has steadily increased over the past decades. Rising production speeds and the associated high throughput of wafers, cells, and modules will make an automatized quality inspection mandatory. In the case of visual optical inspection, automatized quality control by using machine vision is already possible. To localize cracks in solar cells, luminescence imaging is used, where several approaches for an automatized inspection exist, but a standard solution for an automatized inspection algorithm is not yet available. This is, in particular, true for multicrystalline solar cells, where the grainy structures in the luminescence images are hard to distinguish from small cracks. Another obstacle in automatic crack analysis is that reference segmentation algorithms are generally not publicly available. Accordingly, a new algorithm can hardly be compared by ranking it to an existing standard. In this paper, we adapted the vesselness algorithm for automatic processing of electroluminescence images of multicrystalline silicon solar cells. Segmentation of cracks in multicrystalline solar cells with the proposed enhanced crack segmentation algorithm shows very promising results on the used database compared with three different commonly used approaches. Furthermore, the segmentation code is made publicly available, and we propose that this algorithm may serve as a reference algorithm, sparking further progress in automatized crack segmentation for multicrystalline silicon solar cells.},
author = {Stromer, Daniel and Vetter, Andreas and Özkan, Hasan Can and Probst, Christian and Maier, Andreas},
doi = {10.1109/JPHOTOV.2019.2895808},
faupublication = {yes},
journal = {IEEE Journal of Photovoltaics},
keywords = {Crack detection; crack segmentation; electroluminescence (EL) imaging; multicrystalline solar cell imaging; photovoltaic (PV)},
note = {CRIS-Team Scopus Importer:2019-05-07},
pages = {752-758},
peerreviewed = {Yes},
title = {{Enhanced} {Crack} {Segmentation} ({eCS}): {A} {Reference} {Algorithm} for {Segmenting} {Cracks} in {Multicrystalline} {Silicon} {Solar} {Cells}},
volume = {9},
year = {2019}
}
@misc{faucris.112829904,
author = {Wilke, Peter and Schnaittinger, T. and Werner, F. and Lampka, K. and Grosser, N.},
faupublication = {yes},
keywords = {Entwicklung; Software; Werkzeug; Risiko-Management},
note = {UnivIS-Import:2016-06-30:Pub.2001.tech.IMMD.IMMD2.{\_}entwi},
peerreviewed = {automatic},
title = {{Entwicklung} eines {Software}-{Werkzeuges} für {Risiko}-{Management}},
year = {2001}
}
@inproceedings{faucris.107946124,
address = {Berlin Heidelberg},
author = {Maier, Andreas and Haderlein, Tino and Nöth, Elmar},
booktitle = {Text, Speech and Dialogue},
date = {2006-09-11/2006-09-15},
editor = {Sojka Petr, Kopecek Ivan, Pala Karel},
faupublication = {yes},
pages = {431-437},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Environmental} {Adaptation} with a {Small} {Data} {Set} of the {Target} {Domain}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Maier06-EAW.pdf},
venue = {Brno},
year = {2006}
}
@inproceedings{faucris.212329053,
author = {Bier, Bastian and Aichert, André and Felsner, Lina and Unberath, Mathias and Levenstone, Marc and Gold, Garry and Fahrig, Rebecca and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2017 Algorithmen Systeme Anwendungen (Bildverarbeitung für die Medizin 2017)},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0{\_}47},
faupublication = {yes},
isbn = {9783662543443},
pages = {209-214},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Epipolar} consistency conditions for motion correction in weight-bearing imaging},
venue = {Heidelberg},
year = {2017}
}
@inproceedings{faucris.111206084,
author = {Würfl, Tobias and Maass, Nicole and Dennerlein, Frank and Huang, Xiaolin and Maier, Andreas},
booktitle = {Proceedings of the 14th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.epipol{\_}8},
pages = {181-185},
peerreviewed = {unknown},
title = {{Epipolar} {Consistency} {Guided} {Beam} {Hardening} {Reduction} - {ECC²}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Wurfl17-ECCsquaredFully3D.pdf},
venue = {Xi'an, Shaanxi, China},
year = {2017}
}
@inproceedings{faucris.111142064,
address = {Swansea, UK},
author = {Aichert, André and Wang, Jian and Schaffert, Roman and Dörfler, Arnd and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the British Machine Vision Conference 2015},
faupublication = {yes},
isbn = {1-901725-53-7},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.epipol{\_}3},
pages = {86},
peerreviewed = {unknown},
publisher = {BMVA Press},
title = {{Epipolar} {Consistency} in {Fluoroscopy} for {Image}-{Based} {Tracking}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Aichert15-ECI.pdf},
venue = {Swansea, UK},
year = {2015}
}
@phdthesis{faucris.296580751,
abstract = {Two X-ray projection images of a rigid object may have different points of view,
yet redundant information can be identified in such images. Not unlike a checksum,
these occur naturally in the data and are known as consistency conditions. Real
acquisitions, however, result from a measurement process which is affected by inaccurate
geometric calibration of the scanner, physical effects such as scatter and
beam-hardening or in some applications patient motion. These effects can be observed
as differences between theoretically redundant information in the data and, to
some extent, can be corrected.
Consistency conditions have been known for decades, yet only few practical applications
have been demonstrated. State-of-the-art often assumes 2D parallel or
fan-beam geometries in a perfect circle around the object. Extension of these findings
to flat-panel detector geometry are not straight-forward. Meanwhile, however,
practical applicability in flat-detector computed tomography has been demonstrated
for a set of pairwise conditions known as epipolar consistency (EC). Their advantage
is that they can be applied, in principle, to any two 2D projection images.
This thesis first gives a brief introduction to data consistency conditions in two
and three dimensions, providing a context for the main part of this work. The
reader is then introduced to projective geometry of real two- and three-space and the
geometry of X-ray imaging. This provides the mathematical tools for a derivation of
the novel epipolar consistency conditions and demonstrates the connection to wellunderstood
computer vision tasks. Three flavors of a metric to measure epipolar
inconsistency in two images are suggested and a framework for motion compensation
is introduced. Finally, the metric is used for motion correction in three applications
of FDCT imaging. First, an unknown object under fluoroscopy is tracked relative to
a small set of reference views. Second, respiratory and cardiac motion in rotational
angiography is estimated. And third, the alignment of two computed tomography
acquisitions is estimated from their raw data.
die Erkennung von hochohmigen Erdschlüssen eine der schwierigsten Aufgaben der Schutztechnik.
Durch die zahlreichen Einflussparameter wie beispielsweise Fehlerursache, Bodenbeschaffenheit und
Witterung auf Fehler- und Erdimpedanz können konventionelle Verfahren Erdschlüsse nicht in jedem
Fall zuverlässig erkennen.
In diesem Poster soll deshalb ein Konzept vorgestellt werden, das durch Verwendung von Künstlichen
Neuronalen Netzen eine Ergänzung zu den etablierten Verfahren bilden soll. Durch ein Training sollen
die Neuronalen Netze erlernen die komplexen Muster der Erdschlüsse zu erkennen und von anderen
Schalthandlungen oder Fehlern abgrenzen können. Im Gegensatz zu konventionellen
Schutzkonzepten, deren Erkennung meist von den Werten einzelner Parametern abhängt, sollen die
Neuronalen Netze ein generisches Verständnis für die Muster entwickeln und so robuster und
vielseitiger einsetzbar sein.
Für die Generierung der Trainingsdaten ist ein möglichst akkurates Modell des entsprechenden
Einsatzgebietes nötig. Mit diesem können automatisiert Simulationen durchgeführt, und Messdaten
exportiert werden. Dabei werden verschiedene Fehlerorte und -zeitpunkte mit verschiedenen
Parametern simuliert, um einen möglichst diversen Datensatz für ein robustes Training zu generieren.
Die Messdaten aus den Simulationen werden anschließend für das Training der Neuronalen Netze
verwendet. Um die Fehlererkennungsfähigkeit der Netze zu verifizieren, können diese anschließend
mit Messdaten aus realen elektrischen Netzen validiert werde},
author = {Kordowich, Georg and Lorz, Tobias and Jaworski, Michael and Klumpp, Philipp and Pérez Toro, Paula Andrea and Gaube, Sven and Kereit, Matthias and Böhme, Klaus and Nöth, Elmar and Jäger, Johann},
booktitle = {12. VDE ETG-/FNN-Tutorial Schutz- und Leittechnik},
date = {2022-06-21/2022-06-22},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Erdschlusserkennung} basierend auf {Künstlichen} {Neuronalen} {Netzen}},
venue = {Berlin},
year = {2022}
}
@inproceedings{faucris.123005784,
author = {Eischer, Michael and Blank, Peter and Danzer, Alexander and Hauck, Adrian and Hoffmann, Markus and Reck, Benjamin and Eskofier, Björn},
booktitle = {Robot Soccer World Cup XIX Proceedings},
faupublication = {yes},
note = {UnivIS-Import:2016-06-01:Pub.2015.tech.IMMD.IMMD5.erforc},
pages = {-},
peerreviewed = {unknown},
title = {{ER}-{Force} {Extended} {Team} {Description} {Paper} for {Robocup} 2015},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Eischer15-EET.pdf},
venue = {Hefei, China},
year = {2015}
}
@inproceedings{faucris.117659784,
address = {Graz, Austria},
author = {Blank, Peter and Bleier, Michael and Drexler, Sebastian and Kallwies, Jan and Kugler, Patrick and Lahmann, Dominik and Nordhus, Philipp and Riess, Christian and Swadzba, Thaddäus and Tully, Jan},
booktitle = {RoboCup 2009: Robot Soccer World Cup XIII Proceedings},
date = {2009-06-29/2009-07-05},
editor = {RoboCup Foundation},
faupublication = {yes},
pages = {N/A},
title = {{ER}-{Force} {Team} {Description} {Paper} for {RoboCup} 2009},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Blank09-ETD.pdf},
venue = {Graz, Austria},
year = {2009}
}
@inproceedings{faucris.110452364,
address = {Singapore, Singapore},
author = {Blank, Peter and Bleier, Michael and Kallwies, Jan and Kugler, Patrick and Lahmann, Dominik and Nordhus, Philipp and Riess, Christian},
booktitle = {RoboCup 2010: Robot Soccer World Cup XIV Proceedings},
date = {2010-06-19/2010-06-25},
faupublication = {yes},
pages = {N/A},
title = {{ER}-{Force} {Team} {Description} {Paper} for {RoboCup} 2010},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Blank-ETD.pdf},
venue = {Singapore, Singapore},
year = {2010}
}
@inproceedings{faucris.118453104,
address = {Istanbul, Turkey},
author = {Bauer, Florian and Blank, Peter and Bleier, Michael and Dohrn, Hannes and Eischer, Michael and Friedrich, Stefan and Hauck, Adrian and Kallwies, Jan and Kugler, Patrick and Lahmann, Dominik and Nordhus, Philipp and Reck, Benjamin and Riess, Christian},
booktitle = {RoboCup 2011: Robot Soccer World Cup XV Proceedings},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2011.tech.IMMD.IMMD5.erforc},
pages = {N/A},
publisher = {-},
title = {{ER}-{Force} {Team} {Description} {Paper} for {RoboCup} 2011},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Bauer11-ETD.pdf},
venue = {Istanbul, Turkey},
year = {2011}
}
@inproceedings{faucris.123543464,
abstract = {In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists. The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.},
author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian Thomas and Eysholdt, Ulrich and Nöth, Elmar},
faupublication = {yes},
keywords = {Cleft lip and palate;pathologic speech;Children's speech},
month = {Jan},
pages = {2671-2674},
peerreviewed = {unknown},
title = {{Erlangen}-{CLP}: {A} {Large} {Annotated} {Corpus} of {Speech} from {Children} with {Cleft} {Lip} and {Palate}},
year = {2014}
}
@inproceedings{faucris.110634744,
address = {Berlin},
author = {Taubmann, Oliver and Lauritsch, Günter and Maier, Andreas and Fahrig, Rebecca and Hornegger, Joachim},
booktitle = {Medical Image Computing and Computer-Assisted Intervention MICCAI 2015},
doi = {10.1007/978-3-319-24571-3{\_}69},
faupublication = {yes},
isbn = {978-3-319-24571-3},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.estima{\_}9},
pages = {579-586},
peerreviewed = {Yes},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {{Estimate}, {Compensate}, {Iterate}: {Joint} {Motion} {Estimation} and {Compensation} in 4-{D} {Cardiac} {C}-arm {Computed} {Tomography}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Taubmann15-ECI.pdf},
venue = {Munich, Germany},
year = {2015}
}
@inproceedings{faucris.120196384,
abstract = {Being able to automatically determine which portion of the human body is shown by a CT volume image offers various possibilities like automatic labeling of images or initializing subsequent image analysis algorithms. This paper presents a method that takes a CT volume as input and outputs the vertical body coordinates of its top and bottom slice in a normalized coordinate system whose origin and unit length are determined by anatomical landmarks. Each slice of a volume is described by a histogram of visual words: Feature vectors consisting of an intensity histogram and a SURF descriptor are first computed on a regular grid and then classified into the closest visual words to form a histogram. The vocabulary of visual words is a quantization of the feature space by offline clustering a large number of feature vectors from prototype volumes into visual words (or cluster centers) via the K-Means algorithm. For a set of prototype volumes whose body coordinates are known the slice descriptions are computed in advance. The body coordinates of a test volume are computed by a 1D rigid registration of the test volume with the prototype volumes in axial direction. The similarity of two slices is measured by comparing their histograms of visual words. Cross validation on a dataset of 44 volumes proved the robustness of the results. Even for test volumes of ca. 20cm height, the average error was 15.8mm. © 2009 Copyright SPIE - The International Society for Optical Engineering.},
author = {Feulner, Johannes and Zhou, S. Kevin and Seifert, Sascha and Hornegger, Joachim and Comaniciu, Dorin and Cavallaro, Alexander Josef},
booktitle = {Medical Imaging 2009 - Image Processing},
doi = {10.1117/12.810240},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Estimating} the body portion of {CT} volumes by matching histograms of visual words},
venue = {Lake Buena Vista, FL},
volume = {7259},
year = {2009}
}
@inproceedings{faucris.229710892,
abstract = {We present a general method to estimate the fundamental matrix from a pair of images under perspective projection without the need for image point correspondences. Our method is particularly well-suited for transmission imaging, where state-of-the-art feature detection and matching approaches generally do not perform well. Estimation of the fundamental matrix plays a central role in auto-calibration methods for reflection imaging. Such methods are currently not applicable to transmission imaging. Furthermore, our method extends an existing technique proposed for reflection imaging which potentially avoids the outlier-prone feature matching step from an orthographic projection model to a perspective model.
Our method exploits the idea that under a linear attenuation model line integrals along corresponding epipolar lines are equal if we compute their derivatives in orthogonal direction to their common epipolar plane.
We use the fundamental matrix to parametrize this equality.
Our method estimates the matrix by formulating a non-convex optimization problem, minimizing an error in our measurement of this equality.
We believe this technique will enable the application of the large body of work on image-based camera pose estimation to transmission imaging leading to more accurate and more general motion compensation and auto-calibration algorithms, particularly in medical X-ray and Computed Tomography imaging},
author = {Würfl, Tobias and Aichert, André and Maass, Nicole and Dennerlein, Frank and Maier, Andreas},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
date = {2019-10-27/2019-11-02},
doi = {10.1109/iccv.2019.00116},
faupublication = {yes},
keywords = {Structure from Motion, CT reconstruction},
pages = {1072 - 1081},
peerreviewed = {Yes},
title = {{Estimating} the {Fundamental} {Matrix} {Without} {Point} {Correspondences} {WithApplication} to {Transmission} {Imaging}},
url = {http://openaccess.thecvf.com/content{\_}ICCV{\_}2019/papers/Wurfl{\_}Estimating{\_}the{\_}Fundamental{\_}Matrix{\_}Without{\_}Point{\_}Correspondences{\_}With{\_}Application{\_}to{\_}ICCV{\_}2019{\_}paper.pdf},
venue = {Seoul, Südkorea},
year = {2019}
}
@inproceedings{faucris.121216964,
abstract = {Iterative reconstruction methods with 3D resolution recovery, and attenuation and scatter compensations are now common in clinical practice. Still, the reconstruction of ECG gated cardiac SPECT data is often done with fdtered backprojection (FBP) to save reconstruction time. The reconstruction times of the 2007 release of Flash3D (Siemens' OSEM reconstruction with 3D distance dependent resolution recovery and optional scatter and attenuation corrections) have been significantly improved and it is now possible to process an entire clinical gated cardiac data set in clinically acceptable times. It has been shown that Flash3D enables the use of rapid acquisition protocols, yet maintains clinical diagnostic ability. In this work we evaluated the estimation accuracy of the cardiac ejection fraction of gated myocardial SPECT/CT perfusion images, acquired with currently used clinical protocols, as well as rapid acquisition protocols. For this, we acquired ECG gated image data of a dynamic cardiac torso phantom manufactured by Data Spectrum. Images were reconstructed using FBP and the new Flash3D with and without scatter and attenuation corrections. We analyzed the reconstructed volumes of the dynamic phantom using our own quantitative analysis tool as well as 4D-MSPECT and compared the image-based estimated ejection fraction (EF) to the true ejection fraction delivered by the dynamic phantom. Results show high correlation (r >0.97) between conventional clinical protocols with FBP reconstruction and half time protocols using Flash3D except for 16 gates an 128×128 matrix (r=0.95). Best ejection fraction accuracy was found for 16 gates and 64x64 matrix with a mean deviation of 0.5±1.2% (full time FBP) 0.9±1.6% (half time Flash3D) from the true value. ©2007 IEEE.},
author = {Zeintl, Johannes and Hornegger, Joachim and Kuwert, Torsten and et al.},
author_hint = {Zeintl J., Ding X., Vija A., Hawman E., Hornegger J., Kuwert T.},
booktitle = {2007 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS-MIC},
doi = {10.1109/NSSMIC.2007.4437109},
faupublication = {yes},
pages = {4491-4496},
peerreviewed = {unknown},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Estimation} accuracy of ejection fraction in gated cardiac {SPECT}/{CT} imaging using iterative reconstruction with {3D} resolution recovery in rapid acquisition protocols},
venue = {Honolulu, HI},
volume = {6},
year = {2007}
}
@inproceedings{faucris.279698741,
author = {Luckner, Christoph and Maier, Andreas and Dennerlein, Frank},
booktitle = {Informatik aktuell},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}23},
editor = {Hans-Peter Meinzer, Heinz Handels, Thomas Martin Deserno, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783642541100},
note = {CRIS-Team Scopus Importer:2022-08-05},
pages = {102-107},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Estimation} of convolution kernels for {X}-ray scatter signal correction {Schätzung} von {Faltungskernen} zur {Röntgen}-{Streusignalkorrektur}},
venue = {Aachen, DEU},
year = {2014}
}
@inproceedings{faucris.111205864,
author = {Breininger, Katharina and Pfister, Marcus and Koutouzi, Giasemi and Kowarschik, Markus and Maier, Andreas},
booktitle = {3rd Conference on Image-Guided Interventions & Fokus Neuroradiologie},
date = {2017-11-06/2017-11-07},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.estima},
pages = {23-24},
peerreviewed = {unknown},
title = {{Estimation} of femoral artery access location for anatomic deformation correction},
venue = {Magdeburg},
year = {2017}
}
@inproceedings{faucris.118308124,
author = {Pohlmann, Marcel and Berger, Martin and Maier, Andreas and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Proceedings of the third international conference on image formation in x-ray computed tomography},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.estima},
pages = {203-207},
title = {{Estimation} of missing fan-beam projections using frequency consistency conditions},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Pohlmann14-EOM.pdf},
venue = {Salt Lake City, UT, USA},
year = {2014}
}
@inproceedings{faucris.108193184,
author = {Jakob, Carolin and Kugler, Patrick and Hebenstreit, Felix and Reinfelder, Samuel and Jensen, Ulf and Schuldhaus, Dominik and Lochmann, Matthias and Eskofier, Björn},
booktitle = {BodyNets 2013},
date = {2013-09-30/2013-10-02},
editor = {IEEE},
faupublication = {yes},
pages = {n/a},
title = {{Estimation} of the {Knee} {Flexion}-{Extension} {Angle} {During} {Dynamic} {Sport} {Motions} {Using} {Body}-worn {Inertial} {Sensors}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Jakob13-EOT.pdf},
venue = {Boston, MA, USA},
year = {2013}
}
@inproceedings{faucris.203719819,
author = {Luckner, Christoph and Mertelmeier, Thomas and Maier, Andreas and Ritschl, Ludwig},
booktitle = {Proceedings of the Fifth International Conference on Image Formation in X-Ray Computed Tomography},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.estima},
pages = {78-81},
peerreviewed = {unknown},
title = {{Estimation} of the {Source}-{Detector} {Alignment} of {Cone}-{Beam} {X}-ray {Systems} using {Collimator} {Edge} {Tracking}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/LUckner18-EOT.pdf},
venue = {Salt Lake City, USA},
year = {2018}
}
@article{faucris.282049349,
abstract = {With the advent of 'heavy Artificial Intelligence' - big data, deep learning, and ubiquitous use of the internet, ethical considerations are widely dealt with in public discussions and governmental bodies. Within Computational Paralinguistics with its manifold topics and possible applications (modelling of long-term, medium-term, and short-term traits and states such as personality, emotion, or speech pathology), we have not yet seen that many contributions. In this article, we try to set the scene by (1) giving a short overview of ethics and privacy, (2) describing the field of Computational Paralinguistics, its history and exemplary use cases, as well as (de-)anonymisation and peculiarities of speech and text data, and (3) proposing rules for good practice in the field, such as choosing the right performance measure, and accounting for representativity and interpretability.},
author = {Batliner, Anton and Hantke, Simone and Schuller, Bjorn},
doi = {10.1109/TAFFC.2020.3021015},
faupublication = {yes},
journal = {IEEE Transactions on Affective Computing},
note = {CRIS-Team WoS Importer:2022-09-23},
pages = {1236-1253},
peerreviewed = {Yes},
title = {{Ethics} and {Good} {Practice} in {Computational} {Paralinguistics}},
volume = {13},
year = {2022}
}
@inproceedings{faucris.107882324,
author = {Ganguly, Arundhuti and Fieselmann, Andreas and Boese, Jan and Rohkohl, Christopher and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Medical Imaging 2010: Visualization, Image-Guided Procedures, and Modeling},
date = {2010-02-12/2010-02-17},
editor = {Wong Kenneth H., Miga Michael I.},
faupublication = {yes},
pages = {76250K},
peerreviewed = {unknown},
title = {{Evaluating} the {Feasibility} of {C}-arm {CT} for {Brain} {Perfusion} {Imaging}: {An} in vitro {Study}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Ganguly10-ETF.pdf},
venue = {San Diego, CA},
year = {2010}
}
@inproceedings{faucris.109078904,
abstract = {Nowadays, many tracking systems in football provide positional data of players but only a few systems provide reliable data of the ball. The tracking quality of many available systems suffers from high ball velocities up to 120km/h and from the occlusion of both the players and the ball. Radio-based local positioning systems use sensors integrated in the ball and located on the players’ back or near the shoes to avoid such issues. However, a qualitative evaluation of the tracking precision of radio-based systems is often not available and to the best of our knowledge there are actually no studies that deal with the positional accuracy of ball tracking. In this paper we close this gap and use the RedFIR radio-based locating system together with a ball shooting machine to repeatedly simulate realistic situations with different velocities in an indoor environment. We compare the derived positions from high speed camera footage to the positions provided by the RedFIR system by means of root mean square error (RMSE) and Bland-Altman analysis. We found an overall positional RMSE of 12.5cm for different ball velocities ranging from 45km/h to 61km/h. There was a systematic bias of 11.5cm between positions obtained by RedFIR and positions obtained by the high speed camera. Bland-Altman analysis showed 95% limits of agreement of [21.1cm, 1.9cm]. Taking the ball diameter of 22cm into account these results indicate that RedFIR is a valid tool for kinematic, tactical and time-motion analysis of ball movements in football.},
address = {Cham},
author = {Seidl, Thomas and Witt, Nicolas and Poimann, Dino and Czyz, Titus and Franke, Norbert and Lochmann, Matthias and Völker, Matthias},
booktitle = {Proceedings of the 10th International Symposium on Computer Science in Sports (ISCSS)},
date = {2015-09-09/2015-09-11},
doi = {10.1007/978-3-319-24560-7{\_}28},
editor = {Chung, P., Soltoggio, A., Dawson, C.W., Meng, Q., Pain, M. (Eds.)},
faupublication = {no},
isbn = {9783319245584},
keywords = {soccer;tracking;positioning;ball tracking;accuracy;radio-based},
pages = {217-224},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Evaluating} the {Indoor} {Football} {Tracking} {Accuracy} of a {Radio}-{Based} {Real}-{Time} {Locating} {System}},
venue = {Leicestershire},
year = {2016}
}
@inproceedings{faucris.107862304,
author = {Bocklet, Tobias and Haderlein, Tino and Hönig, Florian Thomas and Rosanowski, Frank and Nöth, Elmar},
booktitle = {Proceedings of the 3rd Advanced Voice Function Assessment International Workshop},
date = {2009-05-18/2009-05-20},
editor = {3rd Advanced Voice Function Assessment International Workshop},
faupublication = {yes},
pages = {89-92},
title = {{Evaluation} and {Assessment} of {Speech} {Intelligibility} on {Pathologic} {Voices} {Based} {Upon} {Acoustic} {Speaker} {Models}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Bocklet09-EAA.pdf},
venue = {Madrid},
year = {2009}
}
@inproceedings{faucris.121349184,
address = {Berlin},
author = {Ulrich, Christian and Schaller, Christian and Penne, Jochen and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin},
date = {2010-03-14/2010-03-16},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {to appear},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Evaluation} of a {Time}-of-{Flight} based respiratory motion management system},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Ulrich10-EOA.pdf},
venue = {Aachen},
year = {2010}
}
@inproceedings{faucris.121380864,
abstract = {Smile detection received a enormous attention due to its famous application as a `smile shutter' in digital cameras. Edge Orientation Histograms (EOH) is one of the possible feature descriptors in a smile detector. This paper presents an evaluation of the use of Edge Orientation Histograms in a lip image based smile detector. The system built in this paper aims to discriminate lip images depicting a smile (including thin smile and broad smile) from lip images depicting non-smiling expressions. By dividing the lip images into 2 × 4 cells, and using 5° histogram bin size, we achieved 87.8% arithmetic means of accuracies. The experiments show that it is recommended not to use spatial binning that is too small. However, it is recommended to use fine orientation binning. Finally, it is recommended to use all orientation bins as features.},
author = {Timotius, Ivanna and Setyawan, Iwan},
booktitle = {The 6th International Conference on Information Technology and Electrical Engineering (ICITEE 2014)},
doi = {10.1109/ICITEED.2014.7007905},
faupublication = {no},
isbn = {978-1-4799-5302-8},
keywords = {smile detection; edge orientation histograms; estimated arithmetic means of accuracies},
pages = {1 - 5},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Evaluation} of {Edge} {Orientation} {Histograms} in {Smile} {Detection}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7007905},
venue = {Yogyakarta},
year = {2014}
}
@inproceedings{faucris.267630657,
address = {CHAM},
author = {Ferrer Riesgo, Carlos A. and Rodriguez-Guillen, Reinier and Nöth, Elmar},
booktitle = {PROGRESS IN ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION},
doi = {10.1007/978-3-030-89691-1{\_}42},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2021-12-31},
pages = {434-443},
peerreviewed = {unknown},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {{Evaluation} of {GOI} {Detectors} in {EGG} {Signals} {Assuming} {Different} {Models} for the {Pulse} {Length} {Variability}},
venue = {, ELECTR NETWORK},
year = {2021}
}
@inproceedings{faucris.121132924,
author = {Müller, Kerstin and Zheng, Yefeng and Lauritsch, Günter and Rohkohl, Christopher and Schwemmer, Chris and Maier, Andreas and Fahrig, Rebecca and Hornegger, Joachim},
booktitle = {Proceedings of the second international conference on image formation in x-ray computed tomography},
date = {2012-06-24/2012-06-27},
editor = {Frederic Noo},
faupublication = {yes},
note = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Mueller12-EOI.pdf},
pages = {5-8},
title = {{Evaluation} of {Interpolation} {Methods} for {Motion} {Compensated} {Tomographic} {Reconstruction} for {Cardiac} {Angiographic} {C}-arm {Data}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Mueller12-EOI.pdf},
venue = {Salt Lake City, Utah},
year = {2012}
}
@article{faucris.120174604,
abstract = {Purpose: For interventional cardiac procedures, anatomical and functional information about the cardiac chambers is of major interest. With the technology of angiographic C-arm systems it is possible to reconstruct intraprocedural three-dimensional (3D) images from 2D rotational angiographic projection data (C-arm CT). However, 3D reconstruction of a dynamic object is a fundamental problem in C-arm CT reconstruction. The 2D projections are acquired over a scan time of several seconds, thus the projection data show different states of the heart. A standard FDK reconstruction algorithm would use all acquired data for a filtered backprojection and result in a motion-blurred image. In this approach, a motion compensated reconstruction algorithm requiring knowledge of the 3D heart motion is used. The motion is estimated from a previously presented 3D dynamic surface model. This dynamic surface model results in a sparse motion vector field (MVF) defined at control points. In order to perform a motion compensated reconstruction, a dense motion vector field is required. The dense MVF is generated by interpolation of the sparse MVF. Therefore, the influence of different motion interpolation methods on the reconstructed image quality is evaluated. Methods: Four different interpolation methods, thin-plate splines (TPS), Shepard's method, a smoothed weighting function, and a simple averaging, were evaluated. The reconstruction quality was measured on phantom data, a porcine model as well as on in vivo clinical data sets. As a quality index, the 2D overlap of the forward projected motion compensated reconstructed ventricle and the segmented 2D ventricle blood pool was quantitatively measured with the Dice similarity coefficient and the mean deviation between extracted ventricle contours. For the phantom data set, the normalized root mean square error (nRMSE) and the universal quality index (UQI) were also evaluated in 3D image space. Results: The quantitative evaluation of all experiments showed that TPS interpolation provided the best results. The quantitative results in the phantom experiments showed comparable nRMSE of ≈0.047 ± 0.004 for the TPS and Shepard's method. Only slightly inferior results for the smoothed weighting function and the linear approach were achieved. The UQI resulted in a value of ≈ 99% for all four interpolation methods. On clinical human data sets, the best results were clearly obtained with the TPS interpolation. The mean contour deviation between the TPS reconstruction and the standard FDK reconstruction improved in the three human cases by 1.52, 1.34, and 1.55 mm. The Dice coefficient showed less sensitivity with respect to variations in the ventricle boundary. Conclusions: In this work, the influence of different motion interpolation methods on left ventricle motion compensated tomographic reconstructions was investigated. The best quantitative reconstruction results of a phantom, a porcine, and human clinical data sets were achieved with the TPS approach. In general, the framework of motion estimation using a surface model and motion interpolation to a dense MVF provides the ability for tomographic reconstruction using a motion compensation technique. © 2013 American Association of Physicists in Medicine.},
author = {Müller, Kerstin and Schwemmer, Chris and Hornegger, Joachim and Zheng, Yefeng and Wang, Yang and Lauritsch, Günter and Rohkohl, Christopher and Maier, Andreas and Schultz, Carl and Fahrig, Rebecca},
doi = {10.1118/1.4789593},
faupublication = {yes},
journal = {Medical Physics},
pages = {031107},
peerreviewed = {Yes},
title = {{Evaluation} of interpolation methods for surface-based motion compensated tomographic reconstruction for cardiac angiographic {C}-arm data},
volume = {40},
year = {2013}
}
@inproceedings{faucris.118746364,
author = {Yang, Qiao and Wu, Meng and Maier, Andreas and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Bildverarbeitung für die Medizin},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.evalua{\_}9},
pages = {42-47},
title = {{Evaluation} of {Spectrum} {Mismatching} using {Spectrum} {Binning} {Approach} for {Statistical} {Polychromatic} {Reconstruction} in {CT}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Yang14-EOS.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.279698995,
abstract = {In CT, the nonlinear attenuation characteristics of polychromatic X-rays cause beam hardening artifacts in the reconstructed images. Statistical algorithms can effectively correct beam hardening artifacts while providing the benefit of noise reduction. In practice, a big challenge for CT is the difficulty at acquiring accurate energy spectrum information, which hinders the efficiency of beam hardening correction approaches that require the spectrum as prior knowledge such as the statistical methods. In this paper, we used proposed energy spectrum binning approach for reducing prior knowledge from full spectrum to three energy bins to compare the results when applying parameters optimized for one spectrum to data measured using a different spectrum.},
author = {Yang, Qiao and Wu, Meng and Maier, Andreas and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Informatik aktuell},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}13},
editor = {Hans-Peter Meinzer, Heinz Handels, Thomas Martin Deserno, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783642541100},
note = {CRIS-Team Scopus Importer:2022-08-05},
pages = {42-47},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Evaluation} of spectrum mismatching using spectrum binning for statistical polychromatic reconstruction in {CT}},
venue = {Aachen},
year = {2014}
}
@article{faucris.113186084,
author = {Schuster, Maria and Maier, Andreas and Haderlein, Tino and Nkenke, Emeka and Wohlleben, Ulrike and Rosanowski, Frank and Eysholdt, Ulrich and Nöth, Elmar},
doi = {10.1016/j.ijporl.2006.05.016},
faupublication = {yes},
journal = {International Journal of Pediatric Otorhinolaryngology},
pages = {1741-1747},
peerreviewed = {Yes},
title = {{Evaluation} of speech intelligibility for children with cleft lip and palate by means of automatic speech recognition},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Schuster06-EOS.pdf},
volume = {70/2006},
year = {2006}
}
@article{faucris.107382704,
abstract = {We present an evaluation of state-of-the-art computer hardware architectures for implementing the FDK method, which solves the 3-D image reconstruction task in cone-beam computed tomography (CT). The computational complexity of the FDK method prohibits its use for many clinical applications unless appropriate hardware acceleration is employed. Today's most powerful hardware architectures for high-performance computing applications are based on standard multi-core processors, off-the-shelf graphics boards, the Cell Broadband Engine Architecture (CBEA), or customized accelerator platforms (e.g., FPGA-based computer components). For each hardware platform under consideration, we describe a thoroughly optimized implementation of the most time-consuming parts of the FDK algorithm; the filtering step as well as the subsequent back-projection step. We further explain the required code transformations to parallelize the algorithm for the respective target architecture. We compare both the implementation complexity and the resulting performance of all architectures under consideration using the same two medical datasets which have been acquired using a standard C-arm device. Our optimized back-projection implementations achieve at least a speedup of 6.5 (CBEA, two processors), 22.0 (GPU, single board), and 35.8 (FPGA, 9 chips) compared to a standard workstation equipped with a quad-core processor. © 2011 Elsevier B.V. All rights reserved.},
author = {Scherl, Holger and Kowarschik, Markus and Hofmann, Hannes and Keck, Benjamin and Hornegger, Joachim},
doi = {10.1016/j.parco.2011.10.004},
faupublication = {yes},
journal = {Parallel Computing},
pages = {111-124},
peerreviewed = {Yes},
title = {{Evaluation} of state-of-the-art hardware architectures for fast cone-beam {CT} reconstruction},
volume = {38},
year = {2012}
}
@inproceedings{faucris.118580044,
address = {In Press},
author = {Sembritzki, Klaus and Hager, Georg and Krammer, Bettina and Eitzinger, Jan and Wellein, Gerhard},
booktitle = {PGAS12},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2012.tech.IMMD.phleir.{\_}evalu},
pages = {-},
peerreviewed = {Yes},
publisher = {ACM Digital Library},
title = {{Evaluation} of the {Coarray} {Fortran} {Programming} {Model} on the {Example} of a {Lattice} {Boltzmann} {Code}},
venue = {Santa Barbara, CA, USA},
year = {2012}
}
@inproceedings{faucris.120203424,
abstract = {Recently, we proposed a new view differentiation scheme for analytical cone-beam reconstruction formulae that demonstrated a strong robustness to changes in the data acquisition geometry and to coarse view sampling, unlike former differentiation schemes. We incorporated this new scheme into the Katsevich reconstruction formula for the circle-plus-line trajectory. We also implemented an alternative Katsevich formula for the same trajectory, where the view differentiation step was eliminated by using integration by parts. This work evaluates both formulae in terms of resolution performance, noise performance, visual image quality and computational effort. We also evaluate the impact of the z-sampling on the line segment. Experiments are presented from simulated cone-beam data. The experiments show that the view differentiation approach with the new view differentiation scheme achieves similar image quality as the integration-by-part approach while being at the same time much more efficient. © 2007 IEEE.},
author = {Hoppe, Stefan and Dennerlein, Frank and Lauritsch, Günter and Hornegger, Joachim and Noo, Frédéric},
booktitle = {2007 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS-MIC},
doi = {10.1109/NSSMIC.2007.4437025},
faupublication = {yes},
pages = {4097-4102},
peerreviewed = {unknown},
title = {{Evaluation} of the impact of view differentiation and backprojection weight in circle-plus-line cone-beam tomography},
venue = {Honolulu, HI},
volume = {6},
year = {2007}
}
@inproceedings{faucris.121213444,
abstract = {This article focuses on the problem of threedimensional image reconstruction from cone-beam data acquired along a partial circular scan (short-scan): We present a detailed comparative evaluation of three state-of-the-art analytical algorithms suggested to achieve image reconstruction in this short-scan geometry. Our evaluation involves quantitative studies, such as the estimation of the contrast-to-noise performance, of the achievable spatial resolution and of the cone-beam artifact behavior of these reconstruction algorithms. In addition to that, we also provide a visual assessment of image quality by evaluating reconstructions of the FORBILD head phantom and a disc phantom. The numerical results presented in this paper were obtained using computer-simulated cone-beam data, while focusing on non-truncated projection data and geometry parameters that are similar to those of real medical C-arm devices. © 2007 IEEE.},
author = {Dennerlein, Frank and Noo, Frédéric and Hoppe, Stefan and Hornegger, Joachim and Lauritsch, Günter},
booktitle = {2007 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS-MIC},
doi = {10.1109/NSSMIC.2007.4436979},
faupublication = {yes},
pages = {3933-3938},
peerreviewed = {unknown},
title = {{Evaluation} of three analytical methods for reconstruction from cone-beam data on a short circular scan},
venue = {Honolulu, HI},
volume = {5},
year = {2007}
}
@inproceedings{faucris.118290744,
address = {Dresden},
author = {Haderlein, Tino and Nöth, Elmar and Schuster, Maria and Eysholdt, Ulrich and Rosanowski, Frank},
booktitle = {Proc. Speech Prosody, 3rd International Conference},
date = {2006-05-02/2006-05-05},
editor = {Hoffmann Rüdiger, Mixdorff Hansjörg},
faupublication = {yes},
pages = {701-704},
peerreviewed = {Yes},
publisher = {TUDpress},
title = {{Evaluation} of {Tracheoesophageal} {Substitute} {Voices} {Using} {Prosodic} {Features}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Haderlein06-EOT.pdf},
venue = {Dresden},
year = {2006}
}
@article{faucris.254726827,
abstract = {In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation. However, keeping track of these annotations to ensure a high-quality multi-purpose data set is a challenging and labour intensive task. We developed the open-source online platform EXACT (EXpert Algorithm Collaboration Tool) that enables the collaborative interdisciplinary analysis of images from different domains online and offline. EXACT supports multi-gigapixel medical whole slide images as well as image series with thousands of images. The software utilises a flexible plugin system that can be adapted to diverse applications such as counting mitotic figures with a screening mode, finding false annotations on a novel validation view, or using the latest deep learning image analysis technologies. This is combined with a version control system which makes it possible to keep track of changes in the data sets and, for example, to link the results of deep learning experiments to specific data set versions. EXACT is freely available and has already been successfully applied to a broad range of annotation tasks, including highly diverse applications like deep learning supported cytology scoring, interdisciplinary multi-centre whole slide image tumour annotation, and highly specialised whale sound spectroscopy clustering.},
author = {Marzahl, Christian and Aubreville, Marc and Bertram, Christof A. and Maier, Jennifer and Bergler, Christian and Kröger, Christine and Voigt, Jörn and Breininger, Katharina and Klopfleisch, Robert and Maier, Andreas},
doi = {10.1038/s41598-021-83827-4},
faupublication = {yes},
journal = {Scientific Reports},
note = {CRIS-Team Scopus Importer:2021-04-09},
peerreviewed = {Yes},
title = {{EXACT}: a collaboration toolset for algorithm-aided annotation of images with annotation version control},
volume = {11},
year = {2021}
}
@inproceedings{faucris.121225104,
abstract = {X-ray 3D rotational angiography based on C-arm systems has become a versatile and established tomographic imaging modality for high contrast objects in interventional environment. Improvements in data acquisition, e.g. by use of flat panel detectors, will enable C-arm systems to resolve even low-contrast details. However, further progress will be limited by the incompleteness of data acquisition on the conventional short-scan circular source trajectories. Cone artifacts, which result from that incompleteness, significantly degrade image quality by severe smearing and shading. To assure data completeness a combination of a partial circle with one or several line segments is investigated. A new and efficient reconstruction algorithm is deduced from a general inversion formula based on 3D Radon theory. The method is theoretically exact, possesses shift-invariant filtered backprojection (FBP) structure, and solves the long object problem. The algorithm is flexible in dealing with various circle and line configurations. The reconstruction method requires nothing more than the theoretically minimum length of scan trajectory. It consists of a conventional short-scan circle and a line segment approximately twice as long as the height of the region-of-interest. Geometrical deviations from the ideal source trajectory are considered in the implementation in order to handle data of real C-arm systems. Reconstruction results show excellent image quality free of cone artifacts. The proposed scan trajectory and reconstruction algorithm assure excellent image quality and allow low-contrast tomographic imaging with C-arm based cone-beam systems. The method can be implemented without any hardware modifications on systems commercially available today.},
author = {Dennerlein, Frank and Katsevich, Alexander and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Medical Imaging 2005 - Image Processing},
doi = {10.1117/12.595186},
editor = {Fitzpatrick J.M.Reinhardt J.M.},
faupublication = {yes},
pages = {388-399},
peerreviewed = {unknown},
title = {{Exact} and efficient cone-beam reconstruction algorithm for a short-scan circle combined with various lines},
venue = {San Diego, CA},
volume = {5747},
year = {2005}
}
@inproceedings{faucris.121822624,
author = {Blank, Peter and Eskofier, Björn},
booktitle = {10. Symposium der dvs Sportinformatik},
faupublication = {yes},
note = {UnivIS-Import:2016-06-01:Pub.2014.tech.IMMD.IMMD5.exerga{\_}6},
pages = {26-27},
peerreviewed = {unknown},
title = {{Exergaming} on {Mobile} {Devices}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Blank14-EOM.pdf},
venue = {Vienna, Austria},
year = {2014}
}
@inproceedings{faucris.110207944,
abstract = {We propose an exhaustive extension to graph cut-based coronary artery reconstruction from multiple views of a rotational angiography sequence. The reconstruction is formulated as an energy minimization problem that is solved using the a-expansion algorithm. We enforce reprojection-based data consistency and completeness conditions on the reconstructed centerline. The proposed strategy omits the need for selection and manual refinement of a reference view. A phantom study is used to assess the performance in 2D and 3D. The average reprojection error decreased from 1.32 ± 0.99mm to 0.54 ± 0.02 mm. Moreover, an increase in Dice score from 0.50 ± 0.04 mm to 0.59 ± 0.00 mm was observed, indicating superior volumetric reconstruction quality. The results suggest that the proposed extension removes the susceptibility to reference frame selection and manual interaction, while increasing reconstruction quality.},
author = {Unberath, Mathias and Achenbach, Stephan and Fahrig, Rebecca and Maier, Andreas},
booktitle = {Proceedings of the ISBI},
date = {2016-04-13/2016-04-16},
doi = {10.1109/ISBI.2016.7493468},
faupublication = {yes},
isbn = {9781479923502},
keywords = {C-arm CT; Cardiac Dynamics; Cardiac Imaging; Epipolar Geometry; Graph Cut; Symmetrization},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.exhaus{\_}2},
pages = {1143-1146},
peerreviewed = {unknown},
publisher = {IEEE Computer Society},
title = {{Exhaustive} {Graph} {Cut}-based {Vasculature} {Reconstruction}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Unberath16-EGC.pdf},
venue = {Prague, CZ},
volume = {2016-June},
year = {2016}
}
@article{faucris.113647644,
abstract = {In this publication experiences with commercial spoken dialogue systems are discussed and guidelines for achieving high usability are pointed out. Different from most commercially deployed IVR (Interactive Voice Response) systems, the systems discussed in this paper belong to a new generation of real mixed-initiative spoken dialogue systems, i. e.,the user may take the initiative, using full sentences, at virtually any point in time during the dialogue. We use three commercially deployed systems as example applications: the automated switchboard of a large German company, the movie information system operated by Germany’s largest multiplex cinema, and a football Bundesliga information system operated by a German media compan},
author = {Nöth, Elmar and Horndasch, Axel and Gallwitz, Florian and Haas, Jürgen},
faupublication = {yes},
journal = {it - Information Technology},
keywords = {Spoken dialogue systems, mixed-initiative spoken dialogue systems, IVR (Interactive Voice Response) systems},
pages = {315-321},
peerreviewed = {Yes},
title = {{Experiences} with {Commercial} {Telephone}-based {Dialogue} {Systems}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Noeth04-EWC.pdf},
volume = {46.0},
year = {2004}
}
@article{faucris.318685618,
author = {Putz, Florian and Haderlein, Marlen and Lettmaier, Sebastian and Semrau, Sabine and Fietkau, Rainer and Huang, Yixing},
doi = {10.1016/j.ijrobp.2023.11.062},
faupublication = {yes},
journal = {International Journal of Radiation Oncology Biology Physics},
keywords = {Large language model; GPT-4; Radiation Oncology},
pages = {900-904},
peerreviewed = {Yes},
title = {{Exploring} the {Capabilities} and {Limitations} of {Large} {Language} {Models} for {Radiation} {Oncology} {Decision} {Support}},
volume = {118},
year = {2024}
}
@inproceedings{faucris.222102246,
abstract = {Because total variation (TV) is non-differentiable, iterative reconstruction using a TV penalty comes with technical difficulties. To avoid these, it is popular to use a smooth approximation of TV instead, which is defined using a single parameter, herein called δ, with the convention that the approximation is better when δ is smaller. To our knowledge, it is not known how well image reconstruction with this approximation can approach a converged non-smooth TV-regularized result. In this work, we study this particular question in the context of X-ray computed tomography (CT). Experimental results are reported with real CT data of a head phantom and supplemented with a theoretical analysis. To address our question, we make proficient use of a generalized iterative soft-thresholding algorithm that allows us to handle TV and its smooth approximation in the same framework. Our results support the following conclusions. First, images reconstructed using the smooth approximation of TV appears to smoothly converge towards the TV result as δ tends to zero. Second, the value of δdoes not need to be overly small to obtain a result that is essentially equivalent to TV, implying that numerical instabilities can be avoided. Last, though it is smooth, the convergence with δ is not particularly fast, as the mean absolute pixel difference decreases only as √δ in our experiments. Altogether, we conclude that the approximation is a theoretically valid way to approximate the non-smooth TV penalty for CT, opening the door to safe utilization of a wide variety of optimization algorithms.},
author = {Haase, Viktor and Stierstorfer, K. and Hahn, K. and Schöndube, H. and Maier, Andreas and Noo, F.},
booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
date = {2019-02-17/2019-02-20},
doi = {10.1117/12.2513375},
editor = {Hilde Bosmans, Guang-Hong Chen, Taly Gilat Schmidt},
faupublication = {yes},
isbn = {9781510625433},
keywords = {Computed tomography; GISTA; Huber function; Iterative reconstruction; Total variation},
note = {CRIS-Team Scopus Importer:2019-07-12},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{Exploring} the space between smoothed and non-smooth total variation for {3D} iterative {CT} reconstruction},
venue = {San Diego, CA},
volume = {10948},
year = {2019}
}
@article{faucris.203366630,
author = {Carvalho, Tiago and Riess, Christian and Angelopoulou, Elli and Pedrini, Helio and Rocha, Anderson},
doi = {10.1109/TIFS.2013.2265677},
faupublication = {yes},
journal = {IEEE Transactions on Information Forensics and Security},
pages = {1182--1194},
peerreviewed = {Yes},
title = {{Exposing} {Digital} {Image} {Forgeries} by {Illumination} {Color} {Classification}},
volume = {8},
year = {2013}
}
@article{faucris.121128084,
abstract = {Recent reports show that three-dimensional cone-beam (CB) imaging with a floor-mounted (or ceiling-mounted) C-arm system has become a valuable tool in interventional radiology. Currently, a circular short scan is used for data acquisition, which inevitably yields CB artifacts and a short coverage in the direction of the patient table. To overcome these two limitations, a more sophisticated data acquisition geometry is needed. This geometry should be complete in terms of Tuy's condition and should allow continuous scanning, while being compatible with the mechanical constraints of mounted C-arm systems. Additionally, the geometry should allow accurate image reconstruction from truncated data. One way to ensure such a feature is to adopt a trajectory that provides full R-line coverage within the field-of-view (FOV). An R-line is any segment of line that connects two points on a source trajectory, and the R-line coverage is the set of points that belong to an R-line. In this work, we propose a novel geometry called the extended ellipse-line-ellipse (ELE) for long-object imaging with a mounted C-arm system. This trajectory is built from modules consisting of two elliptical arcs connected by a line. We demonstrate that the extended ELE can be configured in many ways so that full R-line coverage is guaranteed. Both tight and relaxed parametric settings are presented. All results are supported by extensive mathematical proofs provided in appendices. Our findings make the extended ELE trajectory attractive for axially-extended FOV imaging in interventional radiology.},
author = {Yu, Zhicong and Lauritsch, Günter and Dennerlein, Frank and Mao, Yanfei and Hornegger, Joachim and Noo, Frederic},
doi = {10.1088/0031-9155/61/4/1829},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
keywords = {R-line;long-object;C-arm;cone-beam;tomography;ELE},
pages = {1829-1851},
peerreviewed = {Yes},
title = {{Extended} ellipse-line-ellipse trajectory for long-object cone-beam imaging with a mounted {C}-arm system},
volume = {61},
year = {2016}
}
@article{faucris.114047164,
abstract = {Stereopsis is one of several visual depth cues. It has been evaluated for athletes of different types of sports in the past. However, most studies do not cover the full range of stereopsis performance. Therefore, we propose computer-supported stereopsis tests that provide an extended assessment and analysis of stereopsis performance including stereo acuity and response times. By providing stationary and moving stimuli they cover static and dynamic stereopsis, respectively. The proposed stereopsis tests were used to compare professional and amateur soccer players with subjects without soccer background. The soccer players could not perform significantly (p <= 0.05) superior than the subjects without soccer background. However, the soccer players showed significantly (p <= 0.01) superior choice reaction times for monocular stimuli. The results are in congruence with previous findings in literature.},
author = {Paulus, Jan and Tong, Jie and Hornegger, Joachim and Schmidt, Michael and Eskofier, Björn and Michelson, Georg},
doi = {10.3389/fpsyg.2014.01186},
faupublication = {yes},
journal = {Frontiers in Psychology},
keywords = {stereopsis;soccer;stereo acuity;depth perception;visual performance},
peerreviewed = {Yes},
title = {{Extended} stereopsis evaluation of professional and amateur soccer players and subjects without soccer background},
volume = {5},
year = {2014}
}
@inproceedings{faucris.118692024,
author = {Yu, Zhicong and Noo, Frédéric and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Proceedings of The 12th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2013.tech.IMMD.IMMD5.extend},
pages = {245-248},
title = {{Extended} {Volume} {Image} {Reconstruction} {Using} the {Ellipse}-{Line}-{Ellipse} {Trajectory} for a {C}-arm {System}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Yu13-EVI.pdf},
venue = {Lake Tohoe, California, USA},
year = {2013}
}
@inproceedings{faucris.108109804,
author = {Forman, Christoph and Aksoy, Murat and Straka, Matus and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the ISMRM Workshop on Current Concepts of Motion Correction for MRI & MRS},
date = {2010-02-24/2010-02-28},
editor = {International Society for Magnetic Resonance in Medicine},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Extending} the {Tracking} {Range} for {Prospective} {Motion} {Correction} using a {Single} {In}-bore {Camera} and the {Self}-{Encoded} {Marker}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Forman10-ETT.pdf},
venue = {Kitzbühel},
year = {2010}
}
@inproceedings{faucris.106472564,
abstract = {Face recognition is a technology that is achieving more and more prominence today. This technology is now found in various applications such as automatic photo tagging and identification of criminal suspects. While the task of recognizing faces is easy for humans, the task of teaching a computer to do so is very challenging. This paper presents a face recognition system based on the Kernel Fishers Discriminant Analysis (KFDA) and Nearest Neighbor (NN) algorithms. We use the KFDA algorithm as a feature extractor and the NN algorithm as a classifier. Our current implementation of the system has achieved a recognition success rate of more than 83%.},
author = {Setyawan, Iwan and Putra, Abraham F. and Timotius, Ivanna and Febrianto, Andreas A.},
booktitle = {2011 6th International Conference on Telecommunication Systems, Services, and Applications (TSSA)},
date = {2011-10-20/2011-10-21},
doi = {10.1109/TSSA.2011.6095396},
faupublication = {no},
isbn = {978-1-4577-1441-2},
peerreviewed = {Yes},
title = {{Face} recognition using {Kernel} {Fisher}'s {Discriminant} {Analysis} and nearest neighbor},
url = {http://ieeexplore.ieee.org/document/6095396/},
venue = {Bali},
year = {2011}
}
@inproceedings{faucris.117772864,
abstract = {Face recognition by machines has various important applications in our daily life. However, the task to teach machine to recognize face images has been a very challenging task. This paper presents face recognition by combining Generalized Discriminant Analysis (GDA) as a feature extractor and Support Vector Machines (SVM) as a classifier. Our experiment showed that the performance of combining these two methods as a face image classifier is better than by only using SVM. The accuracy of combined method is above 85%.},
author = {Timotius, Ivanna and Linasari, The Christiani and Setyawan, Iwan and Febrianto, Andreas A.},
booktitle = {2011 6th International Conference on Telecommunication Systems, Services, and Applications (TSSA)},
doi = {10.1109/TSSA.2011.6095397},
faupublication = {no},
isbn = {978-1-4577-1441-2},
keywords = {Face Recognition; Generalized Discriminant Analysis; Support Vector Machines},
pages = {8 - 10},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Face} recognition using support vector machines and generalized discriminant analysis},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6095397},
venue = {Bali},
year = {2011}
}
@inproceedings{faucris.121213224,
abstract = {In this article, we propose a novel factorization of the circular cone-beam (CB) reconstruction problem into a set of independent 2D inversion problems. This factorization is established in the context of modern two-step Hilbert reconstruction methods by combining the ideas of an empirically derived CB inversion approach with a firm and exact theory. We were able to accurately discretize these 2D inversion problems, which allows a detailed investigation of CB reconstruction by using the Singular Value Decomposition and also allows efficient iterative reconstruction approaches. The introduced theory is applied for preliminary studies of the stability of circular CB tomography assuming a short object. We analyzed, how the radius of the circular scan affects the stability and investigated the effect of an additional linear scan onto the condition of the problem. Numerical results are presented for a disc phantom. © 2006 IEEE.},
author = {Dennerlein, Frank and Noo, Frédéric and Hornegger, Joachim and Lauritsch, Günter},
booktitle = {2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD},
doi = {10.1109/NSSMIC.2006.356485},
faupublication = {yes},
pages = {2908-2912},
peerreviewed = {unknown},
title = {{Factorization} of the reconstruction problem in circular cone-beam tomography and its use for stability analysis},
venue = {San Diego, CA},
volume = {5},
year = {2007}
}
@article{faucris.115524024,
abstract = {Oral squamous cell carcinoma (OSCC) and its treatment impair speech intelligibility by alteration of the vocal tract. The aim of this study was to identify the factors of oral cancer treatment that influence speech intelligibility by means of an automatic, standardized speech-recognition system. The study group comprised 71 patients (mean age 59.89, range 35-82 years) with OSCC ranging from stage T1 to T4 (TNM staging). Tumours were located on the tongue (n=23), lower alveolar crest (n=27), and floor of the mouth (n=21). Reconstruction was conducted through local tissue plasty or microvascular transplants. Adjuvant radiotherapy was performed in 49 patients. Speech intelligibility was evaluated before, and at 3, 6, and 12 months after tumour resection, and compared to that of a healthy control group (n=40). Postoperatively, significant influences on speech intelligibility were tumour localization (P=0.010) and resection volume (P=0.019). Additionally, adjuvant radiotherapy (P=0.049) influenced intelligibility at 3 months after surgery. At 6 months after surgery, influences were resection volume (P=0.028) and adjuvant radiotherapy (P=0.034). The influence of tumour localization (P=0.001) and adjuvant radiotherapy (P=0.022) persisted after 12 months. Tumour localization, resection volume, and radiotherapy are crucial factors for speech intelligibility. Radiotherapy significantly impaired word recognition rate (WR) values with a progression of the impairment for up to 12 months after surgery.},
author = {Stelzle, Florian and Knipfer, Christian and Schuster, M. and Bocklet, Tobias and Nöth, Elmar and Adler, Werner and Schempf, L. and Vieler, Peter and Riemann, Max and Neukam, Friedrich Wilhelm and Nkenke, Emeka},
doi = {10.1016/j.ijom.2013.05.021},
faupublication = {yes},
journal = {International journal of oral and maxillofacial surgery},
pages = {1377-84},
peerreviewed = {unknown},
title = {{Factors} influencing relative speech intelligibility in patients with oral squamous cell carcinoma: a prospective study using automatic, computer-based speech analysis.},
volume = {42},
year = {2013}
}
@inproceedings{faucris.259687621,
abstract = {Manufacturing engineering is concerned with the application of engineering practices in manufacturing processes and production methods. Continuous optimization of processes, tools as well as machinery and equipment is the key to producing quality products with optimal capital investment. Hereby, maintenance plays a crucial role and allows manufacturers to optimize their processes. To enable improvements in this field it is required to analyze and evaluate the necessities for actions on component level. In this work we want to present a detailed retrospective analysis of more than 4.000 maintenance reports and analyze causes for assembly failures depending on the associated components. Furthermore, we extend the analysis and investigate the failure dependency with respect to the days elapsed from the date of maintenance request to resolving the issue. It turned out, not all cases with high failure rates are associated with subsequent higher risks considering the respective urgency related to each failure case. Furthermore, we discovered especially hydraulic and pneumatic components have a significant high to critical risk, as the labour safety and other components are threatened by their failure. Moreover we determined, that only 10% of all actions were planned maintenance and thus we propose based on the results of the risks analysis, how planned and preventive maintenance should be extended to reduce costs in this regard.
3 volume can be sampled in less than one second with an error below 0.1 mm. Furthermore, we accelerate the interpolation of a 2563 dense deformation field to only 6.5 minutes using the proposed methods from days with previous methods.},
address = {Berlin},
author = {Maier, Andreas and Taubmann, Oliver and Wetzl, Jens and Wasza, Jakob and Forman, Christoph and Fischer, Peter and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Bildverarbeitung für die Medizin 2014},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}34},
edition = {1},
faupublication = {yes},
isbn = {978-3-642-54110-0},
keywords = {interpolation, motion field, phantom},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.fastin{\_}7},
pages = {168-173},
publisher = {Springer},
title = {{Fast} {Interpolation} of {Dense} {Motion} {Fields} from {Synthetic} {Phantoms}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Maier14-FIO.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.121152284,
abstract = {In computed tomography (CT), the nonlinear characteristics of beam hardening are due to the polychromaticity of X-rays, which severely degrade the CT image quality and diagnostic accuracy. The correction of beam hardening has been an active area since the early years of CT, and various techniques have been developed. State of- the-art works on multi-material beam hardening correction (BHC) are mainly based on segmenting datasets into different materials, and correcting the non-linearity iteratively. Those techniques are limited in correction effectiveness due to inaccurate segmentation. Furthermore, most of them are computationally intensive. In this study, we introduce a fast BHC scheme based on frequency splitting with the fact that beam hardening artifacts mainly contain in the low frequency components and take more iterations to be corrected in comparison with high frequency components. After low-pass filtering and correcting artifacts at down-sampled projections, an artifact reduced high resolution reconstruction will be obtained by incorporating the original edge information from the high frequency components. Evaluations in terms of correction accuracy and computational eficiency are performed using simulated and real CT datasets. In comparison to the BHC algorithm without frequency splitting, the proposed accelerated algorithm yields comparable results in correcting cupping and streak artifacts with tremendously reduced computational effort. We conclude that the presented framework can achieve a significant speedup while still obtaining excellent artifact reduction. This is a significant practical advantage for clinical as well as industrial CT. © 2013 SPIE.},
author = {Yang, Qiao and Elter, Matthias and Schasiepen, Ingo and Maass, Nicole and Hornegger, Joachim},
booktitle = {Medical Imaging 2013: Physics of Medical Imaging},
doi = {10.1117/12.2007808},
faupublication = {yes},
pages = {-},
title = {{Fast} iterative beam hardening correction based on frequency splitting in computed tomography},
venue = {Lake Buena Vista, FL},
volume = {8668},
year = {2013}
}
@inproceedings{faucris.203848468,
abstract = {This paper discusses fast pose verification for radiation therapy on a new high-speed radiation therapy device. The PHASER system follows the idea of 4th generation CT imaging and allows fast 360° treatment using a steerable electron beam. Doing so, dose delivery is possible in few seconds. A major problem, however, is fast verification of the patient pose during treatment. In this paper, we suggest to use a projection-based approach that can be evaluated quickly and allows an accuracy below 1 mm as shown by our simulation study based on planning data from six 4D CT data sets.},
address = {Heidelberg},
author = {Maier, Andreas and Westphal, Susanne and Geimer, Tobias and Maxim, Peter G. and King, Gregory and Schueler, Emil and Fahrig, Rebecca and Loo, Billy},
booktitle = {Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0{\_}27},
faupublication = {yes},
isbn = {9783662543450},
note = {UnivIS-Import:2018-09-11:Pub.2017.tech.IMMD.IMMD5.fastpo},
pages = {104-109},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Fast} {Pose} {Verification} for {High}-{Speed} {Radiation} {Therapy}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Maier17-FPV.pdf},
venue = {Heidelberg},
year = {2017}
}
@inproceedings{faucris.121455224,
address = {Erlangen},
author = {Hönig, Florian Thomas and Batliner, Anton and Nöth, Elmar},
booktitle = {3rd Russian-Bavarian Conference on Biomedical Engineering},
date = {2007-07-02/2007-07-03},
editor = {Hornegger Joachim, Mayr Ernst W., Schookin Sergey, Feußner Hubertus, Navab Nassir, Gulyaev Yuri V., Höller Kurt, Ganzha Victor},
faupublication = {yes},
pages = {47-52},
publisher = {Union aktuell},
title = {{Fast} {Recursive} {Data}-driven {Multi}-resolution {Feature} {Extraction} for {Physiological} {Signal} {Classification}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Hoenig07-FRD.pdf},
venue = {Erlangen},
year = {2007}
}
@inproceedings{faucris.208870119,
author = {Davari, Amirabbas and Özkan, Hasan Can and Maier, Andreas and Riess, Christian},
booktitle = {IEEE International Geoscience and Remote Sensing Symposium},
date = {2018-07-22/2018-07-27},
doi = {10.1109/IGARSS.2018.8517643},
faupublication = {yes},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Fast} {Sample} {Generation} with {Variational} {Bayesian} for {Limited} {Data} {Hyperspectral} {Image} {Classification}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Davari18-FSG.pdf},
venue = {Valencia},
year = {2018}
}
@article{faucris.121156244,
abstract = {Many scientists in the field of x-ray imaging rely on the simulation of x-ray images. As the phantom models become more and more realistic, their projection requires high computational effort. Since x-ray images are based on transmission, many standard graphics acceleration algorithms cannot be applied to this task. However, if adapted properly, the simulation speed can be increased dramatically using state-of-the-art graphics hardware. A custom graphics pipeline that simulates transmission projections for tomographic reconstruction was implemented based on moving spline surface models. All steps from tessellation of the splines, projection onto the detector and drawing are implemented in OpenCL. We introduced a special append buffer for increased performance in order to store the intersections with the scene for every ray. Intersections are then sorted and resolved to materials. Lastly, an absorption model is evaluated to yield an absorption value for each projection pixel. Projection of a moving spline structure is fast and accurate. Projections of size 640×480 can be generated within 254ms. Reconstructions using the projections show errors below 1 HU with a sharp reconstruction kernel. Traditional GPU-based acceleration schemes are not suitable for our reconstruction task. Even in the absence of noise, they result in errors up to 9HU on average, although projection images appear to be correct under visual examination. Projections generated with our new method are suitable for the validation of novel CT reconstruction algorithms. For complex simulations, such as the evaluation of motion-compensated reconstruction algorithms, this kind of x-ray simulation will reduce the computation time dramatically. © 2012 Institute of Physics and Engineering in Medicine.},
author = {Maier, Andreas and Hofmann, Hannes and Schwemmer, Chris and Hornegger, Joachim and Keil, Andreas and Fahrig, Rebecca},
doi = {10.1088/0031-9155/57/19/6193},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {6193-6210},
peerreviewed = {Yes},
title = {{Fast} simulation of x-ray projections of spline-based surfaces using an append buffer},
volume = {57},
year = {2012}
}
@article{faucris.106944244,
abstract = {The snack food potato chips induces food intake in ad libitum fed rats, which is associated with modulation of the brain reward system and other circuits. Here, we show that food intake in satiated rats is triggered by an optimal fat/carbohydrate ratio. Like potato chips, an isocaloric fat/carbohydrate mixture influenced whole brain activity pattern of rats, affecting circuits related e.g. to reward/addiction, but the number of modulated areas and the extent of modulation was lower compared to the snack food itself.},
author = {Hoch, Tobias and Kreitz, Silke and Gaffling, Simone and Pischetsrieder, Monika and Heß, Andreas},
doi = {10.1038/srep10041},
faupublication = {yes},
journal = {Scientific Reports},
note = {UnivIS-Import:2015-07-08:Pub.2015.nat.dchph.llmch.fatcar},
pages = {10041},
peerreviewed = {Yes},
title = {{Fat}/carbohydrate ratio but not energy density determines snack food intake and activates brain reward areas},
url = {http://www.nature.com/search?facets=new&journal=srep&q=SREP10041},
volume = {5},
year = {2015}
}
@inproceedings{faucris.203720078,
author = {Schneider, Manuel and Lugauer, Felix and Hoppe, Elisabeth and Nickel, Dominik and Dale, Brian M. and Kiefer, Berthold and Maier, Andreas and Bashir, Mustafa R.},
booktitle = {Proceedings of the Joint Annual Meeting ISMRM-ESMRMB},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.fatcon},
pages = {2773},
peerreviewed = {unknown},
title = {{Fat} {Content} and {Fatty} {Acid} {Composition} {Quantification} {Using} a {3D} {Stack}-of-{Radial} {Trajectory} {With} {Adaptive} {Gradient} {Calibration}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Schneider18-FCA.pdf},
venue = {Paris, France},
year = {2018}
}
@inproceedings{faucris.208683828,
author = {Danner, Daniel and Kaufhold, Caroline and Kranz, Peter and Müller, Rainer and Pfaller, Sven and Riess, Christian and Angelopoulou, Elli},
booktitle = {28th IEEE International Real-Time Systems Symposium (RTSS 2007)},
date = {2007-12-03/2007-12-06},
faupublication = {yes},
peerreviewed = {No},
title = {{FAUBOT}: {Purposeful} {Navigation} of a {Robot} in a {Simulated} {Environment}},
venue = {Tucson, AZ},
year = {2007}
}
@inproceedings{faucris.107894204,
author = {Spiegl, Werner and Riedhammer, Korbinian Thomas and Steidl, Stefan and Nöth, Elmar},
booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
date = {2010-05-19/2010-05-21},
editor = {European Language Resources Association (ELRA)},
faupublication = {yes},
pages = {2420-2423},
title = {{FAU} {IISAH} {Corpus} - {A} {German} {Speech} {Database} {Consisting} of {Human}-{Machine} and {Human}-{Human} {Interaction} {Acquired} by {Close}-{Talking} and {Far}-{Distance} {Microphones}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Spiegl10-FIC.pdf},
venue = {Valletta},
year = {2010}
}
@inproceedings{faucris.120186264,
abstract = {For emergency cases in the interventional room, 3D long-object cone-beam(CB) imaging using a C-arm system could save valuable time and reduce risks to the patient by avoiding the traditionally-used CT scan, and thus could potentially be a crucial tool for patient health. To accomplish such a task, the reverse helix is an attractive trajectory, however theoretically-exact and stable (TES) reconstruction with a reverse helix is challenging. Two TES solutions are available, but both of them come with a heavy computational load and some issues in terms of image quality. This work proposes three new approximate reconstruction algorithms for the reverse helix that are stable and efficient, and thus practical. Though not exact, reconstruction results obtained from all three methods appear acceptable. © 2011 IEEE.},
author = {Yu, Zhicong and Noo, Frédéric and Dennerlein, Frank and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {2011 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2011},
doi = {10.1109/NSSMIC.2011.6153757},
faupublication = {yes},
pages = {3980-3985},
peerreviewed = {unknown},
title = {{FDK}-type reconstruction algorithms for the reverse helical trajectory},
venue = {Valencia},
volume = {null},
year = {2012}
}
@article{faucris.248374069,
abstract = {Objective: This pilot study aimed to assess the feasibility of intraoperative assessment of safe margins with Confocal Laser Endomicroscopy (CLE) during planned partial or total laryngectomy. Methods: Eight patients with confirmed larynx squamous cell carcinoma (SCC) and planned partial or total laryngectomy were included in this study in March 2020. Two head and neck surgeons and one pathologist were asked to classify carcinoma or healthy epithelium in a sample of 94 representative sequences (5.640 images), blinded to the histological results (H&E staining). Results: Healthy mucosa areas showed epithelium with cells of uniform size and shape with distinct cytoplasmic membranes and regular vessel architecture. CLE optical biopsy of SCC demonstrated a disorganized arrangement of variable cellular morphology. We calculated an accuracy, sensitivity, specificity, PPV, and NPV of 80.1%, 72.3%, 87.9%, 85.7%, and 76.1%, respectively. A distinct transition between healthy appearing tissue and suspicious lesions could also be detected. Conclusion: CLE can be easily integrated into the intraoperative setting, generate real-time, in-vivo microscopic images of the larynx for evaluation and demarcation of cancer. If validated in further studies, CLE could eventually contribute to a less radical approach by enabling a more precise evaluation of the cancer margin.},
author = {Sievert, Matti and Oetter, Nicolai and Aubreville, Marc and Stelzle, Florian and Maier, Andreas and Eckstein, Markus and Mantsopoulos, Konstantinos and Gostian, Antoniu Oreste and Mueller, Sarina K. and Koch, Michael and Agaimy, Abbas and Iro, Heinrich and Goncalves, Miguel},
doi = {10.1016/j.anl.2021.01.005},
faupublication = {yes},
journal = {Auris Nasus Larynx},
keywords = {Confocal laser endomicroscopy; Laryngeal cancer; Safe surgical margins},
note = {CRIS-Team Scopus Importer:2021-01-29},
peerreviewed = {Yes},
title = {{Feasibility} of intraoperative assessment of safe surgical margins during laryngectomy with confocal laser endomicroscopy: {A} pilot study},
year = {2021}
}
@inproceedings{faucris.215001554,
author = {Maier, Jennifer and Aichert, André and Mehringer, Wolfgang and Bier, Bastian and Eskofier, Björn and Levenston, Marc and Gold, Garry and Fahrig, Rebecca and Bonaretti, Serena and Maier, Andreas},
booktitle = {Conference Record of the 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)},
date = {2018-11-10/2018-11-17},
doi = {10.1109/nssmic.2018.8824463},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Feasibility} of {Motion} {Compensation} using {Inertial} {Measurement} in {C}-arm {CT}},
venue = {Sydney},
year = {2018}
}
@inproceedings{faucris.106518764,
author = {Wetzl, Jens and Schroeder, Lea and Forman, Christoph and Lugauer, Felix and Rehner, Robert and Fenchel, Matthias and Maier, Andreas and Hornegger, Joachim and Speier, Peter},
booktitle = {Proceedings of the 24th Annual Meeting of the ISMRM (ISMRM 2016)},
faupublication = {yes},
note = {UnivIS-Import:2017-01-09:Pub.2016.tech.IMMD.IMMD5.feasib},
pages = {2613},
peerreviewed = {unknown},
title = {{Feasibility} {Study}: {Free}-{Breathing} 3-{D} {CINE} {Imaging} with {Respiratory} {Gating} {Based} on {Pilot} {Tone} {Navigation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Wetzl16-FSF.pdf},
venue = {Singapur},
year = {2016}
}
@inproceedings{faucris.107914664,
address = {Erlangen},
author = {Han, Jingfeng and Hornegger, Joachim and Kuwert, Torsten and Bautz, Werner and Römer, Wolfgang},
booktitle = {Frontiers in Simulation},
date = {2005-09-12/2005-09-15},
editor = {Hülsemann Frank, Kowarschik Markus, Rüde Ulrich},
faupublication = {yes},
pages = {638-643},
peerreviewed = {unknown},
publisher = {SCS Publishing House e.V.},
title = {{Feature} {Constrained} {Non}-rigid {Image} {Registration}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Han05-FCN.pdf},
venue = {Erlangen},
year = {2005}
}
@inproceedings{faucris.249776116,
abstract = {It has been long known that denoising of SPECT projection data from multi channel collimators harbors the danger that features are filtered away as distinction between noise and signal in the 2D projection image does not consider the tomographic information (see Vija, Yahil et al.). We investigate if an approach using Neural Networks can overcome the past issues, by training a U-Net on Monte Carlo Simulations of the XCAT phantom. Although error metrics indicate improvement of signal statistics, we observe a loss of image features after the reconstruction. We show that when using OSEM reconstruction without denoising in projection domain, these features can be preserved.
Methods: In this work, we propose two fiducial marker detection methods: direct detection from distorted markers (direct method) and detection after marker recovery (recovery method). For direct detection from distorted markers in reconstructed volumes, an efficient automatic marker detection method using {two neural networks and a conventional circle detection algorithm} is proposed. For marker recovery, a task-specific learning strategy is proposed to recover markers from severely truncated data. Afterwards, a conventional marker detection algorithm is applied for position detection.
Results: The two methods are evaluated on simulated and real data. The direct method achieves 100% detection rates with maximal 2-pixel difference on simulated data with normal truncation and simulated data with severe noise, but fails to detect all the markers in extremely severe truncation case. The recovery method detects all the markers successfully with maximal 1 pixel difference on all simulated data sets. For real data, both methods achieve 100% marker detection rates with mean registration error below 0.2 mm.
Conclusions: Our experiments demonstrate that the direct method is capable of detecting distorted markers accurately and the recovery method with task-specific learning has high robustness and generalizability on various data sets.
The task-specific learning is able to reconstruct structures of interest outside the FOV from severely truncated data, which has the potential to empower CBCT systems with new applications.
In computed tomography (CT), data truncation is a common problem. Images reconstructed by the standard filtered back-projection algorithm from truncated data suffer from cupping artifacts inside the field-of-view (FOV), while anatomical structures are severely distorted or missing outside the FOV. Deep learning, particularly the U-Net, has been applied to extend the FOV as a post-processing method. Since image-to-image prediction neglects the data fidelity to measured projection data, incorrect structures, even inside the FOV, might be reconstructed by such an approach. Therefore, generating reconstructed images directly from a post-processing neural network is inadequate. In this work, we propose a data consistent reconstruction method, which utilizes deep learning reconstruction as prior for extrapolating truncated projections and a conventional iterative reconstruction to constrain the reconstruction consistent to measured raw data. Its efficacy is demonstrated in our study, achieving small average root-mean-square error of 24 HU inside the FOV and a high structure similarity index of 0.993 for the whole body area on a test patient's CT data.
},
author = {Huang, Yixing and Gao, Lei and Preuhs, Alexander and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin: Algorithmen – Systeme – Anwendungen},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}40},
editor = {Andreas Maier, Klaus Hermann Maier-Hein, Thomas Martin Deserno, Heinz Handels, Thomas Tolxdorff},
faupublication = {yes},
keywords = {Deep learning; data truncation; FOV extension; data consistency},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Field} of {View} {Extension} in {Computed} {Tomography} {Using} {Deep} {Learning} {Prior}},
url = {https://arxiv.org/abs/1911.01178},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.119177124,
address = {-},
author = {Batliner, Anton and Kießling, Andreas and Burger, Stefanie and Nöth, Elmar},
booktitle = {Proc. of the 13th Intl. Congress of Phonetic Sciences},
date = {1995-08-13/1995-08-19},
editor = {-},
faupublication = {yes},
pages = {472-475},
publisher = {-},
title = {{Filled} {Pauses} in {Spontaneous} {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1995/Batliner95-FPI.pdf},
venue = {Stockholm},
year = {1995}
}
@article{faucris.267016961,
abstract = {Biometric identification techniques such as photo-identification require an array of unique natural markings to identify individuals. From 1975 to present, Bigg’s killer whales have been photo-identified along the west coast of North America, resulting in one of the largest and longest-running cetacean photo-identification datasets. However, data maintenance and analysis are extremely time and resource consuming. This study transfers the procedure of killer whale image identification into a fully automated, multi-stage, deep learning framework, entitled FIN-PRINT. It is composed of multiple sequentially ordered sub-components. FIN-PRINT is trained and evaluated on a dataset collected over an 8-year period (2011–2018) in the coastal waters off western North America, including 121,000 human-annotated identification images of Bigg’s killer whales. At first, object detection is performed to identify unique killer whale markings, resulting in 94.4% recall, 94.1% precision, and 93.4% mean-average-precision (mAP). Second, all previously identified natural killer whale markings are extracted. The third step introduces a data enhancement mechanism by filtering between valid and invalid markings from previous processing levels, achieving 92.8% recall, 97.5%, precision, and 95.2% accuracy. The fourth and final step involves multi-class individual recognition. When evaluated on the network test set, it achieved an accuracy of 92.5% with 97.2% top-3 unweighted accuracy (TUA) for the 100 most commonly photo-identified killer whales. Additionally, the method achieved an accuracy of 84.5% and a TUA of 92.9% when applied to the entire 2018 image collection of the 100 most common killer whales. The source code of FIN-PRINT can be adapted to other species and will be publicly available.
0.96) and significant (P ≪.01) correlations between radial and Cartesian PDFF measurements for both the motion-averaged reconstruction (slope: 0.90; intercept: 0.07%) and the motion-resolved reconstruction (slope: 0.90; intercept: 0.11%). The motion-averaged technique overestimated hepatic (Formula presented.) values (slope: 0.35; intercept: 30.2 1/s) compared to the Cartesian reference. However, performing a respiratory-resolved reconstruction led to better (Formula presented.) value consistency (slope: 0.77; intercept: 7.5 1/s). Conclusions: The proposed techniques are promising alternatives to conventional Cartesian imaging for fat and (Formula presented.) quantification in patients with limited breath-holding capabilities. For accurate (Formula presented.) estimation, respiratory-resolved reconstruction should be used.},
author = {Schneider, Manuel and Benkert, Thomas and Solomon, Eddy and Nickel, Dominik and Fenchel, Matthias and Kiefer, Berthold and Maier, Andreas and Chandarana, Hersh and Block, Kai Tobias},
doi = {10.1002/mrm.28280},
faupublication = {yes},
journal = {Magnetic Resonance in Medicine},
keywords = {compressed sensing; free-breathing fat/ R2∗ quantification; multi-echo 3D stack-of-stars GRE; nonalcoholic fatty liver disease; radial sampling; respiratory motion-resolved reconstruction},
note = {CRIS-Team Scopus Importer:2020-04-28},
peerreviewed = {Yes},
title = {{Free}-breathing fat and {R2}∗ quantification in the liver using a stack-of-stars multi-echo acquisition with respiratory-resolved model-based reconstruction},
year = {2020}
}
@inproceedings{faucris.221695313,
abstract = {We present a free-breathing multi-contrast 3-D cardiac CINE acquisition and reconstruction technique based on Compressed Sensing. Inversion pulses were repeatedly applied during a continuous acquisition to sample contrast- and cardiac-resolved 3-D data, while a self-navigation method was applied for respiratory gating. Validation was performed in a phantom, showing recovery curves and T1* maps in good correlation to known T1 values for the phantom as well as a MOLLI reference measurement. Feasibility for in-vivo application was demonstrated in a healthy voluntee},
author = {Hoppe, Elisabeth and Wetzl, Jens and Forman, Christoph and Koerzdoerfer, Gregor and Schneider, Manuel and Speier, Peter and Schmidt, Michaela and Maier, Andreas},
booktitle = {Proceedings of the Joint Annual Meeting ISMRM-ESMRMB (27th Annual Meeting & Exhibition)},
date = {2019-05-11/2019-05-16},
faupublication = {yes},
keywords = {Magnetic Resonance Imaging, Cardiac CINE Magnetic Resonance Imaging, Multicontrast Imaging, Compressed Sensing},
pages = {2129},
peerreviewed = {unknown},
title = {{Free}-{Breathing}, {Self}-{Navigated} and {Dynamic} 3-{D} {Multi}-{Contrast} {Cardiac} {CINE} {Imaging} {Using} {Cartesian} {Sampling} and {Compressed} {Sensing}},
venue = {Montreal},
year = {2019}
}
@inproceedings{faucris.118388424,
author = {Wetzl, Jens and Lugauer, Felix and Kroeker, Randall and Schmidt, Michaela and Maier, Andreas and Forman, Christoph},
booktitle = {Proceedings of the 25th Annual Meeting of the ISMRM},
faupublication = {yes},
note = {UnivIS-Import:2017-07-10:Pub.2017.tech.IMMD.IMMD5.freebr{\_}8},
pages = {3152},
peerreviewed = {unknown},
title = {{Free}-{Breathing} {Self}-{Navigated} {Isotropic} 3-{D} {CINE} {Imaging} of the {Whole} {Heart} using {Adaptive} {Triggering} and {Retrospective} {Gating}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Wetzl17-FSI.pdf},
venue = {Honolulu, HI, USA},
year = {2017}
}
@inproceedings{faucris.109224764,
author = {Wetzl, Jens and Lugauer, Felix and Schmidt, Michaela and Maier, Andreas and Hornegger, Joachim and Forman, Christoph},
booktitle = {Proceedings of the 24th Annual Meeting of the ISMRM (ISMRM 2016)},
faupublication = {yes},
note = {UnivIS-Import:2017-01-09:Pub.2016.tech.IMMD.IMMD5.freebr},
pages = {411},
peerreviewed = {unknown},
title = {{Free}-{Breathing}, {Self}-{Navigated} {Isotropic} 3-{D} {CINE} {Imaging} of the {Whole} {Heart} {Using} {Cartesian} {Sampling}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Wetzl16-FSI.pdf},
venue = {Singapur},
year = {2016}
}
@inproceedings{faucris.120331684,
address = {Berlin Heidelberg},
author = {Forman, Christoph and Grimm, Robert and Hutter, Jana and Maier, Andreas and Hornegger, Joachim and Zenge, Michael O.},
booktitle = {MICCAI 2013, Part II, LNCS 8150},
date = {2013-09-22/2013-09-26},
editor = {Mori K., Sakuma I., Sato Y., Barillot C., Navab N.},
faupublication = {yes},
pages = {575-582},
publisher = {Springer},
title = {{Free}-{Breathing} {Whole}-{Heart} {Coronary} {MRA}: {Motion} {Compensation} {Integrated} into {3D} {Cartesian} {Compressed} {Sensing} {Reconstruction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Forman13-FWC.pdf},
venue = {Nagoya, Japan},
year = {2013}
}
@inproceedings{faucris.118275564,
author = {Forman, Christoph and Grimm, Robert and Hutter, Jana and Wasza, Jakob and Kraus, Martin and Hornegger, Joachim and Zenge, Michael O.},
booktitle = {Proceedings of the 21st Annual Meeting of ISMRM},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2013.tech.IMMD.IMMD5.freebr{\_}2},
pages = {4528},
title = {{Free}-{Breathing} {Whole}-{Heart} {Coronary} {MRI}: {An} {Image}-{Based} {Motion} {Compensation} {Integrated} {Into} {Compressed}-{Sensing} {Reconstruction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Forman13-FWC.pdf},
venue = {Salt Lake City, UT, USA},
year = {2013}
}
@inproceedings{faucris.108132904,
author = {Yu, Zhicong and Maier, Andreas and Schönborn, Manfred and Vogt, Florian and Köhler, Christoph and Lauritsch, Günter and Hornegger, Joachim and Noo, Frédéric},
booktitle = {Proceedings of The second international conference on image formation in x-ray computed tomography},
date = {2012-06-24/2012-06-27},
editor = {Noo Frederic},
faupublication = {yes},
pages = {364-368},
peerreviewed = {Yes},
title = {{Frist} experimental results on long-object imaging using a reverse helical trajectory with a {C}-arm system},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Yu12-FER.pdf},
venue = {Salt Lake City, UT},
year = {2012}
}
@article{faucris.243601107,
abstract = {Embodied cognition research on Parkinson's disease (PD) points to disruptions of frontostriatal language functions as sensitive targets for clinical assessment. However, no existing approach has been tested for crosslinguistic validity, let alone by combining naturalistic tasks with machine-learning tools. To address these issues, we conducted the first classifier-based examination of morphological processing (a core frontostriatal function) in spontaneous monologues from PD patients across three typologically different languages. The study comprised 330 participants, encompassing speakers of Spanish (61 patients, 57 matched controls), German (88 patients, 88 matched controls), and Czech (20 patients, 16 matched controls). All subjects described the activities they perform during a regular day, and their monologues were automatically coded via morphological tagging, a computerized method that labels each word with a part-of-speech tag (e.g., noun, verb) and specific morphological tags (e.g., person, gender, number, tense). The ensuing data were subjected to machine-learning analyses to assess whether differential morphological patterns could classify between patients and controls and reflect the former's degree of motor impairment. Results showed robust classification rates, with over 80% of patients being discriminated from controls in each language separately. Moreover, the most discriminative morphological features were associated with the patients' motor compromise (as indicated by Pearson r correlations between predicted and collected motor impairment scores that ranged from moderate to moderate-to-strong across languages). Taken together, our results suggest that morphological patterning, an embodied frontostriatal domain, may be distinctively affected in PD across languages and even under ecological testing conditions.},
author = {Eyigoz, Elif and Courson, Melody and Sedeño, Lucas and Rogg, Katharina and Orozco-Arroyave, Juan Rafael and Nöth, Elmar and Skodda, Sabine and Trujillo, Natalia and Rodríguez, Mabel and Rusz, Jan and Muñoz, Edinson and Cardona, Juan F. and Herrera, Eduar and Hesse, Eugenia and Ibáñez, Agustín and Cecchi, Guillermo and García, Adolfo M.},
doi = {10.1016/j.cortex.2020.08.020},
faupublication = {yes},
journal = {Cortex},
keywords = {Automated speech analysis; Cross-linguistic validity; Linguistic assessments; Morphology; Parkinson's disease},
note = {CRIS-Team Scopus Importer:2020-10-09},
pages = {191-205},
peerreviewed = {Yes},
title = {{From} discourse to pathology: {Automatic} identification of {Parkinson}'s disease patients via morphological measures across three languages},
volume = {132},
year = {2020}
}
@inproceedings{faucris.121384604,
abstract = {The monitoring of emotional user states can help to assess the progress of human-machine-communication. If we look at specific databases, however, we are faced with several problems: users behave differently, even within one and the same setting, and some phenomena are sparse; thus it is not possible to model and classify them reliably. We exemplify these difficulties on the basis of SympaFly, a database with dialogues between users and a fully automatic speech dialogue telephone system for flight reservation and booking, and discuss possible remedies.},
address = {Berlin},
author = {Batliner, Anton and Hacker, Christian and Steidl, Stefan and Nöth, Elmar and Haas, Jürgen},
booktitle = {Affective Dialogue Systems, Proceedings of a Tutorial and Research Workshop},
editor = {André E., Dybkiaer L., Minker W., Heisterkamp P.},
faupublication = {yes},
month = {Jan},
pages = {1-12},
peerreviewed = {Yes},
publisher = {Springer},
title = {{From} {Emotion} to {Interaction} - {Lessons} from {Real} {Human}-{Machine}-{Dialogues}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Batliner04-FET.pdf},
venue = {Kloster Irsee},
year = {2004}
}
@inproceedings{faucris.110732204,
author = {Bourier, Felix and Schneider, Hans-Jürgen and Heißenhuber, Frank and Ganslmeier, Patrycja and Fischer, Robert and Brost, Alexander and Koch, Martin and Strobel, Norbert and Hornegger, Joachim and Kurzidim, Klaus},
booktitle = {77. Jahrestagung},
date = {2011-04-27/2011-04-30},
editor = {Deutsche Gesellschaft für Kardiologie},
faupublication = {yes},
pages = {188.0},
peerreviewed = {unknown},
title = {{Frühzeitige} {Registrierung} eines {3D}-{Overlays} des linken {Atriums} während linksatrialen {Ablationen} mittels {Koronarsinuskatheter}},
venue = {Mannheim},
year = {2011}
}
@article{faucris.107820064,
abstract = {We propose a data-driven method for extracting a respiratory surrogate signal from SPECT list-mode data. The approach is based on dimensionality reduction with Laplacian Eigenmaps. By setting a scale parameter adaptively and adding a series of post-processing steps to correct polarity and normalization between projections, we enable fully-automatic operation and deliver a respiratory surrogate signal for the entire SPECT acquisition. We validated the method using 67 patient scans from three acquisition types (myocardial perfusion, liver shunt diagnostic, lung inhalation/perfusion) and an Anzai pressure belt as a gold standard. The proposed method achieved a mean correlation against the Anzai of 0.81 ± 0.17 (median 0.89). In a subsequent analysis, we characterize the performance of the method with respect to count rates and describe a predictor for identifying scans with insufficient statistics. To the best of our knowledge, this is the first large validation of a data-driven respiratory signal extraction method published thus far for SPECT, and our results compare well with those reported in the literature for such techniques applied to other modalities such as MR and PET.},
author = {Sanders, James Chester and Ritt, Philipp and Kuwert, Torsten and Vija, A. Hans and Maier, Andreas},
doi = {10.1109/TMI.2016.2576899},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
note = {EVALuna2:13863},
pages = {2425-2435},
peerreviewed = {Yes},
title = {{Fully} {Automated} {Data}-{Driven} {Respiratory} {Signal} {Extraction} {From} {SPECT} {Images} {Using} {Laplacian} {Eigenmaps}},
volume = {35},
year = {2016}
}
@inproceedings{faucris.113161884,
author = {Wels, Michael and Huber, Martin and Hornegger, Joachim},
booktitle = {3D Segmentation in the Clinic - A Grand Challenge MICCAI 2007 Workshop Proceedings},
date = {2007-10-29/2007-11-02},
editor = {Heimann Tobias, Styner Martin, van Ginneken Bram},
faupublication = {yes},
pages = {19-27},
peerreviewed = {unknown},
title = {{Fully} {Automated} {Knowledge}-{Based} {Segmentation} of the {Caudate} {Nuclei} in 3-{D} {MRI}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Wels07-FAK.pdf},
venue = {Brisbane, QLD},
year = {2007}
}
@article{faucris.120202324,
abstract = {This paper addresses segmentation of multiple sclerosis lesions in multispectral 3-D brain MRI data. For this purpose, we propose a novel fully automated segmentation framework based on probabilistic boosting trees, which is a recently introduced strategy for supervised learning. By using the context of a voxel to be classified and its transformation to an overcomplete set of Haar-like features, it is possible to capture class specific characteristics despite the well-known drawbacks of MR imaging. By successively selecting and combining the most discriminative features during ensemble boosting within a tree structure, the overall procedure is able to learn a discriminative model for voxel classification in terms of posterior probabilities. The final segmentation is obtained after refining the preliminary result by stochastic relaxation and a standard level set approach. A quantitative evaluation within a leave-one-out validation shows the applicability of the proposed method. © 2008 Pleiades Publishing, Ltd.},
author = {Wels, Michael and Huber, M. and Hornegger, Joachim},
doi = {10.1134/S1054661808020235},
faupublication = {yes},
journal = {Pattern Recognition and Image Analysis},
note = {UnivIS-Import:2015-04-16:Pub.2008.tech.IMMD.IMMD5.fullya},
pages = {347-350},
peerreviewed = {unknown},
title = {{Fully} automated segmentation of multiple sclerosis lesions in multispectral {MRI}},
volume = {18},
year = {2008}
}
@article{faucris.120325744,
author = {Maier, Andreas and Nöth, Elmar and Batliner, Anton and Nkenke, Emeka and Schuster, Maria},
faupublication = {yes},
journal = {Informatica},
pages = {477-482},
peerreviewed = {Yes},
title = {{Fully} {Automatic} {Assessment} of {Speech} of {Children} with {Cleft} {Lip} and {Palate}},
url = {http://ai.ijs.si/informatica/},
year = {2006}
}
@inproceedings{faucris.232522521,
abstract = {Recently, deep learning (DL) found its way to interventional X-ray skin dose estimation. While its performance was found to be acceptable, even more accurate results could be achieved if more data sets were available for training. One possibility is to turn to computed tomography (CT) data sets. Typically, computed tomography (CT) scans can be mapped to tissue labels and mass densities to obtain training data. However, care has to be taken to make sure that the different clinical settings are properly accounted for. First, the interventional environment is characterized by wide variety of table setups that are significantly different from the typical patient tables used in conventional CT. This cannot be ignored, since tables play a crucial role in sound skin dose estimation in an interventional setup, e.,g., when the X-ray source is directly underneath a patient (posterior-anterior view). Second, due to interpolation errors, most CT scans do not facilitate a clean segmentation of the skin border. As a solution to these problems, we applied connected component labeling (CCL) and Canny edge detection to (a) robustly separate the patient from the table and (b) to identify the outermost skin layer. Our results show that these extensions enable fully-automatic, generalized pre-processing of CT scans for further simulation of both skin dose and corresponding X-ray projection},
author = {Roser, Philipp and Birkhold, Annette and Preuhs, Alexander and Stimpel, Bernhard and Syben, Christopher and Strobel, Norbert and Kowarschik, Markus and Fahrig, Rebecca and Maier, Andreas},
booktitle = {Informatik Aktuell
Bildverarbeitung für die Medizin 2020
Algorithmen - Systeme - Anwendungen},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}26},
faupublication = {yes},
keywords = {X-ray simulation; Computed tomography; Data preparation},
pages = {1-6},
peerreviewed = {Yes},
title = {{Fully}-automatic {CT} data preparation for interventional {X}-ray skin dose simulation},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.107005404,
author = {Müller, Kerstin and Berger, Martin and Choi, Jang-Hwan and Datta, Sanjit and Gehrisch, Sonja and Moore, Teri and Marks, Michael P and Maier, Andreas and Fahrig, Rebecca},
booktitle = {Proceedings of the 13th Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {no},
note = {UnivIS-Import:2015-07-08:Pub.2015.tech.IMMD.IMMD5.fullya{\_}7},
pages = {534-537},
peerreviewed = {Yes},
title = {{Fully} {Automatic} {Head} {Motion} {Correction} for {Interventional} {C}-arm {Systems} using {Fiducial} {Markers}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Mueller15-FAH.pdf},
venue = {Newport, RI, USA},
year = {2015}
}
@inproceedings{faucris.121435204,
author = {Seeger, Christoph and Brost, Alexander and Dobre, Mircea and Fischbein, Nancy and Han, Zhaoying and Maclaren, Julian and Vos, Sjoerd and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the 21st Annual meeting of the ISMRM},
date = {2013-04-20/2013-04-26},
editor = {ISMRM},
faupublication = {yes},
pages = {1146.0},
title = {{Fully} {Automatic} {Maximum} {Intensity} {Projections} of {Regions} of {Interest} in {Magnetic} {Resonance} {Angiograms}},
venue = {Salt Lake City, UT},
year = {2013}
}
@phdthesis{faucris.233908907,
abstract = {The leading cause of death worldwide are cardiovascular diseases. In addition, the
number of patients suffering from heart failure is rising. The underlying cause of heart failure is often a myocardial infarction. For diagnosis in clinical routine, cardiac magnetic resonance imaging is used, as it provides information about morphology, blood flow, perfusion, and tissue characterization. In more detail, the analysis of the
tissue viability is very important for diagnosis, procedure planning, and guidance, i.e., for implantation of a bi-ventricular pacemaker. The clinical gold standard for
the viability assessment is 2-D late gadolinium enhanced magnetic resonance imaging
(LGE-MRI). In the last years, the imaging quality continuously improved and LGE-MRI was extended to a 3-D whole heart scan. This scan guarantees an accurate
quantification of the myocardium to the extent of myocardial scarring.
The main challenge arises in the accurate segmentation and analysis of such images. In this work, novel methods for the segmentation of the LGE-MRI data sets, both 2-D and 3-D, are proposed. One important goal is the direct segmentation of the LGE-MRI and the independence of an anatomical scan to avoid errors from the anatomical scan contour propagation. For the 2-D LGE-MRI segmentation, the short
axis stack of the left ventricle (LV) is used. First, the blood pool is detected and a rough outline is maintained by a morphological active contours without edges approach. Afterwards, the endocardial and epicardial boundary is estimated by either a filter or learning based method in combination with a minimal cost path search in polar space. For the endocardial contour refinement, an additional scar exclusion step is added. For the 3-D LGE-MRI, the LV is detected within the whole heart scan. In the next step, the short axis view is estimated using principal component analysis. For the endocardial and epicardial boundary estimation also a filter based or learning
based approach can be applied in combination with dynamic programming in polar
space. Furthermore, because of the high resolution also the papillary muscles are
segmented.
In addition to the fully automatic LV segmentation approaches, a generic semi-
automatic method based on Hermite radial basis function interpolation is introduced in combination with a smart brush. Effective interactions with less number of equations accelerate the performance and therefore, a real-time and an intuitive, interactive segmentation of 3-D objects is supported effectively.
After the segmentation of the left ventricle’s myocardium, the scar tissue is quantified. In this thesis, three approaches are investigated. The full-width-at-half-max algorithm and the x-standard deviation methods are implemented in a fully automatic manner. Furthermore, a texture based scar classification algorithm is introduced.
Subsequently, the scar tissue can be visualized, either in 3-D as a surface mesh or in 2-D projected onto the 16 segment bull’s eye plot of the American Heart Association.
However, for precise procedure planning and guidance, the information about the scar transmurality is very important. Hence, a novel scar layer visualization is introduced.
Therefore, the scar tissue is divided into three layers depending on the location of
the scar within the myocardium. With this novel visualization, an easy distinction between endocardial, mid-myocardial, or epicardial scar is possible. The scar layers
can also be visualized in 3-D as surface meshes or in 2-D projected onto the 16
segment bull’s eye plot.
2 and wide field 10 × 10 mm2 volumetric OCT data were generated using two volumetric scans, each obtained in 1.4 seconds. High definition 10 mm and 6 mm B-scans were obtained by averaging and registering 25 B-scans obtained over the same position in 0.57 seconds. One of the advantages of volumetric OCT data is the generation of en face OCT images with arbitrary cross sectional B-scans registered to fundus features. This technology should enable screening applications to identify early retinal disease, before irreversible vision impairment or loss occurs. Handheld OCT technology also promises to enable applications in a wide range of settings outside of the traditional ophthalmology or optometry clinics including pediatrics, intraoperative, primary care, developing countries, and military medicine. © 2013 Optical Society of America.},
author = {Lu, Chen D. and Kraus, Martin and Potsaid, Benjamin and Liu, Jonathan J. and Choi, WooJhon and Jayaraman, Vijaysekhar and Cable, Alex E. and Hornegger, Joachim and Duker, Jay S. and Fujimoto, James G.},
doi = {10.1364/BOE.5.000293},
faupublication = {yes},
journal = {Biomedical Optics Express},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.handhe},
pages = {293-311},
peerreviewed = {Yes},
title = {{Handheld} ultrahigh speed swept source optical coherence tomography instrument using a {MEMS} scanning mirror},
volume = {5},
year = {2014}
}
@article{faucris.112503204,
author = {Riess, Christian and Unberath, Mathias and Naderi Boldaji, Farzad and Pfaller, Sven and Stamminger, Marc and Angelopoulou, Elli},
doi = {10.1007/s11042-016-3655-0},
faupublication = {yes},
journal = {Multimedia Tools and Applications},
pages = {4747-4764},
peerreviewed = {Yes},
title = {{Handling} multiple materials for exposure of digital forgeries using 2-{D} lighting environments},
volume = {76},
year = {2017}
}
@inproceedings{faucris.219351593,
abstract = {Handwritten text recognition (HTR) is a difficult research problem. In
particular for historical documents, this task is hard as handwriting
style, orthography, and text quality pose significant challenges.
Creation of a single multi-purpose HTR system seems to be out of reach
for current state-of-the-art systems. Therefore, we are interested in
fast creation of specialized HTR systems for a particular set of
historical documents. Still manual annotation by historical experts is
expensive and can often not be applied at a large scale. Instead, we use
the transcripts of naive transcribers that may still contain a
significant amount of errors. In this paper, we propose to fuse the
recognized word-chain with naive transcribers that can be obtained in a
cost-effective way. For the actual fusion, we rely on a word-level
approach, the so-called Recognizer Output Voting Error Reduction
(ROVER). Results indicate that we are able to reduce the Word Error Rate
(WER) of an HTR system trained with only few pages from 2.6 % to 19.2%
with two additional transcribers with 25.1% and 27.1% WER each. This
performance is already close to current state-of-the-art systems trained
with significantly more dat},
author = {Christlein, Vincent and Nicolaou, Anguelos and Schlauwitz, Thorsten and Späth, Sabrina and Herbers, Klaus and Maier, Andreas},
doi = {10.18420/infdh2018-13},
editor = {Burghardt, Manuel; Müller-Birn, Claudia},
faupublication = {yes},
keywords = {handwritten text recognition; line fusion; naive transcribers; Nürnberg; Briefbücher; 15. Jahrhundert},
pages = {1-8},
peerreviewed = {unknown},
title = {{Handwritten} {Text} {Recognition} {Error} {Rate} {Reduction} in {Historical} {Documents} using {Naive} {Transcribers}},
url = {https://dl.gi.de/handle/20.500.12116/16993},
year = {2018}
}
@article{faucris.247769848,
abstract = {Magnetic resonance imaging (MRI) systems and their continuous, failure-free operation is crucial for high-quality diagnostics and seamless workflows. One important hardware component is coils as they detect the magnetic signal. Before every MRI scan, several image features are captured which represent the used coil’s condition. These image features recorded over time are used to train machine learning models for classification of coils into normal and broken coils for faster and easier maintenance. The state-of-the-art techniques for classification of time series involve different kinds of neural networks. We leveraged sequential data and trained three models, long short-term memory (LSTM), fully convolutional network (FCN), and the combination of those called LSTMFCN as reported by Karim et al. (IEEE access 6:1662–1669, 2017). We found LSTMFCN to combine the benefits of LSTM and FCN. Thus, we achieved the highest F1-score of 87.45% and the highest accuracy of 99.35% using LSTMFCN. Furthermore, we tackled the high data imbalance of only 2.1% data collected from broken coils by training a Gaussian process (GP) regressor and adding predicted sequences as artificial samples to our broken labelled data. Adding 40 synthetic samples increased the classification results of LSTMFCN to an F1-score of 92.30% and accuracy of 99.83%. Thus, MRI head/neck coils can be classified normal or broken by training a LSTMFCN on image features, successfully. Augmenting the data using GP-generated samples can improve the performance even further.},
author = {Rücker, Nadine and Pflueger, Lea and Maier, Andreas},
doi = {10.1007/s10278-020-00411-4},
faupublication = {yes},
journal = {Journal of Digital Imaging},
keywords = {Gaussian process regression; Hardware failure prediction; Machine learning; Time series classification},
note = {CRIS-Team Scopus Importer:2021-01-15},
peerreviewed = {Yes},
title = {{Hardware} {Failure} {Prediction} on {Imbalanced} {Times} {Series} {Data}: {Generation} of {Artificial} {Data} {Using} {Gaussian} {Process} and {Applying} {LSTMFCN} to {Predict} {Broken} {Hardware}},
year = {2021}
}
@inproceedings{faucris.120332784,
address = {Berlin},
author = {Siegl, Christian and Hofmann, Hannes and Keck, Benjamin and Prümmer, Marcus and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2011},
date = {2011-03-20/2011-03-22},
doi = {10.1007/978-3-642-19335-4{\_}92},
editor = {Handels Heinz, Ehrhardt Jan, Deserno Thomas Martin, Meinzer Hans-Peter, Tolxdorff Thomas},
faupublication = {yes},
pages = {449-453},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Hardware}-unabhängige {Beschleunigung} von {Medizinischer} {Bildverarbeitung} mit {OpenCL}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Siegl11-HBV.pdf},
venue = {Lübeck},
year = {2011}
}
@article{faucris.238796733,
abstract = {Nowadays, the accessibility of digitized historical documents is extremely important to facilitate fast and efficient retrieval of historical information and knowledge extraction from such data. To provide such functionality, it is necessary to convert document images into plain text using optical character recognition (OCR). Many OCR related methods and tools have been proposed, however, they are often too complicated for a standard user, some important parts are missing or they are not available in free versions. Therefore, this paper describes a complex and flexible web framework for historical document manipulation and analysis with the main focus on OCR. The framework contains eight modules to facilitate three main tasks: image pre-processing and segmentation, creation of data for OCR model training and the OCR itself. This framework is freely available for non commercial purposes. We have experimentally evaluated this framework on real data and we have shown that this system is efficient and can save human labour in the process of annotated data preparation. Moreover, we have reached state-of-the-art OCR results.
Quantification of mitotic figures (MF) within the tumor areas of highest mi- totic density is the most important prognostic parameter for outcome assessment of many tumor types. However, high intra- and inter-rater variability results from difficulties in individual MF identification and region of interest (ROI) se- lection due to uneven MF distribution. Deep learning-based algorithms for MF detection and ROI selection are very promising methods to overcome these lim- itations. As of today, few datasets of human mammary carcinoma are available. They provide labels only in small image sections of the whole slide image (WSI) and include up to 1,552 MF annotations.
Our research group has developed a large-scale, open access dataset with annotations for MF in 32 cases of canine cutaneous mast cell tumors. Entire WSI were completely labeled by two pathologists resulting in 44,800 MF anno- tations. Of those, 5.5% were initially missed by expert WSI screening and added through a deep learning-based pipeline for identification of potential candidates.
For algorithmic validation, we used a two-stage approach (RetinaNet followed by cell classificator), which yielded a F1 score of 0.820. Through the algorith- m-aided completion of the dataset we were able to increase the F1 score by 3.4 percentage points. Influence of the size of the dataset was assessed by stepwise reduction of the number of WSI and size (in high power fields, HPF) of the image sections used for training. With the number of included images, the F1 score moderately increased (3 WSI: 0.772; 6 WSI: 0.804; 12 WSI: 0.817; 21 WSI: 0.820). The size of the tumor area in training (ROI selected by an expert) had significant effects on the F1 score (5 HPF: 0.583; 10 HPF: 0.676; 50 HPF: 0.770; complete WSI: 0.820), which was determined in entire WSI of the test set. We emphasize the benefit of appropriate dataset size and complete WSI labeling.
},
address = {Wiesbaden},
author = {Bertram, Christof A. and Aubreville, Marc and Marzahl, Christian and Maier, Andreas and Klopfleisch, Robert},
booktitle = {Bildverarbeitung für die Medizin 2020},
date = {2020-03-17/2020-03-19},
doi = {10.1007/978-3-658-29267-6{\_}65},
editor = {Tolxdorff T., Deserno T., Handels H., Maier A., Maier-Hein K., Palm C.},
faupublication = {yes},
isbn = {978-3-658-29266-9},
keywords = {mitotic figures; tumor diagnostics; open data; big data; canine cutaneous mast cell tumor},
pages = {293-293},
peerreviewed = {Yes},
publisher = {Springer Vieweg},
title = {{How} {Big} is {Big} {Enough}?: {A} {Large}-{Scale} {Histological} {Dataset} of {Mitotic} {Figures}},
url = {https://link.springer.com/content/pdf/10.1007/978-3-658-29267-6{\_}65.pdf},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.107953384,
author = {Hönig, Florian Thomas and Batliner, Anton and Weilhammer, Karl and Nöth, Elmar},
booktitle = {Proceedings of the INTERSPEECH 2010 Satellite Workshop on Second Language Studies: Acquisition, Learning, Education and Technology (L2WS)/Speech and Language Technology in Education (SLaTE)},
date = {2010-09-22/2010-09-24},
editor = {AESOP SLaTE NICT & LASS},
faupublication = {yes},
pages = {-},
title = {{How} {Many} {Labellers}? {Modelling} {Inter}-{Labeller} {Agreement} and {System} {Performance} for the {Automatic} {Assessment} of {Non}-{Native} {Prosody}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Hoenig10-HML.pdf},
venue = {Tokyo},
year = {2010}
}
@inproceedings{faucris.113244824,
author = {Hönig, Florian Thomas and Batliner, Anton and Nöth, Elmar},
booktitle = {Proceedings of the ISCA Special Interest Group on Speech and Language Technology in Education},
date = {2011-08-24/2011-08-26},
editor = {Helmer Strik, Catia Cucchiarini, Rodolfo Delmonte, Rocco Tripodi},
faupublication = {yes},
pages = {no pagination},
title = {{How} {Many} {Labellers} {Revisited} - {Naives}, {Experts}, and {Real} {Experts}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Hoenig11-HML.pdf},
venue = {Venice},
year = {2011}
}
@inproceedings{faucris.110636064,
author = {Hönig, Florian Thomas and Batliner, Anton and Nöth, Elmar},
booktitle = {Workshop on Speech and Language Technology in Education},
faupublication = {yes},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.howman{\_}9},
pages = {1-4},
title = {{How} {Many} {Speakers}, {How} {Many} {Texts} - {The} {Automatic} {Assessment} of {Non}-{Native} {Prosody}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Hoenig15-HMS.pdf},
venue = {Leipzig, Germany},
year = {2015}
}
@incollection{faucris.221673718,
abstract = {The paper explains and illustrates how the concept of word classes can
be added to the widely used open-source speech recognition toolkit
Kaldi. The suggested extensions to existing Kaldi recipes are limited to
the word-level grammar (G) and the pronunciation lexicon (L)
models. The implementation to modify the weighted finite state
transducers employed in Kaldi makes use of the OpenFST library. In
experiments on small and mid-sized corpora with vocabulary sizes of
1.5 K and 5.5 K respectively a slight improvement of the word error rate
is observed when the approach is tested with (hand-crafted) word
classes. Furthermore it is shown that the introduction of sub-word unit
models for open word classes can help to robustly detect and classify
out-of-vocabulary words without impairing word recognition accurac},
address = {Cham},
author = {Horndasch, Axel and Kaufhold, Caroline and Nöth, Elmar},
booktitle = {Text, Speech, and Dialogue. TSD 2016},
doi = {10.1007/978-3-319-45510-5{\_}56},
editor = {Sojka P., Horák A., Kopeček I., Pala K.},
faupublication = {yes},
isbn = {978-3-319-45509-9},
keywords = {OOV detection and classification; Kaldi speech recognition toolkit; Word classes},
pages = {486-494},
peerreviewed = {Yes},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
title = {{How} to add word classes to the {Kaldi} speech recognition toolkit},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Horndasch16-HTA.pdf},
volume = {9924},
year = {2016}
}
@misc{faucris.208852713,
author = {Gloe, Thomas and Kirchner, Matthias and Riess, Christian},
faupublication = {yes},
peerreviewed = {automatic},
title = {{How} we learned to stop worrying about content and love the metadata},
url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.714.5583&rep=rep1&type=pdf},
year = {2013}
}
@inproceedings{faucris.251751985,
abstract = {Twitter sentiment analysis, which often focuses on predicting the polarity of tweets, has attracted increasing attention over the last years, in particular with the rise of deep learning (DL). In this paper, we propose a new task: predicting the predominant sentiment among (first-order) replies to a given tweet. Therefore, we created RETwEET, a large dataset of tweets and replies manually annotated with sentiment labels. As a strong baseline, we propose a two-stage DL-based method: first, we create automatically labeled training data by applying a standard sentiment classifier to tweet replies and aggregating its predictions for each original tweet; our rationale is that individual errors made by the classifier are likely to cancel out in the aggregation step. Second, we use the automatically labeled data for supervised training of a neural network to predict reply sentiment from the original tweets. The resulting classifier is evaluated on the new ReTweeT dataset, showing promising results, especially considering that it has been trained without any manually labeled data. Both the dataset and the baseline implementation are publicly available.
The
C-arm CT X-ray acquisition process is a common modality in medical
imaging. After image formation, anatomical structures can be extracted
via segmentation. Interactive segmentation methods bear the advantage of
a dynamically adjustable trade-off between time and achieved
segmentation quality for the object of interest w. r. t. fully automated
approaches. The segmentation’s quality can be measured in terms of the
Dice coefficient with the ground truth segmentation image. A user’s
interaction traditionally consist of drawing pictorial hints on an
overlay image to the acquired image data via a graphical user interface
(UI). The quality of a segmentation utilizing a set of drawn seeds
varies depending on the location of the seed points in the image.
In this paper, we (1) investigate the influence of seed point location
on segmentation quality and (2) propose an approximation framework for
ideal seed placements utilizing an extension of the well established
GrowCut segmentation algorithm and (3) introduce a user interface for
the utilization of the suggested seed point locations.
An
extensive evaluation of the predictive power of seed importance is
conducted from hepatic lesion input images. As a result, our approach
suggests seed points with a median of 72.5% of the ideal seed points’
associated Dice scores, which is an increase of 8.4% points to sampling
the seed location at random.
},
author = {Amrehn, Mario and Strumia, Maddalena and Steidl, Stefan and Horz, Tim and Kowarschik, Markus and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2018},
date = {2018-03-11/2018-03-13},
doi = {10.1007/978-3-662-56537-7{\_}60},
faupublication = {yes},
isbn = {978-3-662-56536-0},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.ideals{\_}4},
pages = {210-215},
peerreviewed = {Yes},
publisher = {Springer Vieweg},
title = {{Ideal} {Seed} {Point} {Location} {Approximation} for {GrowCut} {Interactive} {Image} {Segmentation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Amrehn18-ISP.pdf},
venue = {Erlangen},
year = {2018}
}
@article{faucris.226028143,
abstract = {Fast identification of failure root causes is a major task in minimizing rejects in manufacturing. Due to increasing complexity of products and supply chains many interdependencies affect the final product quality. As knowledge about every possible interdependence is hardly held by individuals, data analysis strategies are required to evaluate captured information. Hence, we propose a root cause identification method for determining the main influencing factors on end products failing end of line tests. Additionally, graphical representation of calculation results in spectrograms similar to audio signals facilitates human interpretation. The evaluation of the proposed method on the basis of a use case proves the applicability in a real scenario. The method is able to identify the root cause for rejects within short periods of time. In this specific case it shortened the analysis time by a factor of about 50. In the future, it empowers smart production systems to automatically identify failure root causes and to take countermeasures like adjusting process parameters.
This paper analyses the effects of including pathological speech during the pre-training of wav2vec2.0, where quantized speech representations are learned, on the performance of a fine-tuned pathology detection task. We show that this architecture can be successfully fine-tuned for cleft lip and palate (CLP) detection, where the best-performing model yields an F1-score of
when pre-trained on healthy speech only. Our experiments show, that including pathological speech during pre-training drastically degrades the performance on detection of the same pathology for which it was fine-tuned. The worst-performing model was pre-trained exclusively on CLP speech, resulting in an F1-score of
. Whilst performed experiments only focus on CLP, the magnitude of the results suggest, that other pathologies will also follow this tren},
address = {Cham},
author = {Weise, Tobias and Maier, Andreas and Demir, Kubilay and Pérez Toro, Paula Andrea and Arias Vergara, Tomás and Heismann, Björn and Nöth, Elmar and Schuster, Maria and Yang, Seung Hee},
booktitle = {Text, Speech, and Dialogue},
date = {2023-09-04/2023-09-06},
doi = {10.1007/978-3-031-40498-6{\_}13},
editor = {Kamil Ekštein, František Pártl, Miloslav Konopík},
faupublication = {yes},
isbn = {9783031404979},
keywords = {wav2vec2.0; self-supervised learning; transformer; pathological speech},
pages = {141-153},
peerreviewed = {unknown},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
title = {{Impact} of {Including} {Pathological} {Speech} in {Pre}-training on {Pathology} {Detection}},
venue = {Pilsen},
volume = {14102},
year = {2023}
}
@inproceedings{faucris.224610863,
abstract = {Automatic Age estimation using speech is a challenging problem. Among other things, the many influences that lead to a change in the voice make it difficult to estimate the exact age. Examples are the microphone used, the distance to this microphone or the sex of the speaker. Stable results can be achieved by extracting Mel-Frequency Cepstral Coefficients (MFCCs) from the speech signal and processing them into i‑vectors, classification and regression tools such as Support Vector Regression (SVR) can then be used for the age estimation from these features. An additional factor influencing the age estimation are speech or voice disorders of a speaker. Rarely is this impact assessed, resulting in systems that are not tailored to the needs of pathological speakers like Siri or Amazon echo. Another example are companies which use automatic age estimation to forward calls to persons of the same age as the caller. These systems are also adapted to the characteristics of healthy speakers. This paper examines the impacts of such pathologies on age estimation and assess the possibility of reducing their influence by using the Word Accuracy (WA) of the speakers. This measure gives information about the intelligibility of a speaker and should help to reduce the variance of the extracted features. The features with low variance should provide more stable results in the age estimation.
To achieve this, we compare the results of an age estimation for four different groups of speakers. All speakers at once, only pathological speakers, only healthy speakers and training the SVR with healthy speakers while testing with pathological speakers. Each of these groups are further separated by the WA of the speaker},
address = {Rostock},
author = {Schwinn, Leo and Haderlein, Tino and Nöth, Elmar and Maier, Andreas},
booktitle = {Fortschritte der Akustik - DAGA 2019},
date = {2019-03-18/2019-03-21},
edition = {1},
editor = {Deutsche Gesellschaft für Akustik e.V.},
faupublication = {yes},
isbn = {978-3-939296-14-0},
keywords = {age estimation; speech recognition; speaker characteristics},
note = {UnivIS-Import:2019-08-15:Pub.2019.tech.IMMD.IMMD5.impact},
pages = {939-942},
peerreviewed = {No},
publisher = {Deutsche Gesellschaft für Akustik e.V. (DEGA)},
title = {{Impact} of {Pathologies} on {Automatic} {Age} {Estimation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Schwinn19-IOP.pdf},
venue = {Rostock},
volume = {1},
year = {2019}
}
@inproceedings{faucris.203721753,
abstract = {Model-based
iterative reconstruction is a promising approach to achieve dose reduction
without affecting image quality in diagnostic X-ray computed tomography. In the
problem formulation, it is common to enforce non-negative values, which is motivated
by physics but narrows down the choice of optimization algorithm. In this work,
we report on experiments assessing the impact of the non-negativity constraint
on image quality and reconstruction speed. The assessment is performed under
eight scenarios that challenge the usefulness of the constraint. These include
reconstructions from full and sparse view sampling, with quadratic or
edge-preserving regularization, for two different objects. Our results show that
improvements due to the nonnegativity constraint are strongly
scenario-dependent, and likely negligible for conventional full view CT
imaging. This implies that for specific reconstructions, the non-negativity
constraint could be disregarded to simplify the optimization proble},
author = {Haase, Viktor and Hahn, Katharina and Schöndube, Harald and Stierstorfer, Karl and Noo, Frédéric},
booktitle = {Proceedings of the Fifth International Conference on Image Formation in X-Ray Computed Tomography (CT Meeting)},
date = {2018-05-20/2018-05-23},
doi = {10.1002/mp.13702},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.impact{\_}4},
pages = {339-343},
peerreviewed = {unknown},
title = {{Impact} of the {Non}-{Negativity} {Constraint} in {Model}-{Based} {Iterative} {Reconstruction} from {CT} {Data}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Haase18-IOT.pdf},
venue = {Salt Lake City, UT},
year = {2018}
}
@article{faucris.230310597,
abstract = {Model-based iterative reconstruction is a promising approach to achieve dose reduction without affecting image quality in diagnostic x-ray computed tomography (CT). In the problem formulation, it is common to enforce non-negative values to accommodate the physical non-negativity of x-ray attenuation. Using this a priori information is believed to be beneficial in terms of image quality and convergence speed. However, enforcing non-negativity imposes limitations on the problem formulation and the choice of optimization algorithm. For these reasons, it is critical to understand the value of the non-negativity constraint. In this work, we present an investigation that sheds light on the impact of this constraint.
We primarily focus our investigation on the examination of properties of the converged solution. To avoid any possibly confounding bias, the reconstructions are all performed using a provably converging algorithm started from a zero volume. To keep the computational cost manageable, an axial CT scanning geometry with narrow collimation is employed. The investigation is divided into five experimental studies that challenge the non-negativity constraint in various ways, including noise, beam hardening, parametric choices, truncation, and photon starvation. These studies are complemented by a sixth one that examines the effect of using ordered subsets to obtain a satisfactory approximate result within 50 iterations. All studies are based on real data, which come from three phantom scans and one clinical patient scan. The reconstructions with and without the non-negativity constraint are compared in terms of image similarity and convergence speed. In select cases, the image similarity evaluation is augmented with quantitative image quality metrics such as the noise power spectrum and closeness to a known ground truth.
For cases with moderate inconsistencies in the data, associated with noise and bone-induced beam hardening, our results show that the non-negativity constraint offers little benefit. By varying the regularization parameters in one of the studies, we observed that sufficient edge-preserving regularization tends to dilute the value of the constraint. For cases with strong data inconsistencies, the results are mixed: the constraint can be both beneficial and deleterious; in either case, however, the difference between using the constraint or not is small relative to the overall level of error in the image. The results with ordered subsets are encouraging in that they show similar observations. In terms of convergence speed, we only observed one major effect, in the study with data truncation; this effect favored the use of the constraint, but had no impact on our ability to obtain the converged solution without constraint.
Our results did not highlight the non-negativity constraint as being strongly beneficial for diagnostic CT imaging. Altogether, we thus conclude that in some imaging scenarios, the non-negativity constraint could be disregarded to simplify the optimization problem or to adopt other forward projection models that require complex optimization machinery to be used together with non-negativity.
},
author = {Haase, Viktor and Hahn, Katharina and Schöndube, Harald and Stierstorfer, Karl and Maier, Andreas and Noo, Frédéric},
doi = {10.1002/mp.13702},
faupublication = {yes},
journal = {Medical Physics},
keywords = {model-based iterative reconstruction; non-negativity constraint; penalized weighted least-squares; positivity constraint; x-ray computed tomography},
pages = {e835-e854},
peerreviewed = {Yes},
title = {{Impact} of the non-negativity constraint in model-based iterative reconstruction from {CT} data},
url = {https://aapm.onlinelibrary.wiley.com/doi/full/10.1002/mp.13702},
volume = {46},
year = {2019}
}
@inproceedings{faucris.260286401,
address = {CLARE},
author = {Dürrbeck, Christopher and Pflaum, L. and Schulz, M. and Kallis, Karoline and Geimer, Tobias and Abu-Hossin, N. and Strnad, Vratislav and Maier, Andreas and Fietkau, Rainer and Bert, Christoph},
booktitle = {RADIOTHERAPY AND ONCOLOGY},
doi = {10.1016/s0167-8140(21)06313-1},
faupublication = {yes},
note = {CRIS-Team WoS Importer:2021-06-18},
pages = {S76-S77},
peerreviewed = {unknown},
publisher = {ELSEVIER IRELAND LTD},
title = {{Implant}-based {CT} estimation towards adaptive breast brachytherapy},
year = {2021}
}
@article{faucris.207562558,
author = {Horn, Florian and Leghissa, Martino and Käppler, Sebastian and Pelzer, Georg and Rieger, Jens and Seifert, Maria and Wandner, Johannes and Weber, Thomas and Michel, Thilo and Riess, Christian and Anton, Gisela},
doi = {10.1038/s41598-018-19482-z},
faupublication = {yes},
journal = {Scientific Reports},
peerreviewed = {Yes},
title = {{Implementation} of a {Talbot}-{Lau} {Interferometer} in a {Clinical}-like {C}-{Arm} {Setup}: {A} {Feasibility} {Study}},
url = {https://www.nature.com/articles/s41598-018-19482-z},
volume = {8},
year = {2018}
}
@inproceedings{faucris.121218284,
abstract = {In most of today's commercially available cone-beam CT scanners, the well known FDK method is used for solving the 3D reconstruction task. The computational complexity of this algorithm prohibits its use for many medical applications without hardware acceleration. The brand-new Cell Broadband Engine Architecture (CBEA) with its high level of parallelism is a cost-efficient processor for performing the FDK reconstruction according to the medical requirements. The programming scheme, however, is quite different to any standard personal computer hardware. In this paper, we present an innovative implementation of the most time-consuming parts of the FDK algorithm: filtering and back-projection. We also explain the required transformations to parallelize the algorithm for the CBEA. Our software framework allows to compute the filtering and back-projection in parallel, making it possible to do an on-the-fly-reconstruction. The achieved results demonstrate that a complete FDK reconstruction is computed with the CBEA in less than seven seconds for a standard clinical scenario. Given the fact that scan times are usually much higher, we conclude that reconstruction is finished right after the end of data acquisition. This enables us to present the reconstructed volume to the physician in real-time, immediately after the last projection image has been acquired by the scanning device.},
author = {Scherl, Holger and Körner, Mario and Hofmann, Hannes and Eckert, Wieland and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {Medical Imaging 2007: Physics of Medical Imaging},
doi = {10.1117/12.708754},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Implementation} of the {FDK} algorithm for cone-beam {CT} on the cell broadband engine architecture},
venue = {San Diego, CA},
volume = {6510},
year = {2007}
}
@inproceedings{faucris.121203324,
abstract = {We present an algorithm for the segmentation of the liver in 2-D computed tomography slice images. The basis for our algorithm is an implicit active shape model. In order to detect the liver boundary and guide the shape model deformation, a boundary classifier has been integrated into the implicit framework in a novel manner. The accuracy of the algorithm has been evaluated for 20 test cases including both normal and abnormal livers. © 2008 IEEE.},
author = {Wimmer, Andreas and Hornegger, Joachim and Soza, Grzegorz},
booktitle = {2008 19th International Conference on Pattern Recognition, ICPR 2008},
doi = {10.1109/ICPR.2008.4760968},
faupublication = {yes},
pages = {1 - 4},
peerreviewed = {unknown},
title = {{Implicit} active shape model employing boundary classifier},
venue = {Tampa, FL},
volume = {null},
year = {2008}
}
@inproceedings{faucris.120681484,
author = {Forman, Christoph and Aksoy, Murat and Straka, Matus and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the 18th Annual Meeting of ISMRM & ESMRMB},
date = {2010-05-01/2010-05-07},
editor = {International Society for Magnetic Resonance in Medicine (ISMRM)},
faupublication = {yes},
pages = {497.0},
peerreviewed = {unknown},
title = {{Improved} {Pose} {Detection} for {Single} {Camera} {Real}-{Time} {MR} {Motion} {Correction} {Using} a {Self}-{Encoded} {Marker}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Forman10-IPD.pdf},
venue = {Stockholm},
year = {2010}
}
@inproceedings{faucris.121473044,
author = {Aksoy, Murat and Forman, Christoph and Straka, Matus and Holdsworth, Samantha and Skare, Stefan and Santos, Juan and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the 18th Annual Meeting of ISMRM & ESMRMB},
date = {2010-05-01/2010-05-07},
editor = {International Society for Magnetic Resonance in Medicine (ISMRM)},
faupublication = {yes},
pages = {1613.0},
peerreviewed = {unknown},
title = {{Improved} {Prospective} {Optical} {Motion} {Correction} for {DTI} {Using} an {Extended}-{Field}-of-{View} and {Self}-{Encoded} {Marker}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Aksoy10-IPO.pdf},
venue = {Stockholm},
year = {2010}
}
@article{faucris.207562867,
author = {Käppler, Sebastian and Rieger, Jens and Pelzer, Georg and Horn, Florian and Michel, Thilo and Maier, Andreas and Anton, Gisela and Riess, Christian},
doi = {10.1117/1.JMI.4.3.034005},
faupublication = {yes},
journal = {Journal of Medical Imaging},
keywords = {phase contrast; phase stepping; moiré; reconstruction; Talbot-Lau},
peerreviewed = {Yes},
title = {{Improved} {Reconstruction} of {Phase}-{Stepping} {Data} for {Talbot}-{Lau} {X}-{Ray} {Imaging}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Kaeppler17-IRO.pdf},
volume = {4},
year = {2017}
}
@inproceedings{faucris.111385164,
author = {Zhong, Xia and Hoffmann, Matthias and Strobel, Norbert and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2016},
doi = {10.1007/978-3-662-49465-3{\_}7},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.improv{\_}0},
pages = {26-31},
peerreviewed = {unknown},
title = {{Improved} {Semi}-{Automatic} {Basket} {Catheter} {Reconstruction} from two {X}-{Ray} {Views}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Zhong16-ISB.pdf},
venue = {Charité - Universitätsmedizin Berlin},
year = {2016}
}
@inproceedings{faucris.118747244,
author = {Herbst, Magdalena and Schebesch, Frank and Berger, Martin and Fahrig, Rebecca and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the third international conference on image formation in x-ray computed tomography},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.improv{\_}5},
pages = {274-278},
title = {{Improved} trajectories in {C}-{Arm} computed tomography for non-circular fields of view},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Herbst14-ITI.pdf},
venue = {Salt Lake City, UT, USA},
year = {2014}
}
@inproceedings{faucris.107918624,
author = {Rothgang, Eva and Weiss, Clifford R. and Wacker, Frank and Hornegger, Joachim and Lorenz, Christine H. and Gilson, Wesley D.},
booktitle = {Proceedings of International Society for Magnetic Resonance in Medicine},
date = {2012-05-05/2012-05-11},
editor = {Pipe Jim},
faupublication = {yes},
pages = {1605.0},
peerreviewed = {unknown},
title = {{Improved} {Workflow} for {Freehand} {MR}-{Guided} {Percutaneous} {Needle} {Interventions}: {Methods} and {Validation}},
venue = {Melbourne},
year = {2012}
}
@inproceedings{faucris.229870783,
abstract = {X-ray images can show great variation in contrast and noise levels. In addition, important subject structures might be superimposed with surgical tools and implants. As medical image datasets tend to be of small size, these image characteristics are often under-represented. For the task of automated, learning-based segmentation of bone structures, this may lead to poor generalization towards unseen images and consequently limits practical application. In this work, we employ various data augmentation techniques that address X-ray-specific image characteristics and evaluate them on lateral projections of the femur bone. We combine those with data and feature normalization strategies that could prove beneficial to this domain. We show that instance normalization is a viable alternative to batch normalization and demonstrate that contrast scaling and the overlay of surgical tools and implants in the image domain can boost the representational capacity of available image data. By employing our best strategy, we can improve the average symmetric surface distance measure by 36.22},
address = {Wiesbaden},
author = {Kordon, Florian Johannes and Lasowski, Ruxandra and Swartman, Benedict and Franke, Jochen and Fischer, Peter and Kunze, Holger},
booktitle = {Bildverarbeitung für die Medizin 2019},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}24},
editor = {Handels H., Deserno T.M., Maier A., Maier-Hein K.H., Palm C., Tolxdorff T.},
faupublication = {yes},
isbn = {978-3-658-25326-4},
keywords = {X-Ray; Femur; Bone segmentation; Orthopedics},
pages = {104-109},
peerreviewed = {unknown},
publisher = {Springer Vieweg},
title = {{Improved} {X}-{Ray} {Bone} {Segmentation} by {Normalization} and {Augmentation} {Strategies}},
venue = {Lübeck},
year = {2019}
}
@inproceedings{faucris.121338624,
address = {Berlin},
author = {Placht, Simon and Schaller, Christian and Balda, Michael and Adelt, André and Ulrich, Christian and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin},
date = {2010-03-14/2010-03-16},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {177-181},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Improvement} and {Evaluation} of a {Time}-of-{Flight} based patient positioning system},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Placht10-IAE.pdf},
venue = {Aachen},
year = {2010}
}
@inproceedings{faucris.113231404,
author = {Bocklet, Tobias and Maier, Andreas and Nöth, Elmar and Eysholdt, Ulrich},
booktitle = {Proc. 2nd IEEE Workshop on Spoken Language Technologies (SLT 2010)},
date = {2010-12-12/2010-12-15},
editor = {IEEE},
faupublication = {yes},
pages = {247-252},
peerreviewed = {Yes},
title = {{Improvement} of a {Speech} {Recognizer} for {Standardized} {Medical} {Assessment} of {Children}'s {Speech} by {Integration} of {Prior} {Knowledge}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Bocklet10-IOA.pdf},
venue = {Berkeley, CA},
year = {2010}
}
@inproceedings{faucris.108215404,
author = {Wu, Meng and Maier, Andreas and Yang, Qiao and Fahrig, Rebecca},
booktitle = {The 13th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {yes},
note = {UnivIS-Import:2016-06-01:Pub.2015.tech.IMMD.IMMD5.improv},
pages = {248-251},
peerreviewed = {unknown},
title = {{Improve} {Path} {Seeking} {Accuracy} for {Iterative} {Reconstruction} {Using} the {Karush}-{Kuhn}-{Tucker} {Conditions}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Wu15-IPS.pdf},
venue = {New Port, Rhode Island, US},
year = {2015}
}
@inproceedings{faucris.118747464,
abstract = {Invasive cardiac angiography (catheterization) is still the standard in clinical practice for diagnosing coronary artery disease (CAD) but it involves a high amount of risk and cost. New generations of CT scanners can acquire high-quality images of coronary arteries which allow for an accurate identification and delineation of stenoses. Recently, computational fluid dynamics (CFD) simulation has been applied to coronary blood flow using geometric lumen models extracted from CT angiography (CTA). The computed pressure drop at stenoses proved to be indicative for ischemia-causing lesions, leading to non-invasive fractional flow reserve (FFR) derived from CTA. Since the diagnostic value of non-invasive procedures for diagnosing CAD relies on an accurate extraction of the lumen, a precise segmentation of the coronary arteries is crucial. As manual segmentation is tedious, time-consuming and subjective, automatic procedures are desirable. We present a novel fully-automatic method to accurately segment the lumen of coronary arteries in the presence of calcified and non-calcified plaque. Our segmentation framework is based on three main steps: boundary detection, calcium exclusion and surface optimization. A learning-based boundary detector enables a robust lumen contour detection via dense ray-casting. The exclusion of calcified plaque is assured through a novel calcium exclusion technique which allows us to accurately capture stenoses of diseased arteries. The boundary detection results are incorporated into a closed set formulation whose minimization yields an optimized lumen surface. On standardized tests with clinical data, a segmentation accuracy is achieved which is comparable to clinical experts and superior to current automatic methods. © 2014 SPIE.},
author = {Lugauer, Felix and Zhang, Jingdan and Zheng, Yefeng and Hornegger, Joachim and Kelm, B. Michael},
booktitle = {Proceedings SPIE},
date = {2014-02-16/2014-02-18},
doi = {10.1117/12.2043238},
faupublication = {yes},
keywords = {lumen segmentation; calicum suppression; CTA; CAD},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.improv{\_}60},
pages = {90343U-10},
title = {{Improving} {Accuracy} in {Coronary} {Lumen} {Segmentation} via {Explicit} {Calcium} {Exclusion}, {Learning}-based {Ray} {Detection} and {Surface} {Optimization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Lugauer14-IAI.pdf},
venue = {San Diego, California, USA},
volume = {9034},
year = {2014}
}
@inproceedings{faucris.108205944,
abstract = {
In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available. The acoustic models can be improved by interpolation with the well-trained models of a second recognizer from a different application scenario. In our case, we interpolate a children’s speech recognizer with a recognizer for adults’ speech. Each hidden Markov model has its ownset of interpolation partners; experiments were conducted with up to 50 partners. The interpolation weights are estimated automatically on a validation set using the EM algorithm. The word accuracy of the children’s speech recognizer could be improved from 74.6 % to 81.5 %. This is a relative improvement of almost 10 %.
},
address = {Berlin, Heidelberg, New York},
author = {Steidl, Stefan and Stemmer, Georg and Hacker, Christian and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Pattern Recognition, 25th DAGM Symposium, Magdeburg, Germany, September 2003, Proceedings},
date = {2003-09-10/2003-09-12},
editor = {Michaelis Bernd, Krell Gerald},
faupublication = {yes},
pages = {600-607},
peerreviewed = {Yes},
publisher = {Springer-Verlag},
title = {{Improving} {Children}'s {Speech} {Recognition} by {HMM} {Interpolation} with an {Adults}' {Speech} {Recognizer}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Steidl03-ICS.pdf},
venue = {Magdeburg},
year = {2003}
}
@inproceedings{faucris.224374001,
abstract = {The objective of this work is to evaluate different detrending methods in the quality of auditory evoked responses. We compared the average responses obtained by simply removing the DC level and the linear trend, and also the estimated trends using polynomials and Fourier models up to the 8
th order. Two quality measures were used to compare the results: The standard deviation ratio, as a measure of the signal-to-noise ratio, and the correlation coefficient between consecutive responses obtained under the same experimental conditions. The best results were obtained using a polynomial model of order 7.},
author = {Torres-Rodríguez, Idileisy and Ferrer Riesgo, Carlos Ariel and Velarde-Reyes, Ernesto and Taboada-Crispi, Alberto},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2018-11-19/2018-11-22},
doi = {10.1007/978-3-030-13469-3{\_}82},
editor = {Ruben Vera-Rodriguez, Julian Fierrez, Aythami Morales},
faupublication = {yes},
isbn = {9783030134686},
keywords = {CCR; Detrending; Ensemble averages; Evoked potential; SDR},
note = {CRIS-Team Scopus Importer:2019-08-13},
pages = {707-714},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{Improving} ensemble averaging by epoch detrending in evoked potentials},
venue = {Madrid},
volume = {11401 LNCS},
year = {2019}
}
@article{faucris.268130070,
abstract = {Multiorgan segmentation in computed tomography (CT) images is essential for a variety of clinical applications. Due to variations in acquisition protocols, clinical data differ in terms of soft-tissue contrast, noise, and artifacts. Devising automatic multiorgan segmentation approaches, which are generalized to data acquired using different CT protocols, are challenging and essential when conducting any multicenter/scanner analyses. In this study, we investigate the use of dual-energy CT (DECT) images to train a fully convolutional segmentation network which is generalized to CT images acquired using different protocols (i.e., at different energy levels and using a variety of reconstruction kernels) from different CT scanners. Furthermore, a novel image fusion approach in the frequency domain is proposed and compared to state-of-the-art fusion approaches, in terms of the segmentation quality achieved by the network. Overall, the experiments indicate that the generalization capability of the segmentation network is improved using DECT image fusion. The proposed fusion method outperforms all single-energy CT approaches. It provided a significant improvement in segmentation accuracy, ranging from 16.0% to 23.35% with p \leq 0.03. Furthermore, two image fusion methods statistically significantly improve segmentation quality in the abdominal organs compared to simply using all available DECT data.},
author = {Chen, Shuqing and Zhong, Xia and Dorn, Sabrina and Ravikumar, Nishant and Tao, Qinghua and Huang, Xiaolin and Lell, Michael and Kachelriess, Marc and Maier, Andreas},
doi = {10.1109/TRPMS.2021.3055199},
faupublication = {yes},
journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
keywords = {Data augmentation; deep learning; dual-energy computed tomography (DECT); multiorgan segmentation},
month = {Jan},
note = {CRIS-Team Scopus Importer:2022-01-14},
pages = {79-86},
peerreviewed = {Yes},
title = {{Improving} {Generalization} {Capability} of {Multiorgan} {Segmentation} {Models} {Using} {Dual}-{Energy} {CT}},
volume = {6},
year = {2022}
}
@inproceedings{faucris.108760344,
author = {Mualla, Firas and Schöll, Simon and Sommerfeldt, Björn and Steidl, Stefan and Buchholz, Rainer and Hornegger, Joachim},
booktitle = {IEEE 11th International Symposium on Biomedical Imaging (ISBI)},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.improv{\_}8},
pages = {927-930},
title = {{Improving} {Joint} {Learning} of {Suspended} and {Adherent} {Cell} {Detection} {Using} {Low}-{Pass} {Monogenic} {Phase} and {Transport} of {Intensity} {Equation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Mualla14-IJL.pdf},
venue = {Beijing},
year = {2014}
}
@inproceedings{faucris.109206724,
author = {Lugauer, Felix and Nickel, Dominik and Kannengiesser, Stephan A. R. and Barnes, Samuel and Holshouser, Barbara and Wetzl, Jens and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the 24th Annual Meeting of the ISMRM (ISMRM 2016)},
faupublication = {yes},
note = {UnivIS-Import:2017-01-09:Pub.2016.tech.IMMD.IMMD5.improv{\_}5},
pages = {3269},
peerreviewed = {unknown},
title = {{Improving} {Parameter} {Mapping} in {MRI} {Relaxometry} and {Multi}-{Echo} {Dixon} {Using} an {Automated} {Spectral} {Denoising}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Lugauer16-IPM.pdf},
venue = {Singapur},
year = {2016}
}
@inproceedings{faucris.107892224,
address = {-},
author = {Kompe, Ralf and Kießling, Andreas and Niemann, Heinrich and Nöth, Elmar and Batliner, Anton and Schachtl, Stefanie and Ruland, Tobias and Block, Hans Ulrich},
booktitle = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
date = {1997-04-21/1997-04-24},
editor = {IEEE},
faupublication = {yes},
pages = {811-814},
publisher = {IEEE Computer Society Press},
title = {{Improving} {Parsing} of {Spontaneous} {Speech} with the {Help} of {Prosodic} {Boundaries}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Kompe97-IPO.pdf},
venue = {Munich},
year = {1997}
}
@inproceedings{faucris.111100264,
author = {Unberath, Mathias and Aichert, André and Achenbach, Stephan and Maier, Andreas},
booktitle = {Proceedings of MICCAI CVII-STENT},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.improv{\_}1},
pages = {1-8},
peerreviewed = {unknown},
title = {{Improving} {Segmentation} {Quality} in {Rotational} {Angiography} {Using} {Epipolar} {Consistency}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Unberath16-ISQ.pdf},
venue = {Athens, Greece},
year = {2016}
}
@inproceedings{faucris.111151964,
author = {Schneider, Manuel and Lugauer, Felix and Nickel, Dominik and Dale, Brian M. and Kiefer, Berthold and Maier, Andreas and Bashir, Mustafa R.},
booktitle = {Proceedings of the 25th Annual Meeting of the ISMRM},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.improv{\_}0},
pages = {5195},
peerreviewed = {unknown},
title = {{Improving} the {Noise} {Propagation} {Behavior} of {Different} {Fatty} {Acid} {Quantification} {Techniques} using {Spectral} {Denoising}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Schneider17-ITN.pdf},
venue = {Honolulu},
year = {2017}
}
@inproceedings{faucris.118747684,
author = {Berger, Martin and Sembritzki, Klaus and Hornegger, Joachim and Bauer, Christina},
booktitle = {2014 IEEE International Symposium on Biomedical Imaging},
faupublication = {yes},
isbn = {978-1-4673-1961-4},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.increa{\_}2},
pages = {345-348},
title = {{Increasing} the {Credibility} of {MR} {Spectroscopy}-{Based} {Automatic} {Brain}-{Tumor} {Classification} {Systems}},
venue = {Beijing, China},
year = {2014}
}
@inproceedings{faucris.118075584,
abstract = {We present a new concept as well as the implementation of an FPGA-based reconfigurable platform, the Erlangen Slot Machine (ESM). One main advantage of this platform is the possibility for each module to access its periphery independent from its location through a programmable crossbar, allowing an unrestricted relocation of modules on the device. Furthermore, we propose different intermodule communication structures. © 2005 IEEE.},
author = {Ahmadinia, Ali and Bobda, Christophe and Haller, Thomas and Linarth, Andre Guilherme and Majer, Mateusz and Teich, Jürgen},
booktitle = {IEEE 2005 Conference on Field-Programmable Technology},
date = {2005-12-11/2005-12-14},
doi = {10.1109/FPT.2005.1568522},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2005.tech.IMMD.inform.increa},
pages = {37-42},
title = {{Increasing} the {Flexibility} in {FPGA}-{Based} {Reconfigurable} {Platforms}: {The} {Erlangen} {Slot} {Machine}},
venue = {Singapore},
year = {2005}
}
@inproceedings{faucris.120279984,
author = {Fischer, Peter and Pohl, Thomas and Maier, Andreas and Hornegger, Joachim},
booktitle = {IGIC 2014 - Abstractband},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.increm{\_}6},
pages = {80-81},
title = {{Incremental} {Dimensionality} {Reduction} for {Respiratory} {Signal} {Extraction} {From} {X}-{Ray} {Sequences}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Fischer14-IDR.pdf},
venue = {Magdeburg},
year = {2014}
}
@article{faucris.110787864,
author = {Huang, Xiaolin and Maier, Andreas and Hornegger, Joachim and Suykens, Johan A. K.},
doi = {10.1016/j.acha.2016.09.001},
faupublication = {yes},
journal = {Applied and Computational Harmonic Analysis},
keywords = {indefinite kernel, LS-SVM, kPCA},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.indefi},
peerreviewed = {Yes},
title = {{Indefinite} {Kernels} in {Least} {Squares} {Support} {Vector} {Machines} and {Principal} {Component} {Analysis}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Huang16-IKI.pdf},
year = {2016}
}
@inproceedings{faucris.119059204,
author = {Schuldhaus, Dominik and Zwick, Constantin and Koerger, Harald and Dorschky, Eva and Kirk, Robert and Eskofier, Björn},
booktitle = {21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
date = {2015-08-10/2015-08-13},
editor = {SIGKDD},
faupublication = {yes},
pages = {1-4},
peerreviewed = {unknown},
title = {{Inertial} {Sensor}-{Based} {Approach} for {Shot}/{Pass} {Classification} {During} a {Soccer} {Match}},
venue = {Sydney},
year = {2015}
}
@inproceedings{faucris.112111384,
abstract = {
Macular degeneration is the third leading cause of blindness worldwide and the leading cause of blindness in the developing world. The analysis of gait parameters can be used to assess the influence of macular degeneration on gait. This study examines the effect of macular degeneration on gait using inertial sensor based 3D spatio-temporal gait parameters. We acquired gait data from 21 young and healthy subjects during a 40m obstacle walk. All subjects had to perform the gait trial with and without macular degeneration simulation glasses. The order of starting with or without glasses alternated between each subject in order to test for training effects. Multiple 3D spatio-temporal gait parameters were calculated for the normal vision as well as the impaired vision groups. The parameters trial time, stride time, stride time coefficient of variation (CV), stance time, stance time CV, stride length, cadence, gait velocity and angle at toe off showed statistically significant differences between the two groups. Training effects were visible for the trials which started without vision impair- ment. Inter-group differences in the gait pattern occurred due to an increased sense of insecurity related with the loss of visual acuity from the simulation glasses. In summary, we showed that 3D spatio-temporal gait pa- rameters derived from inertial sensor data are viable to detect differences in the gait pattern of subjects with and without a macular degeneration simulation. We believe that this study provides the basis for an in-depth analysis regarding the impact of macular degeneration on gait.
},
author = {Kanzler, Christoph M. and Barth, Jens and Klucken, Jochen and Eskofier, Björn},
booktitle = {Proceedings of the 38th IEEE Engineering in Medicine and Biology Society Conference},
date = {2016-08-16/2016-08-20},
faupublication = {yes},
note = {EVALuna2:33529},
pages = {4979-4982},
peerreviewed = {unknown},
title = {{Inertial} {Sensor} based {Gait} {Analysis} {Discriminates} {Subjects} with and without {Visual} {Impairment} {Caused} by {Simulated} {Macular} {Degeneration}},
venue = {Orlando, USA},
year = {2016}
}
@inproceedings{faucris.121949124,
abstract = {
In many cooperative tasks between a human and a robotic assistant, the human guides the robot by exerting forces, either through direct physical interaction or indirectly via a jointly manipulated object. These physical forces perturb the robot's behavior execution and need to be compensated for in order to successfully complete such tasks. Typically, this problem is tackled by means of special purpose force sensors which are, however, not available on many robotic platforms. In contrast, we propose a machine learning approach based on sensor data, such as accelerometer and pressure sensor information. In the training phase, a statistical model of behavior execution is learned that combines Gaussian Process Regression with a novel periodic kernel. During behavior execution, predictions from the statistical model are continuously compared with stability parameters derived from current sensor readings. Differences between predicted and measured values exceeding the variance of the statistical model are interpreted as guidance information and used to adapt the robot's behavior. Several examples of cooperative tasks between a human and a humanoid NAO robot demonstrate the feasibility of our approach.},
author = {Berger, Erik and Vogt, David and Haji Ghassemi, Nooshin and Jung, Bernhard and Ben Amor, Heni},
booktitle = {Inferring guidance information in cooperative human-robot tasks},
faupublication = {no},
peerreviewed = {unknown},
title = {{Inferring} guidance information in cooperative human-robot tasks},
year = {2013}
}
@inproceedings{faucris.255682944,
author = {Wilm, Frauke and Bertram, Christof A. and Marzahl, Christian and Bartel, Alexander and Donovan, Taryn A. and Assenmacher, Charles Antoine and Becker, Kathrin and Bennett, Mark and Corner, Sarah and Cossic, Brieuc and Denk, Daniela and Dettwiler, Martina and Gonzalez, Beatriz Garcia and Gurtner, Corinne and Heier, Annabelle and Lehmbecker, Annika and Merz, Sophie and Plog, Stephanie and Schmidt, Anja and Sebastian, Franziska and Smedley, Rebecca C. and Tecilla, Marco and Thaiwong, Tuddow and Breininger, Katharina and Kiupel, Matti and Maier, Andreas and Klopfleisch, Robert and Aubreville, Marc},
booktitle = {Informatik aktuell},
date = {2021-03-07/2021-03-09},
doi = {10.1007/978-3-658-33198-6{\_}56},
editor = {Christoph Palm, Heinz Handels, Klaus Maier-Hein, Thomas M. Deserno, Andreas Maier, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658331979},
note = {CRIS-Team Scopus Importer:2021-04-19},
pages = {241-246},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Influence} of {Inter}-{Annotator} {Variability} on {Automatic} {Mitotic} {Figure} {Assessment}},
venue = {Regensburg},
year = {2021}
}
@inproceedings{faucris.234875846,
author = {Sanders, James Chester and Wetzl, Matthias and Götz, Theresa and Kuwert, Torsten and Ritt, Philipp},
faupublication = {yes},
note = {EVALuna2:212304},
pages = {S308-S308},
peerreviewed = {Yes},
title = {{Influence} of {Photon} {Count}-{Level} on {Semi}-{Automatic} {Image} {Assessment} in {Myocardial} {Perfusion} {Imaging}},
volume = {45},
year = {2018}
}
@inproceedings{faucris.113235144,
address = {Berlin},
author = {Haderlein, Tino and Nöth, Elmar and Maier, Andreas and Schuster, Maria and Rosanoski, Frank},
booktitle = {Proceedings Text, Speech and Dialogue; 11th International Conference},
date = {2008-09-08/2008-09-12},
editor = {Sojka Petr, Horak Ales, Kopecek Ivan, Pala Karel},
faupublication = {yes},
pages = {325-332},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Influence} of {Reading} {Errors} on the {Text}-{Based} {Automatic} {Evaluation} of {Pathologic} {Voices}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Haderlein08-IOR.pdf},
venue = {Brno},
year = {2008}
}
@inproceedings{faucris.111435764,
address = {Cham, Switzerland},
author = {Haderlein, Tino and Döllinger, Michael and Schützenberger, Anne and Nöth, Elmar},
booktitle = {Proc. Text, Speech and Dialogue; 19th International Conference, TSD 2016},
doi = {10.1007/978-3-319-45510-5{\_}53},
faupublication = {yes},
isbn = {978-3-319-45509-9},
keywords = {Sprache},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.influe},
pages = {461-469},
peerreviewed = {Yes},
publisher = {Springer International Publishing Switzerland},
series = {Lecture Notes in Artificial Intelligence},
title = {{Influence} of {Reverberation} on {Automatic} {Evaluation} of {Intelligibility} with {Prosodic} {Features}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Haderlein16-IOR.pdf},
venue = {Brno, Czech Republic},
volume = {9924},
year = {2016}
}
@inproceedings{faucris.266200866,
author = {Pérez Toro, Paula Andrea and Bayerl, Sebastian and Arias Vergara, Tomás and Vasquez Correa, Juan and Klumpp, Philipp and Schuster, Maria and Nöth, Elmar and Orozco-Arroyave, Juan Rafael and Riedhammer, Korbinian},
booktitle = {Proc. Interspeech 2021},
date = {2021-08-30/2021-09-03},
doi = {10.21437/Interspeech.2021-1589},
faupublication = {yes},
isbn = {9781713836902},
keywords = {Alzheimer's disease; Speaker modeling; Speech analysis; Emotional modeling; Natural language processing},
pages = {3785-3789},
peerreviewed = {unknown},
publisher = {International Speech Communication Association},
title = {{Influence} of the {Interviewer} on the {Automatic} {Assessment} of {Alzheimer}’s {Disease} in the {Context} of the {ADReSSo} {Challenge}},
volume = {6},
year = {2021}
}
@article{faucris.113996344,
abstract = {Autofocusing is essential to high throughput microscopy and live cell imaging and requires reliable focus measures. Phase objects such as separated single Chinese hamster ovary cells are almost invisible at the optical focus position in bright field microscopy images. Because of the phase effect, defocused images of phase objects have more contrast. In this paper, we show that widely used focus measures exhibit an untypical behaviour for such images. In the case of homogeneous cells, that is, when most cells tend to lie in the same focal plane, both gradient-based and statistics-based focus measures tend to have a local minimum instead of a global maximum at the optical focus position. On the other hand, if images show inhomogeneous cells, gradient-based focus measures tend to yield typical focus curves, whereas statistics-based focus measures deliver curves similar to the case of homogeneous cells. These results were interpreted using the equation describing the phase effect and patch-wise analysis of the focus curves. Bioprocess engineering experts are also influenced by the phase effect. Forty-four focus positions selected by them led to the conclusion that they prefer to look at defocused images instead of those at the optical focus. © 2014 The Authors Journal of Microscopy © 2014 Royal Microscopical Society.},
author = {Schöll, Simon and Mualla, Firas and Sommerfeldt, Björn and Steidl, Stefan and Maier, Andreas and Buchholz, Rainer and Hornegger, Joachim},
doi = {10.1111/jmi.12118},
faupublication = {yes},
journal = {Journal of Microscopy},
keywords = {Bright field microscopy; Focus measures; Nontypical focus curves; Phase effect},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.influe},
pages = {65-74},
peerreviewed = {Yes},
title = {{Influence} of the phase effect on gradient-based and statistics-based focus measures in bright field microscopy},
volume = {254},
year = {2014}
}
@inproceedings{faucris.121406164,
author = {Haase, Sven and Köhler, Thomas and Kilgus, Thomas and Maier-Hein, Lena and Hornegger, Joachim and Feußner, Hubertus},
booktitle = {Computer- und Roboter Assistierte Chirurgie},
date = {2013-11-28},
editor = {Freysinger Wolfgang},
faupublication = {yes},
pages = {194-197},
title = {{Instrument} {Segmentation} in {Hybrid} 3-{D} {Endoscopy} using {Multi}-{Sensor} {Super}-{Resolution}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Haase13-ISI.pdf},
venue = {Innsbruck},
year = {2013}
}
@article{faucris.121352264,
author = {Gallwitz, Florian and Niemann, Heinrich and Nöth, Elmar and Warnke, Volker},
faupublication = {yes},
journal = {Speech Communication},
pages = {81-95},
peerreviewed = {Yes},
title = {{Integrated} {Recognition} of {Words} and {Phrase} {Boundaries}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2002/Gallwitz02-IRO.pdf},
volume = {36.0},
year = {2002}
}
@inproceedings{faucris.115615984,
abstract = {In this paper, we present an integrated approach for recognizing both the word sequence and the syntactic-prosodic structure of a spontaneous utterance. The approach aims at improving the performance of the understanding component of speech understanding systems by exploiting not only acoustic-phonetic and syntactic information, but also prosodic information directly within the speech recognition process. Whereas spoken utterances are typically modelled as unstructured word sequences in the speech recognizer, our approach includes phrase boundary information in the language model and provides HMMs to model the acoustic and prosodic characteristics of phrase boundaries. This methodology has two major advantages compared to purely word-based speech recognizers. First, additional syntactic-prosodic boundaries are determined by the speech recognizer which facilitates parsing and resolve syntactic and semantic ambiguities. Second - after having removed the boundary information from the result of the recognizer - the integrated model yields a 4% relative word error rate (WER) reduction compared to a traditional word recognizer. The boundary classification performance is equal to that of a separate prosodic classifier operating on the word recognizer output, thus making a separate classifier unnecessary for this task and saving the computation time involved. Compared to the baseline word recognizer, the integrated word-and-boundary recognizer does not involve any computational overhead. (C) 2002 Elsevier Science B.V. All rights reserved.},
author = {Gallwitz, Florian and Niemann, Heinrich and Nöth, Elmar and Warnke, Volker},
faupublication = {yes},
keywords = {speech recognition;prosody;speech understanding},
month = {Jan},
pages = {81-95},
peerreviewed = {unknown},
publisher = {Elsevier},
title = {{Integrated} recognition of words and prosodic phrase boundaries},
volume = {36},
year = {2002}
}
@inproceedings{faucris.210075412,
author = {Wilke, Peter and Billing, Gunnar and Mansfeld, Christian and Nilson, Jörg},
booktitle = {Proc. Int. Workshop on Modelling, MASCOTS95},
date = {1995-01-19/1995-01-19},
faupublication = {yes},
pages = {4 pp.},
peerreviewed = {unknown},
title = {{Integration} of {Genetic} {Algorithms} and {Fuzzy} {Logic} into a {Neural} {Network} {Simulation} {Environment}, {Analysis} and {Simulation} of {Computer} and {Telecommunication} {Systems}},
venue = {Durham, NC, USA},
year = {1995}
}
@article{faucris.120186704,
abstract = {Background: In primary open angle glaucoma (POAG) and its non-barotraumatic subgroup, normal tension glaucoma (NTG), the pathophysiological differences are not clear. A participation of the 4th neuron of the visual pathway (optic radiation) appears possible on the basis of related experimental studies. The goal of the present study was the evaluation of the optic radiation by diffusion tensor imaging (DTI), which is based on the magnetic resonance imaging. The diffusion and anisotropy parameters of the optic radiation as a marker of axonal integrity and demyelination/damage of glial cells, respectively, were used to investigate the relation between the morphology of the papilla (BLDF, linear discriminant function of Burk) and the contrast sensitivity (FDT, frequency doubling test). Patients and Methods: In this prospective observational study 13 POAG patients, 13 NTG patients, and 7 control patients of the same mean age were included. For segmentation of the optic radiation a semi-automated algorithm was applied and the diffusion and anisotropy parameters were calculated. The importance of the covariates age, BLDF, and FDT for the DTI parameters was determined using partial correlation analysis. Results: Analysis of the covariates partially showed a clear autocorrelation. The correlations between the DTI parameters and BLDF were significant in all groups after correction of the measurement values for the covariates. FDT correlated with DTI parameters in controls and POAG. The NTG group did not show this correlation due to a strong spreading of the FDT values. Conclusion: After statistical elimination of the autocorrelation of the covariates age, BLDF, and FDT the morphology of the papilla correlated with the axonal integrity and demyelination/glia cell impairment of the optic radiation in controls and glaucoma. In NTG the impaired contrast sensitivity is highly variable and is not associated with the condition of the 3rd or 4th neuron, respectively, as compared to POAG. The autocorrelation between individual covariates represents an important element for the judgement of the visual pathway. © Georg Thieme Verlag KG · Stuttgart · New York.},
author = {Michelson, Georg and Wärntges, Simone and Engelhorn, Tobias and El-Rafei, Ahmed Mohamed Ibrahim and Hornegger, Joachim and Dörfler, Arnd},
doi = {10.1055/s-0031-1299262},
faupublication = {yes},
journal = {Klinische Monatsblätter für Augenheilkunde},
pages = {143-148},
peerreviewed = {Yes},
title = {{Integrity}/{Demyelination} of the optic radiation, morphology of the papilla, and contrast sensitivity in glaucoma patients},
volume = {229},
year = {2012}
}
@inproceedings{faucris.121427944,
abstract = {In this paper we examine the quality of the prediction of intelligibility scores of human experts. Furthermore, we investigate the differences between subjective expert raters who evaluated speech disorders of laryngectomees and children with cleft lip and palate. We use the recognition rate of a word recognizer and prosodic features to predict the intelligibility score of each individual expert. For each expert and the mean opinion of all experts we present the best features to model their scoring behavior according to the mean rank obtained during a 10-fold cross-validation. In this manner all individual speech experts were modeled with a correlation coefficient of at least r >.75. The mean opinion of all raters is predicted with a correlation of r =.90 for the laryngectomees and r =.86 for the children.},
address = {Berlin},
author = {Maier, Andreas and Haderlein, Tino and Schuster, Maria and Nkenke, Emeka and Nöth, Elmar},
booktitle = {Text, Speech and Dialogue},
date = {2007-09-03/2007-09-07},
editor = {Matousek Vaclav, Mautner Pavel},
faupublication = {yes},
month = {Jan},
pages = {278-285},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Intelligibility} is more than a single word: {Quantification} of speech intelligibility by {ASR} and prosody},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Maier07-IIM.pdf},
venue = {Pilsen},
year = {2007}
}
@article{faucris.115601464,
abstract = {OBJECTIVE\nData about the effect of unilateral or bilateral cleft lip and palate (CLP) on speech quality are inconsistent. In this study we firstly quantify the intelligibility of children with unilateral and bilateral CLP objectively by means of automatic speech recognition system (ASR).\nMETHODS\nSpeech data of 72 German speaking children (8.7+/-3.0 years) with CLP thereof 17 children with bilateral CLP, 23 with CLP on the right side, and 32 on the left, were compared. A group of 159 children aged 9.1+/-2.9 years served as control group. To quantify intelligibility we calculated the word recognition rate (WR) as the percentage of correctly recognized words of a standardized speech test (PLAKSS).\nRESULTS\nBetween the 3 cleft groups, there was no significant difference in WR. Compared to the control group (WR mean 63.5%+/-12.1%), the patient group (WR mean 48.1%+/-16.3%) shows significant lower WR (p< 0.001). The WR rises with increasing age in the control group and in the patient groups with unilateral cleft significantly. This couldn't be observed in the children with bilateral CLP. In this group the males showed a significantly higher WR than the females. In the control group as in the patient groups with unilateral cleft there is no significant difference between girls and boys.\nCONCLUSIONS\nDespite the greater extent of the malformation of children with a bilateral CLP, there is no significant difference to the children with only a unilateral cleft lip and palate.},
author = {Maier, Andreas and Holst, Alexandra and Schuster, Maria and Schützenberger, Anne and Eysholdt, Ulrich and Nöth, Elmar and Dames, F. and Stelzle, Florian},
doi = {10.1055/s-0029-1225639},
faupublication = {yes},
journal = {Laryngo-Rhino-Otologie},
keywords = {Automatic speech recognition; Cleft lip and palate; Intelligibility; Objective evaluation},
pages = {723-728},
peerreviewed = {unknown},
title = {[{Intelligibility} of children with bilateral and unilateral cleft lip and palate].},
volume = {88},
year = {2009}
}
@inproceedings{faucris.120324424,
address = {Los Alamitos, California, Washington, Tokyo},
author = {Maier, Andreas and Hacker, Christian and Nöth, Elmar and Nkenke, Emeka and Haderlein, Tino and Rosanowski, Frank and Schuster, Maria},
booktitle = {The 18th International Conference on Pattern Recognition},
date = {2006-08-20/2006-08-24},
editor = {Tang Y.Y., Wang S.P., Lorette G., Yeung D.S., Yan H.},
faupublication = {yes},
pages = {274-277},
peerreviewed = {Yes},
publisher = {IEEE Computer Society},
title = {{Intelligibility} of {Children} with {Cleft} {Lip} and {Palate}: {Evaluation} by {Speech} {Recognition} {Techniques}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Maier06-IOC.pdf},
venue = {Hong Kong},
year = {2006}
}
@article{faucris.118304824,
author = {Schuster, Maria and Haderlein, Tino and Nöth, Elmar and Lohscheller, Jörg and Eysholdt, Ulrich and Rosanowski, Frank},
doi = {10.1007/s00405-005-0974-6},
faupublication = {yes},
journal = {European Archives of Oto-Rhino-Laryngology},
pages = {188-193},
peerreviewed = {Yes},
title = {{Intelligibility} of laryngectomees' substitute speech: automatic speech recognition and subjective rating},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Schuster06-IOL.pdf},
volume = {263},
year = {2006}
}
@inproceedings{faucris.113141204,
address = {Berlin},
author = {Haderlein, Tino and Moers, Cornelia and Möbius, Bernd and Rosanowski, Frank and Nöth, Elmar},
booktitle = {Proc. Text, Speech and Dialogue; 14th International Conference},
date = {2011-09-01/2011-09-05},
editor = {Habernal Ivan, Matousek Vaclav},
faupublication = {yes},
pages = {195-202},
publisher = {Springer},
title = {{Intelligibility} {Rating} with {Automatic} {Speech} {Recognition}, {Prosodic}, and {Cepstral} {Evaluation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Haderlein11-IRW.pdf},
venue = {Pilsen},
year = {2011}
}
@inproceedings{faucris.107895304,
abstract = {Current research has shown that the speech intelligibility in children with cleft lip and palate (CLP) can be estimated automatically using speech recognition methods. On German CLP data high and significant correlations between human ratings and the recognition accuracy of a speech recognition system were already reported. In this paper we investigate whether the approach is also suitable for other languages. Therefore, we compare the correlations obtained on German data with the correlations on Italian data. A high and significant correlation (r=0.76; p < 0.01) was identified on the Italian data. These results do not differ significantly from the results on German data (p > 0.05).},
address = {Brighton, England},
author = {Scipioni, Marcello and Gerosa, Matteo and Giuliani, Diego and Nöth, Elmar and Maier, Andreas},
booktitle = {Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech 2009)},
date = {2009-09-06/2009-09-10},
editor = {Moore Roger},
faupublication = {yes},
keywords = {speech recognition;speech intelligibility;cleft lip and palate},
month = {Jan},
pages = {967-970},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{Intelligitility} {Assessment} in {Children} with {Cleft} {Lip} and {Palate} in {Italian} and {German}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Scipioni09-IAI.pdf},
venue = {Brighton},
year = {2009}
}
@inproceedings{faucris.107961524,
address = {Berlin},
author = {Bouattour, Sahla and Heigl, Benno and Hornegger, Joachim and Paulus, Dietrich},
booktitle = {Bildverarbeitung für die Medizin 2004},
date = {2004-03-29/2004-03-30},
doi = {10.1007/978-3-642-18536-6{\_}83},
editor = {Tolxdorff T., Braun J., Handels H., Horsch A., Meinzer H.-P.},
faupublication = {yes},
pages = {405-409},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Intensity}-{Based} {3D}-{Reconstruction} of {Non}-rigid {Moving} {Stenosis} from {Many} {Angiographies}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Bouattour04-IB3.pdf},
venue = {Berlin},
year = {2004}
}
@article{faucris.121355564,
author = {Hopfgartner, Christian and Scholz, Ingo and Gugat, Martin and Leugering, Günter and Hornegger, Joachim},
faupublication = {yes},
journal = {ICGST International Journal on Graphics, Vision and Image Processing},
pages = {27-37},
peerreviewed = {unknown},
title = {{Intensity}-based 3-{D} {Reconstruction} with {Non}-linear {Optimization}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Hopfgartner10-IRW.pdf},
volume = {10.0},
year = {2010}
}
@misc{faucris.109715804,
abstract = {New images of a three-dimensional scene can be generated from known image sequences using lightfields. To get high quality images, it is important to have accurate information about the structure of the scene. In order to optimize this information, we define a residual-function. This function represents the difference between an image, rendered in a known view from neighboured images and the original image at the same position. In order to get optimal results, we minimize the residual-function by defining a nonlinear least-squares problem, which is solved by an appropriate optimization method. We use a nonmonotone variant of the Levenberg-Marquardt method.},
author = {Hopfgartner, Christian and Scholz, Ingo and Gugat, Martin and Leugering, Günter and Hornegger, Joachim},
faupublication = {yes},
keywords = {Nonlinear Optimization; Imaging; Rendering; Nonmonotone Levenberg-Marquardt; 90C30; 68U10; 94A08},
peerreviewed = {automatic},
title = {{Intensity} based {Three}-{Dimensional} {Reconstruction} with {Nonlinear} {Optimization}},
url = {http://www.am.uni-erlangen.de/de/preprints2000.html},
year = {2007}
}
@phdthesis{faucris.203754501,
abstract = {A multispectral or hyperspectral sensor captures images of high spectral resolution by dividing the light spectrum into many narrow bands. With the advent of affordable and flexible sensors, the modality is constantly widening its range of applications. This necessitates novel tools that allow general and intuitive analysis of the image data. In this work, a software framework is presented that bundles interactive visualization techniques with powerful analysis capabilities and is accessible through efficient computation and an intuitive user interface. Towards this goal, several algorithmic solutions to open problems are presented in the fields of edge detection, clustering, supervised segmentation and visualization of hyperspectral images.
In edge detection, the structure of a scene can be extracted by finding discontinuities between image regions. The high dimensionality of hyperspectral data poses specific challenges for this task. A solution is proposed based on a data-driven pseudometric. The pseudometric is computed through a fast manifold learning technique and outperforms established metrics and similarity measures in several edge detection scenarios.
Another approach to scene understanding in the hyperspectral or a derived feature space is data clustering. Through pixel-cluster assignment, a global segmentation of an image is obtained based on reflectance effects and materials in the scene. An established mode-seeking method provides high-quality clustering results, but is slow to compute in the hyperspectral domain. Two methods of speedup are proposed that allow computations for interactive use. A further method is proposed that finds clusters in a learned topological representation of the data manifold. Experimental results demonstrate a quick and accurate clustering of the image data without any assumptions or prior knowledge, and that the proposed methods are applicable for the extraction of material prototypes and for fuzzy clustering of reflectance effects.
For supervised image analysis, an algorithm for seed-based segmentation is introduced to the hyperspectral domain. Specific segmentations can be quickly obtained by giving cues about regions to be included in or excluded from a segment. The proposed method builds on established similarity measures and the proposed data-driven pseudometric. A new benchmark is introduced to assess its performance.
The aforementioned analysis methods are then combined with capable visualization techniques. A method for non-linear false-color visualization is proposed that distinguishes captured spectra in the spatial layout of the image. This facilitates the finding of relationships between objects and materials in the scene. Additionally, a visualization for the spectral distribution of an image is proposed. Raw data exploration becomes more feasible through manipulation of this plot and its link to traditional displays. The combination of false-color coding, spectral distribution plots, and traditional visualization enables a new workflow in manual hyperspectral image analysis.
2< 0.99) between the extracted intensity values in the kV-switching and kV-constant reconstructed volumes, and allows for an automatic differentiation between contrast concentration down to 10% (350 mg/ml iodine) and pure water under low-noise conditions. Preliminary results of iodine and soft tissue separation showed also promising results in the first in vivo pig study. Conclusions: The feasibility of dual-energy imaging using a fast kV-switching method on an angiographic C-arm CT system was investigated. Direct measurements of beam quality in the x-ray field demonstrate the stability of the kV-switching method. Phantom and in vivo experiments showed that images did not deviate from those of corresponding kV-constant scans. All performed experiments confirmed the capability of performing fast kV-switching scans on a clinically available C-arm CT system. More complex material decomposition tasks and postprocessing steps will be part of future investigations.},
author = {Müller, Kerstin and Datta, Sanjit and Moiz, Ahmad and Choi, Jang-Hwan and Moore, Teri and Pung, Leland and Niebler, Christine and Gold, Garry and Maier, Andreas and Fahrig, Rebecca},
doi = {10.1118/1.4962929},
faupublication = {yes},
journal = {Medical Physics},
keywords = {C-arm CT; cone-beam CT (CBCT); dual-energy; rapid kV-switching},
note = {UnivIS-Import:2017-01-09:Pub.2016.tech.IMMD.IMMD5.interv},
pages = {5536-5546},
peerreviewed = {Yes},
title = {{Interventional} dual-energy imaging - {Feasibility} of rapid {kV}-switching on a {C}-arm {CT} system},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Muller16-IDI.pdf},
volume = {43},
year = {2016}
}
@article{faucris.117702464,
abstract = {Today, quantitative analysis of three-dimensional (3D) dynamics of the left ventricle (LV) cannot be performed directly in the catheter lab using a current angiographic C-arm system, which is the workhorse imaging modality for cardiac interventions. Therefore, myocardial wall analysis is completely based on the 2D angiographic images or pre-interventional 3D/4D imaging. In this paper, we present a complete framework to study the ventricular wall motion in 4D (3D+t) directly in the catheter lab. From the acquired 2D projection images, a dynamic 3D surface model of the LV is generated, which is then used to detect ventricular dyssynchrony. Different quantitative features to evaluate LV dynamics known from other modalities (ultrasound, magnetic resonance imaging) are transferred to the C-arm CT data. We use the ejection fraction, the systolic dyssynchrony index a 3D fractional shortening and the phase to maximal contraction (φi, max) to determine an indicator of LV dyssynchrony and to discriminate regionally pathological from normal myocardium. The proposed analysis tool was evaluated on simulated phantom LV data with and without pathological wall dysfunctions. The LV data used is publicly available online at https://conrad.stanford.edu/data/heart. In addition, the presented framework was tested on eight clinical patient data sets. The first clinical results demonstrate promising performance of the proposed analysis tool and encourage the application of the presented framework to a larger study in clinical practice. © 2014 Institute of Physics and Engineering in Medicine.},
author = {Müller, Kerstin and Maier, Andreas and Zheng, Yefeng and Wang, Yang and Lauritsch, Günter and Schwemmer, Chris and Rohkohl, Christopher and Hornegger, Joachim and Fahrig, Rebecca},
doi = {10.1088/0031-9155/59/9/2265},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
keywords = {C-arm CT; cardiac dynamics; functional imaging; interventional imaging; wall motion analysis},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.interv},
pages = {2265-2294},
peerreviewed = {Yes},
title = {{Interventional} heart wall motion analysis with cardiac {C}-arm {CT} systems},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Mueller14-IHW.pdf},
volume = {59},
year = {2014}
}
@inproceedings{faucris.120188244,
abstract = {Magnetic Resonance Imaging (MRI) has several unique advantages for guiding thermal ablation therapies. It not only provides excellent soft-tissue contrast and multiplanar capabilities, but also is sensitive to thermal effects. To make full use of these advantages for thermal ablation procedures, we present an integrated solution for a thermal therapy workflow that combines dedicated MRI pulse sequences and visualization/analysis tools for trajectory planning, automatic slice positioning for image-guided needle placement, and advanced MR thermal mapping. The paper highlights a novel approach to detect the needle in real-time MR images and to automatically realign the scan planes. In addition, a global approach to correct for B field shift during online MR thermometry is introduced. The application has been implemented using the open-source eXtensible Imaging Platform (XIP). © 2011 IEEE.},
author = {Rothgang, Eva and Gilson, Wesley D. and Strehl, Wilhelm and Pan, Li and Roland, Jörg and Lorenz, Christine H. and Hornegger, Joachim},
booktitle = {2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11},
doi = {10.1109/ISBI.2011.5872771},
faupublication = {yes},
pages = {1864-1868},
peerreviewed = {unknown},
title = {{Interventional} {MR}-imaging for thermal ablation therapy},
venue = {Chicago, IL},
volume = {null},
year = {2011}
}
@article{faucris.114461864,
author = {Fieselmann, Andreas and Hornegger, Joachim and Fahrig, Rebecca and Deuerling-Zheng, Yu and Zellerhoff, Michael and Boese, Jan and Ganguly, Arundhuti and Rohkohl, Christopher},
doi = {10.1055/s-002-23729},
faupublication = {yes},
journal = {RöFo : Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren},
note = {UnivIS-Import:2016-02-10:Pub.2012.tech.IMMD.IMMD5.interv{\_}2},
pages = {867},
peerreviewed = {Yes},
title = {{Interventionelle} 4-dimensionale {Darstellung} der {Hirnperfusion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Fieselmann12-I4D.pdf},
year = {2012}
}
@inproceedings{faucris.224021546,
abstract = {Brain deformation (or
brain shift)
during neurosurgical procedures such as tumor resection has a
significant impact on the accuracy of neuronavigation systems.
Compensating for this deformation during surgery is essential for
effective guidance. In this paper, we propose a method for
brain shift
compensation based on registration of vessel centerlines derived from
preoperative C-Arm cone beam CT (CBCT) images, to intraoperative ones. A
hybrid mixture model (HdMM)-based non-rigid registration approach was
formulated wherein, Student’s t and Watson distributions were combined
to model positions and centerline orientations of cerebral vasculature,
respectively. Following registration of the preoperative vessel
centerlines to its intraoperative counterparts, B-spline interpolation
was used to generate a dense deformation field and warp the preoperative
image to each intraoperative image acquired. Registration accuracy was
evaluated using both synthetic and clinical data. The former comprised
CBCT images, acquired using a deformable anthropomorphic brain phantom.
The latter meanwhile, consisted of four 3D digital subtraction
angiography (DSA) images of one patient, acquired before, during and
after surgical tumor resection. HdMM consistently outperformed a
state-of-the-art point matching method, coherent point drift (CPD),
resulting in significantly lower registration errors. For clinical data,
the registration error was reduced from 3.73 mm using CPD to 1.55 mm
using the proposed metho},
author = {Bayer, Siming and Ravikumar, Nishant and Strumia, Maddalena and Tong, Xiaoguang and Gao, Ying and Ostermeier, Martin and Fahrig, Rebecca and Maier, Andreas},
booktitle = {MICCAI 2018: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, pp 116-124, Springer},
date = {2018-09-16/2018-09-20},
doi = {10.1007/978-3-030-00931-1},
editor = {Springer, Cham},
faupublication = {yes},
isbn = {978-3-030-00930-4},
pages = {116-124},
peerreviewed = {Yes},
title = {{Intraoperative} brain shift compensation using a hybrid mixture model},
venue = {Granada, Spain},
year = {2018}
}
@inproceedings{faucris.224606632,
abstract = {Purpose: Fusion of preoperative data with intraoperative X-ray images has proven the potential to reduce radiation exposure and contrast agent, especially for complex endovascular aortic repair (EVAR). Due to patient movement and introduced devices that deform the vasculature, the fusion can become inaccurate. This is usually detected by comparing the preoperative information with the contrasted vessel. To avoid repeated use of iodine, comparison with an implanted stent can be used to adjust the fusion. However, detecting the stent automatically without the use of contrast is challenging as only thin stent wires are visible. Method: We propose a fast, learning-based method to segment aortic stents in single uncontrasted X-ray images. To this end, we employ a fully convolutional network with residual units. Additionally, we investigate whether incorporation of prior knowledge improves the segmentation. Results: We use 36 X-ray images acquired during EVAR for training and evaluate the segmentation on 27 additional images. We achieve a Dice coefficient of 0.933 (AUC 0.996) when using X-ray alone, and 0.918 (AUC 0.993) and 0.888 (AUC 0.99) when adding the preoperative model, and information about the expected wire width, respectively. Conclusion: The proposed method is fully automatic, fast and segments aortic stent grafts in fluoroscopic images with high accuracy. The quality and performance of the segmentation will allow for an intraoperative comparison with the preoperative information to assess the accuracy of the fusion.},
author = {Breininger, Katharina and Albarqouni, Shadi and Kurzendorfer, Tanja and Pfister, Marcus and Kowarschik, Markus and Maier, Andreas},
booktitle = {CARS 2018---Computer Assisted Radiology and Surgery Proceedings of the 32nd International Congress and Exhibition Berlin, Germany, June 20--23, 2018},
doi = {10.1007/s11548-018-1779-6},
faupublication = {yes},
keywords = {Aortic stents; Convolutional neural network; Deep learning; EVAR; Fluoroscopy; Segmentation},
note = {UnivIS-Import:2019-08-15:Pub.2018.tech.IMMD.IMMD5.intrao{\_}2},
pages = {S200-201},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{Intraoperative} stent segmentation in {X}-ray fluoroscopy for endovascular aortic repair},
venue = {Berlin},
volume = {13},
year = {2018}
}
@article{faucris.224591855,
abstract = {Purpose: Fusion of preoperative data with intraoperative X-ray images has proven the potential to reduce radiation exposure and contrast agent, especially for complex endovascular aortic repair (EVAR). Due to patient movement and introduced devices that deform the vasculature, the fusion can become inaccurate. This is usually detected by comparing the preoperative information with the contrasted vessel. To avoid repeated use of iodine, comparison with an implanted stent can be used to adjust the fusion. However, detecting the stent automatically without the use of contrast is challenging as only thin stent wires are visible. Method: We propose a fast, learning-based method to segment aortic stents in single uncontrasted X-ray images. To this end, we employ a fully convolutional network with residual units. Additionally, we investigate whether incorporation of prior knowledge improves the segmentation. Results: We use 36 X-ray images acquired during EVAR for training and evaluate the segmentation on 27 additional images. We achieve a Dice coefficient of 0.933 (AUC 0.996) when using X-ray alone, and 0.918 (AUC 0.993) and 0.888 (AUC 0.99) when adding the preoperative model, and information about the expected wire width, respectively. Conclusion: The proposed method is fully automatic, fast and segments aortic stent grafts in fluoroscopic images with high accuracy. The quality and performance of the segmentation will allow for an intraoperative comparison with the preoperative information to assess the accuracy of the fusion.},
author = {Breininger, Katharina and Albarqouni, Shadi and Kurzendorfer, Tanja and Pfister, Marcus and Kowarschik, Markus and Maier, Andreas},
doi = {10.1007/s11548-018-1779-6},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Aortic stents; EVAR; Fluoroscopy; Convolutional neural network; Deep learning; Segmentation},
note = {UnivIS-Import:2019-08-15:Pub.2018.tech.IMMD.IMMD5.intrao},
pages = {1221-1231},
peerreviewed = {Yes},
title = {{Intraoperative} stent segmentation in {X}-ray fluoroscopy for endovascular aortic repair},
volume = {13},
year = {2018}
}
@article{faucris.108153364,
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Schiel, Florian and Krajewski, Jarek},
faupublication = {yes},
journal = {Computer Speech and Language},
pages = {343-345},
peerreviewed = {No},
title = {{Introduction} to the {Special} {Issue} on {Broadening} the {View} on {Speaker} {Analysis} ({Editorial})},
volume = {28},
year = {2014}
}
@article{faucris.114105244,
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Vinciarelli, Alessandro and Burkhardt, Felix and van Son, Rob},
doi = {10.1016/j.csl.2014.09.004},
faupublication = {yes},
journal = {Computer Speech and Language},
note = {UnivIS-Import:2015-03-11:Pub.2015.tech.IMMD.IMMD5.introd},
pages = {98-99},
peerreviewed = {No},
title = {{Introduction} to the {Special} {Issue} on {Next} {Generation} {Computational} {Paralinguistics} ({Editorial})},
volume = {29},
year = {2015}
}
@article{faucris.121337524,
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton},
doi = {10.1016/j.csl.2012.06.002},
faupublication = {yes},
journal = {Computer Speech and Language},
pages = {1-3},
peerreviewed = {No},
title = {{Introduction} to the {Special} {Issue} on {Paralinguistics} in {Naturalistic} {Speech} and {Language} ({Editorial})},
volume = {27},
year = {2013}
}
@article{faucris.121324104,
author = {Schuller, Björn and Batliner, Anton and Steidl, Stefan},
doi = {10.1016/j.specom.2011.07.003},
faupublication = {yes},
journal = {Speech Communication},
pages = {1059-1061},
peerreviewed = {No},
title = {{Introduction} to the {Special} {Issue} on {Sensing} {Emotion} and {Affect} - {Facing} {Realism} in {Speech} {Processing} ({Editorial})},
volume = {53},
year = {2011}
}
@inproceedings{faucris.119512184,
abstract = {In cases of aortic valve diseases, diagnosis and subsequent interventional planning are highly facilitated by deriving exact three-dimensional geometric models of a patient's aortic valve apparatus from Cardiac Computed Tomography Angiography data. Fully-automatic approaches to do so however lack in absolute reliability and manual editing of the initially detected geometric model is often required. We therefore present an interactive editing method for this scenario - in particular for editing the aortic root model - based on the As-Rigid-As-Possible (ARAP) surface modeling paradigm, which allows efficient, robust, intuitive and physically plausible deformations of three-dimensional geometric models. The user constrains a model's surface by setting and moving handles - the so-called constraints - while the remaining, and only the remaining, free part of the surface is deformed automatically in a way such that the global shape is preserved in real-time. We extended the classical ARAP approach for our scenario by an energy smoothness regularization to overcome non-smooth artifacts at constrained positions. We furthermore incorporated the use of image evidence-based cues in the interactive work ow such that handles can be made "snap" into visible 3-D surface indicators. We evaluated our method in a user study regarding intuitiveness, achievable accuracy, inter-user variability, required time and robustness. The participants started with an initial average mesh-to-mesh surface error of 1.65 mm and achieved after 50 mouse clicks on average and less than 3.5 minutes an average error of 0.48 mm with respect to an expert-de ned ground truth. The inter-user variability was 0.43 mm.},
author = {Lades, Félix and Wels, Michael and Steidl, Stefan and Sühling, Michael},
booktitle = {The 2nd Interactive Medical Image Computing Workshop},
faupublication = {yes},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.intuit},
pages = {29-36},
peerreviewed = {Yes},
title = {{Intuitive} and {Smart} {Editing} of {Three}-{Dimensional} {Geometric} {Heart} {Valve} {Apparatus} {Models} from {Cardiac} {CT} {Data}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Lades15-IAS.pdf},
venue = {Munich, Germany},
year = {2015}
}
@book{faucris.121195404,
abstract = {The automation and speedup of interventional therapy and diagnostic workflows is a crucial issue. One way to improve these workflows is to accelerate the image acquisition procedures by fully automating the patient setup. This paper describes a system that performs this task without the use of markers or other prior assumptions. It returns metric coordinates of the 3-D body shape in real-time for inverse positioning. This is achieved by the application of an emerging technology, called Time-of-Flight (ToF) sensor. A ToF sensor is a cost-efficient, off-the-shelf camera which provides more than 40,000 3-D points in real-time. The first contribution of this paper is the incorporation of this novel imaging technology (ToF) in interventional imaging. The second contribution is the ability of a C-arm system to position itself with respect to the patient prior to the acquisition. We are using the 3-D surface information of the patient to partition the body into anatomical sections. This is achieved by a fast two-stage classification process. The system computes the ISO-center for each detected region. To verify our system we performed several tests on the ISO-center of the head. Firstly, the reproducibility of the head ISO-center computation was evaluated. We achieved an accuracy of (x: 1.73±1.11 mm/y: 1.87±1.31 mm/z: 2.91±2.62 mm). Secondly, a C-arm head scan of a body phantom was setup. Our system automatically aligned the ISO-center of the head with the C-arm ISO-center. Here we achieved an accuracy of ± 1 cm, which is within the accuracy of the patient table control. © 2009 Springer-Verlag.},
address = {Berlin - Heidelberg},
author = {Schaller, Christian and Rohkohl, Christopher and Penne, Jochen and Stürmer, Michael and Hornegger, Joachim},
doi = {10.1007/978-3-642-04268-3{\_}68},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2009.tech.IMMD.IMMD5.invers{\_}6},
pages = {549-556},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Inverse} {C}-arm positioning for interventional procedures using real-time body part detection},
volume = {null},
year = {2009}
}
@inproceedings{faucris.107367524,
author = {Hutter, Jana and Grimm, Robert and Forman, Christoph and Hornegger, Joachim and Schmitt, Peter},
booktitle = {Magnetic Resonance Materials in Physics, Biology and Medicine},
date = {2011-10-06/2011-10-08},
faupublication = {yes},
pages = {92-93},
peerreviewed = {unknown},
publisher = {Springer-Verlag},
title = {{Inverse} root sampling pattern for iterative reconstruction in non-{CE} {MR} angiography},
venue = {Leipzig},
year = {2011}
}
@inproceedings{faucris.121792924,
abstract = {Hemodynamic parameters based on the temporal behavior of contrast agent flow in cerebral aneurysms represent important indicators of the effectiveness of deployed micro devices. These measurements are also interesting for the assessment of virtual treatment planning strategies such as virtual device implantation combined with CFD simulations of blood flow and subsequently generated synthetic angiograms (virtual angiography). Due to settlement effects, contrast agent residence time may increase. As of today, virtual angiography does not explicitly model these effects such that differences between real and virtual angiograms are existent. Hence, we present an approach to examine this contrast agent settlement in virtual angiograms by adding a gravitational effect on simulated contrast agent. The model is evaluated on several cases with different characteristics by generating virtual angiograms with and without the proposed gravity model and comparisons against acquired, real angiograms. Primarily with regards to wash-out behavior and residence time, virtual angiograms including a gravity component show a significantly improved concordance with acquired angiograms.},
address = {Berlin},
author = {Endres, Jürgen and Redel, Thomas and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin: Algorithmen, Systeme, Anwendungen},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}53},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.invest{\_}8},
pages = {282-287},
publisher = {Springer-Verlag},
title = {{Investigating} {Contrast} {Settlement} {Using} {Virtual} {Angiography}},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.111052964,
author = {Oppelt, Maximilian and Sanders, James Chester and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin},
date = {2015-03-15/2015-03-17},
doi = {10.1007/978-3-662-46224-9{\_}86},
faupublication = {yes},
isbn = {9783662462232},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.invest},
pages = {504-509},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Investigation} of {Single} {Photon} {Emission} {Computed} {Tomography} {Acquired} on {Helical} {Trajectories}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Oppelt15-IOS.pdf},
venue = {Lübeck},
year = {2015}
}
@article{faucris.121156024,
abstract = {Purpose: The authors have developed a method to enable cerebral perfusion CT imaging using C-Arm based conebeam CT (CBCT). This allows intraprocedural monitoring of brain perfusion during treatment of stroke. Briefly, the technique consists of acquiring multiple scans (each scan comprised of six sweeps) acquired at different time delays with respect to the start of the x-ray contrast agent injection. The projections are then reconstructed into angular blocks and interpolated at desired time points. The authors have previously demonstrated its feasibility in vivo using an animal model. In this paper, the authors describe an in vitro technique to evaluate the accuracy of their method for measuring the relevant temporal signals. Methods: The authors' evaluation method is based on the concept that any temporal signal can be represented by a Fourier series of weighted sinusoids. A sinusoidal phantom was developed by varying the concentration of iodine as successive steps of a sine wave. Each step corresponding to a different dilution of iodine contrast solution contained in partitions along a cylinder. By translating the phantom along the axis at different velocities, sinusoidal signals at different frequencies were generated. Using their image acquisition and reconstruction algorithm, these sinusoidal signals were imaged with a C-Arm system and the 3D volumes were reconstructed. The average value in a slice was plotted as a function of time. The phantom was also imaged using a clinical CT system with 0.5 s rotation. C-Arm CBCT results using 6, 3, 2, and 1 scan sequences were compared to those obtained using CT. Data were compared for linear velocities of the phantom ranging from 0.6 to 1 cms. This covers the temporal frequencies up to 0.16 Hz corresponding to a frequency range within which 99 of the spectral energy for all temporal signals in cerebral perfusion imaging is contained. Results: The errors in measurement of temporal frequencies are mostly below 2 for all multiscan sequences. For single scan sequences, the errors increase sharply beyond 0.10 Hz. The amplitude errors increase with frequency and with decrease in the number of scans used. Conclusions: Our multiscan perfusion CT approach allows low errors in signal frequency measurement. Increasing the number of scans reduces the amplitude errors. A two-scan sequence appears to offer the best compromise between accuracy and the associated total x-ray and iodine dose. © 2012 American Association of Physicists in Medicine.},
author = {Ganguly, A. and Fieselmann, Andreas and Boese, J. and Rohkohl, Christopher and Hornegger, Joachim and Fahrig, R.},
doi = {10.1118/1.4757910},
faupublication = {yes},
journal = {Medical Physics},
pages = {6652-6659},
peerreviewed = {Yes},
title = {{In} vitro evaluation of the imaging accuracy of {C}-{Arm} conebeam {CT} in cerebral perfusion imaging},
volume = {39},
year = {2012}
}
@inproceedings{faucris.118422524,
author = {Groch, Anja and Hempel, Sarah-Marie and Speidel, Stefanie and Höller, Kurt Emmerich and Engelbrecht, Rainer and Penne, Jochen and Seitel, Alexander and Röhl, Sebastian and Yung, Kwong and Bodenstedt, Sebastian and Pflaum, Felix and Kilgus, Thomas and Meinzer, Stefan and Hornegger, Joachim and Maier-Hein, Lena},
booktitle = {Workshop Bildverarbeitung für die Medizin},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2011.tech.IE.LEH.invitr},
pages = {184-188},
peerreviewed = {unknown},
title = {{In}-vitro {Evaluation} von endoskopischer {Oberflächenrekonstruktion} mittels {Time}-of-{Flight}-{Kameratechnik}},
venue = {Lübeck},
year = {2011}
}
@article{faucris.121154044,
abstract = {Swept source/Fourier domain OCT is demonstrated for in vivo imaging of the rodent eye. Using commercial swept laser technology, we developed a prototype OCT imaging system for small animal ocular imaging operating in the 1050 nm wavelength range at an axial scan rate of 100 kHz with ~6 μm axial resolution. The high imaging speed enables volumetric imaging with high axial scan densities, measuring high flow velocities in vessels, and repeated volumetric imaging over time. The 1050 nm wavelength light provides increased penetration into tissue compared to standard commercial OCT systems at 850 nm. The long imaging range enables multiple operating modes for imaging the retina, posterior eye, as well as anterior eye and full eye length. A registration algorithm using orthogonally scanned OCT volumetric data sets which can correct motion on a per A-scan basis is applied to compensate motion and merge motion corrected volumetric data for enhanced OCT image quality. Ultrahigh speed swept source OCT is a promising technique for imaging the rodent eye, proving comprehensive information on the cornea, anterior segment, lens, vitreous, posterior segment, retina and choroid. © 2013 Optical Society of America.},
author = {Liu, Jonathan J. and Grulkowski, Ireneusz and Kraus, Martin and Potsaid, Benjamin and Lu, Chen D. and Baumann, Bernhard and Duker, Jay S. and Hornegger, Joachim and Fujimoto, James G.},
doi = {10.1364/BOE.4.000351},
faupublication = {yes},
journal = {Biomedical Optics Express},
pages = {351-363},
peerreviewed = {Yes},
title = {{In} vivo imaging of the rodent eye with swept source/{Fourier} domain {OCT}},
volume = {4},
year = {2013}
}
@article{faucris.122514084,
author = {Wang, Bo and Nevins, Jessica E. and Nadler, Zach and Wollstein, Gadi and Ishikawa, Hiroshi and Bilonick, Richard A. and Kagemann, Larry and Sigal, Ian A. and Grulkowski, Ireneusz and Liu, Jonathan J. and Kraus, Martin and Lu, Chen D. and Hornegger, Joachim and Fujimoto, James G. and Schuman, Joel S.},
doi = {10.1167/iovs.13-13109},
faupublication = {yes},
journal = {Investigative Ophthalmology & Visual Science},
keywords = {lamina cribrosa;optical coherence tomography;glaucoma},
pages = {8270-8274},
peerreviewed = {Yes},
title = {{In} {Vivo} {Lamina} {Cribrosa} {Micro}-{Architecture} in {Healthy} and {Glaucomatous} {Eyes} as {Assessed} by {Optical} {Coherence} {Tomography}},
volume = {54},
year = {2013}
}
@inproceedings{faucris.237577645,
abstract = {Modern, state-of-the-art deep learning approaches yield human like performance in numerous object detection and classification tasks. The foundation for their success is the availability of training datasets of substantially high quantity, which are expensive to create, especially in the field of medical imaging. Crowdsourcing has been applied to create large datasets for a broad range of disciplines. This study aims to explore the challenges and opportunities of crowd-algorithm collaboration for the object detection task of grading cytology whole slide images. We compared the classical crowdsourcing performance of twenty participants with their results from crowd-algorithm collaboration. All participants performed both modes in random order on the same twenty images. Additionally, we introduced artificial systematic flaws into the precomputed annotations to estimate a bias towards accepting precomputed annotations. We gathered 9524 annotations on 800 images from twenty participants organised into four groups in concordance to their level of expertise with cytology. The crowd-algorithm mode improved on average the participants’ classification accuracy by 7%, the mean average precision by 8% and the inter-observer Fleiss’ kappa score by 20%, and reduced the time spent by 31%. However, two thirds of the artificially modified false labels were not recognised as such by the contributors. This study shows that crowd-algorithm collaboration is a promising new approach to generate large datasets when it is ensured that a carefully designed setup eliminates potential biases.},
author = {Marzahl, Christian and Aubreville, Marc and Bertram, Christof A. and Gerlach, Stefan and Maier, Jennifer and Voigt, Jörn and Hill, Jenny and Klopfleisch, Robert and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}5},
editor = {Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm},
faupublication = {yes},
isbn = {9783658292669},
note = {CRIS-Team Scopus Importer:2020-04-21},
pages = {26-31},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Is} crowd-algorithm collaboration an advanced alternative to crowd-sourcing on cytology slides?},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.276691300,
abstract = {Multitask learning has been a common technique for improving representations learned by artificial neural networks for decades. However, the actual effects and trade-offs are not much explored, especially in the context of document analysis. We demonstrate a simple and realistic scenario on real-world datasets that produces noticeably inferior results in a multitask learning setting than in a single-task setting. We hypothesize that slight data-manifold and task semantic shifts are sufficient to lead to adversarial competition of tasks inside networks and demonstrate this experimentally in two different multitask learning formulations.},
author = {Mattick, Alexander and Mayr, Martin and Maier, Andreas and Christlein, Vincent},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2022-05-22/2022-05-25},
doi = {10.1007/978-3-031-06555-2{\_}45},
editor = {Seiichi Uchida, Elisa Barney, Véronique Eglin},
faupublication = {yes},
isbn = {9783031065545},
keywords = {Deep learning; Document analysis; Document classification; Multitask learning},
note = {CRIS-Team Scopus Importer:2022-06-10},
pages = {674-687},
peerreviewed = {Yes},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Is} {Multitask} {Learning} {Always} {Better}?},
venue = {La Rochelle},
volume = {13237 LNCS},
year = {2022}
}
@inproceedings{faucris.217468113,
abstract = {An accurate position of the isocenter of a cone-beam CT trajectory is mandatory for accurate image reconstruction. For analytical backprojection algorithms, it is assumed that the X-ray source moves on a perfectly circular trajectory, which is not true for most practical clinical trajectories due to mechanical instabilities. Besides, the flexibility of novel robotic C-arm systems enables new trajectories where the computation of the isocenter might not be straight forward. An inaccurate isocenter position directly affects the computation of the redundancy weights and consequently affects the reconstructions immediately. In this work, we compare different methods for computing the isocenter of a non-ideal circular scan trajectory and evaluate their robustness in the presence of noise. The best results were achieved using a method based on a least-square-based fit. Furthermore, we show that an inaccurate isocenter computation can lead to artifacts in the reconstruction result. Therefore, this work highlights the importance of an accurate isocenter computation with the background of novel upcoming clinical trajectories.},
author = {Amri, Ahmed and Bier, Bastian and Maier, Jennifer and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}61},
editor = {Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658253257},
note = {CRIS-Team Scopus Importer:2019-05-14},
pages = {276-281},
peerreviewed = {unknown},
publisher = {Springer Berlin Heidelberg},
title = {{Isocenter} {Determination} from {Projection} {Matrices} of a {C}-{Arm} {CBCT}},
venue = {Lübeck},
year = {2019}
}
@inproceedings{faucris.107007164,
author = {Wetzl, Jens and Schmidt, Michaela and Zenge, Michael O. and Lugauer, Felix and Lazar, Laszlo and Nadar, Mariappan and Maier, Andreas and Hornegger, Joachim and Forman, Christoph},
booktitle = {Proceedings of the 23rd Annual Meeting of the ISMRM (ISMRM 2015)},
faupublication = {yes},
note = {UnivIS-Import:2015-07-08:Pub.2015.tech.IMMD.IMMD5.isotro},
pages = {1011},
title = {{Isotropic} 3-{D} {CINE} {Imaging} with {Sub}-2mm {Resolution} in a {Single} {Breath}-{Hold}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Wetzl15-I3C.pdf},
venue = {Toronto, Canada},
year = {2015}
}
@article{faucris.120206724,
abstract = {Rationale and Objectives. A statistical based iterative single-photon emission-computed tomography (SPECT) reconstruction algorithm (OSEM) modeling the depth-dependent collimator response in three dimensions has recently been introduced (OSEM3D). The aim of this study was to evaluate the axial shape fidelity of OSEM3D in comparison to OSEM, not taking this variable into account (OSEM2D). Materials and Methods. SPECT and separate spiral CT were performed in a phantom containing spheres filled with In-111. In-111-pentetreotide-SPECT and separate spiral-CT imaging were also performed in 22 patients with neuroendocrine tumors. Using window settings adapting the transversal size of the SPECT hot spots to that on CT and the 50% isocontour as boundary, the three-dimensional extensions (dx, dy, dz) of the SPECT representation of the structures under study were measured. These variables were also determined for CT. Furthermore, an index of eccentricity was calculated by averaging the ratios between dz and dx and dz and dy (IE). For isotropically imaged spheres, IE is 1. Results. For OSEM2D, IE was significantly different from 1 in the phantom data (P < .05); this was not the case for OSEM3D and CT. This finding was accounted for by a significantly greater dz on the OSEM2D-SPECT images. In the patient data, dz was by approximately 15.5% greater for OSEM2D than for the other two modalities (P < .05). Conclusions. The use of OSEM3D avoids deformation of hot SPECT lesions in z-direction. This may be of particular importance in SPECT/CT hybrid imaging capitalizing on the exact match of both modalities. © AUR, 2006.},
author = {Römer, Wolfgang and Reichel, Nicky and Vija, Hans and Nickel, Ingo and Hornegger, Joachim and Bautz, Werner and Kuwert, Torsten},
doi = {10.1016/j.acra.2005.12.004},
faupublication = {yes},
journal = {Academic Radiology},
pages = {496-502},
peerreviewed = {Yes},
title = {{Isotropic} reconstruction of {SPECT} data using {OSEM3D}: {Correlation} with {CT}},
volume = {13},
year = {2006}
}
@inproceedings{faucris.264575311,
abstract = {Speech is a biomarker extensively explored by the scientific community for different health-care applications because its reduced cost and non-intrusiveness. Specifically, in Parkinson’s disease, speech signals and deep learning methods have been explored for the automatic assessment and monitoring of patients. Related studies have shown to be very accurate to discriminate pathological vs. healthy speech. In spite of the high accuracies observed to detect the presence of diseases from speech, it is not clear which additional information about the speakers or the environment is implicitly learned by the deep learning systems. This study proposes a methodology to evaluate intermediate representations of a neural network in order to find out which other speaker traits and aspects are learned by the system during the training process. We trained models to detect the presence of Parkinson’s disease from speech. Then, we used intermediate representations of the network to classify additional speaker traits such as gender, age, and the native language. It is important to detect which information is available inside the neural network that can lead to open the black-box and to detect possible algorithmic biases. The results indicate that the network, in addition to adjusting its parameters for disease classification, also acquires knowledge about gender of the speakers in the first layers, and about speech tasks and the native language in the last layers of the network.},
author = {Rios-Urrego, C. D. and Vásquez-Correa, J. C. and Orozco-Arroyave, J. R. and Nöth, Elmar},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2021-09-06/2021-09-09},
doi = {10.1007/978-3-030-83527-9{\_}37},
editor = {Kamil Ekštein, František Pártl, Miloslav Konopík},
faupublication = {yes},
isbn = {9783030835262},
keywords = {Deep learning; Neural networks; Parkinson’s disease; Pathological speech; Speech processing},
note = {CRIS-Team Scopus Importer:2021-10-01},
pages = {435-447},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Is} {There} {Any} {Additional} {Information} in a {Neural} {Network} {Trained} for {Pathological} {Speech} {Classification}?},
venue = {Olomouc},
volume = {12848 LNAI},
year = {2021}
}
@inproceedings{faucris.269970562,
abstract = {The successful registration of digitized microscopic images is required for many applications in digital pathology. In particular, the registration of specimens scanned by different slide scanning systems may be beneficial to transfer expert annotations from one image domain to another and thereby reduce labeling effort. We present an iterative approach to register microscopic specimens digitized with multiple scanning systems, aiming to compute an optimal global transformation for the images at highest resolution. For this purpose, an initial registration based on a down-scaled version of the images is followed by a patch-based iterative update scheme. We make use of the hierarchical structure of digitized whole slide images to gradually approximate the optimal transformation. By using kernel density estimation to weight local transformation estimates, the influence of registration errors can be further mitigated. We validate our method on five histologic and five cytologic samples, each scanned with four different scanning systems. Furthermore, we perform first experiments on samples stained with different stain combinations. Our experiments demonstrate the potential of the proposed method for a variety of datasets and application fields.
The fusion of multiple recognition engines is known to be able to outperform individual ones, given sufficient independence of methods, models, and knowledge sources. We therefore investigate late fusion of different speech-based recognizers of emotion. Two generally different streams of information are considered: acoustics and linguistics fed by state-of-the-art automatic speech recognition. A total of five emotion recognition engines from different sites that provide heterogeneous output information are integrated by either simple democratic vote or learning ‘which predictor to trust when’. We are able to significantly outperform the best individual engine by fusion, and the so far best reported result on the recently introduced Emotion Challenge task.
},
author = {Schuller, Björn and Metze, Florian and Steidl, Stefan and Batliner, Anton and Eyben, Florian and Polzehl, Tim},
booktitle = {Proceedings of ICASSP},
date = {2010-03-14/2010-03-19},
editor = {ICASSP},
faupublication = {yes},
keywords = {emotion recognition; late fusion; speech analysis},
pages = {5230-5233},
peerreviewed = {Yes},
title = {{Late} {Fusion} of {Individual} {Engines} for {Improved} {Recognition} of {Negative} {Emotion} in {Speech} - {Learning} vs. {Democratic} {Vote}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Schuller10-LFO.pdf},
venue = {Dallas},
year = {2010}
}
@article{faucris.111731224,
author = {Fattahi, Ehsan and Waluga, Christian and Wohlmuth, B. I. and Rüde, Ulrich and Manhart, Michael and Helmig, Rainer},
doi = {10.1016/j.compfluid.2016.10.007},
faupublication = {yes},
journal = {Computers & Fluids},
pages = {247-259},
peerreviewed = {Yes},
title = {{Lattice} {Boltzmann} methods in porous media simulations: {From} laminar to turbulent flow},
url = {http://www.sciencedirect.com/science/article/pii/S0045793016303061},
volume = {140},
year = {2016}
}
@inproceedings{faucris.118387764,
address = {Springer},
author = {Mehmood, Ehsan and Fischer, Peter and Pohl, Thomas and Horz, Tim and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0{\_}22},
faupublication = {yes},
isbn = {9783662543443},
note = {UnivIS-Import:2017-07-10:Pub.2017.tech.IMMD.IMMD5.layere},
pages = {74-79},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Layered} {X}-ray {Motion} {Estimation} using {Primal}-{Dual} {Optimization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Mehmood17-LXM.pdf},
venue = {Heidelberg},
year = {2017}
}
@article{faucris.243946614,
abstract = {Minimally invasive procedures rely on image guidance for navigation at the operation site to avoid large surgical incisions. X-ray images are often used for guidance, but important structures may be not well visible. These structures can be overlaid from pre-operative 3-D images and accurate alignment can be established using 2-D/3-D registration. Registration based on the point-to-plane correspondence model was recently proposed and shown to achieve state-of-the-art performance. However, registration may still fail in challenging cases due to a large portion of outliers. In this paper, we describe a learning-based correspondence weighting scheme to improve the registration performance. By learning an attention model, inlier correspondences get higher attention in the motion estimation while the outlier correspondences are suppressed. Instead of using per-correspondence labels, our objective function allows to train the model directly by minimizing the registration error. We demonstrate a highly increased robustness, e.g. increasing the success rate from 84.9% to 97.0% for spine registration. In contrast to previously proposed learning-based methods, we also achieve a high accuracy of around 0.5mm mean re-projection distance. In addition, our method requires a relatively small amount of training data, is able to learn from simulated data, and generalizes to images with additional structures which are not present during training. Furthermore, a single model can be trained for both, different views and different anatomical structures.},
author = {Schaffert, Roman and Wang, Jian and Fischer, Peter and Borsdorf, Anja and Maier, Andreas},
doi = {10.1109/TMI.2020.2988410},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
note = {CRIS-Team WoS Importer:2020-10-16},
pages = {3159-3174},
peerreviewed = {Yes},
title = {{Learning} an {Attention} {Model} for {Robust} 2-{D}/3-{D} {Registration} {Using} {Point}-{To}-{Plane} {Correspondences}},
volume = {39},
year = {2020}
}
@inproceedings{faucris.237576629,
abstract = {In many minimally invasive procedures, image guidance using a C-arm system is utilized. To enhance the guidance, information from pre-operative 3-D images can be overlaid on top of the 2-D fluoroscopy and 2-D/3-D image registration techniques are used to ensure an accurate overlay. Despite decades of research, achieving a highly reliable registration remains challenging. In this paper, we propose a learning-based correspondence estimation, which focuses on contour points and can be used in combination with the point-to-plane correspondence model-based registration. When combined with classical correspondence estimation in a refinement step, the method highly increases the robustness, leading to a capture range of 36mm and a success rate of 98.5%, compared to 14mm and 71.9% for the purely classical approach, while maintaining a high accuracy of 0.430.08mm of mean re-projection distance.},
author = {Schaffert, Roman and Weiß, Markus and Wang, Jian and Borsdorf, Anja and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}50},
editor = {Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm},
faupublication = {yes},
isbn = {9783658292669},
note = {CRIS-Team Scopus Importer:2020-04-21},
pages = {222-228},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Learning}-based correspondence estimation for 2-{D}/3-{D} registration},
venue = {Berlin, DEU},
year = {2020}
}
@inproceedings{faucris.237575866,
abstract = {In minimally invasive procedures, a standard routine of observing the operational site is using image guidance. X-ray fluoroscopy using C-arm systems is widely used. In complex cases, overlays of preoperative 3-D images are necessary to show structures that are not visible in the 2-D X-ray images. The alignment quality may degenerate during an intervention, e. g. due to patient motion, and a new registration needs to be performed. However, a decrease in alignment quality is not always obvious, as the clinician often focuses on structures which are not visible in the 2-D image, and only these structures are visualized in the overlay. In this paper, we propose a learning-based method for detecting different degrees of misalignment. The method is based on point-to-plane correspondences and a pre-trained neural network originally used for detecting good correspondences. The network is extended by a classification branch to detect different levels of misalignment. Compared to simply using the normalized gradient correlation similarity measure as a basis for the decision, we show a highly improved performance, e. g. improving the AUC score from 0.918 to 0.993 for detecting misalignment above 5mm of mean re-projection distance.},
author = {Schaffert, Roman and Wang, Jian and Fischer, Peter and Borsdorf, Anja and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}52},
editor = {Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm},
faupublication = {yes},
isbn = {9783658292669},
note = {CRIS-Team Scopus Importer:2020-04-21},
pages = {230-235},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Learning}-based misalignment detection for 2-{D}/3-{D} overlays},
venue = {Berlin},
year = {2020}
}
@book{faucris.120207164,
abstract = {The need for non-rigid multi-modal registration is becoming increasingly common for many clinical applications. To date, however, existing proposed techniques remain as largely academic research effort with very few methods being validated for clinical product use. It has been suggested by Crum et al. [1] that the context-free nature of these methods is one of the main limitations and that moving towards context-specific methods by incorporating prior knowledge of the underlying registration problem is necessary to achieve registration results that are accurate and robust enough for clinical applications. In this paper, we propose a novel non-rigid multi-modal registration method using a variational formulation that incorporates a prior learned joint intensity distribution. The registration is achieved by simultaneously minimizing the Kullback-Leibler divergence between an observed and a learned joint intensity distribution and maximizing the mutual information between reference and alignment images. We have applied our proposed method on both synthetic and real images with encouraging results. © Springer-Verlag Berlin Heidelberg 2005.},
address = {Berlin/Heidelberg},
author = {Gütter, Christoph and Xu, Chenyang and Sauer, Frank and Hornegger, Joachim},
doi = {10.1007/11566489{\_}32},
faupublication = {yes},
isbn = {3-540-29326-4},
note = {UnivIS-Import:2015-04-16:Pub.2005.tech.IMMD.IMMD5.learni},
pages = {255-262},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Learning} based non-rigid multi-modal image registration using {Kullback}-{Leibler} divergence},
volume = {2},
year = {2005}
}
@article{faucris.272200103,
abstract = {Objective. During x-ray-guided interventional procedures, the medical staff is exposed to scattered ionizing radiation caused by the patient. To increase the staff's awareness of the invisible radiation and monitor dose online, computational scatter estimation methods are convenient. However, such methods are usually based on Monte Carlo (MC) simulations, which are inherently computationally expensive. Yet, in the interventional environment, immediate feedback to the personnel is desirable. Approach. In this work, we propose deep neural networks to mitigate the computational effort of MC simulations. Our learning-based models consider detailed models of the (outer) patient shape and (inner) anatomy, additional objects in the room, and the x-ray tube spectrum to cover imaging settings encountered in real interventional settings. We investigate two cases of scatter prediction. First, we employ network architectures to estimate the full three-dimensional (3D) scatter distribution. Second, we investigate the prediction of two-dimensional (2D) intensity projections that facilitate the intra-procedural visualization. Main results. Depending on the dimensionality of the estimated scatter distribution and the network architecture, the mean relative error of each network is in the range of 12% and 14% compared to MC simulations. However, 3D scatter distributions can be estimated within 60 ms and 2D distributions within 15 ms. Significance. Overall, our method is suitable to support the online assessment of scattered ionizing radiation in the interventional environment and can help to lower the occupational radiation risk.},
author = {Maul, Noah and Roser, Philipp and Birkhold, Annette and Kowarschik, Markus and Zhong, Xia and Strobel, Norbert and Maier, Andreas},
doi = {10.1088/1361-6560/ac58dc},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
note = {CRIS-Team WoS Importer:2022-04-01},
peerreviewed = {Yes},
title = {{Learning}-based occupational x-ray scatter estimation},
volume = {67},
year = {2022}
}
@inproceedings{faucris.120193304,
abstract = {Disorders of the heart valves constitute a considerable health problem and often require surgical intervention. Recently various approaches were published seeking to overcome the shortcomings of current clinical practice,that still relies on manually performed measurements for performance assessment. Clinical decisions are still based on generic information from clinical guidelines and publications and personal experience of clinicians. We present a framework for retrieval and decision support using learning based discriminative distance functions and visualization of patient similarity with relative neighborhood graphsbased on shape and derived features. We considered two learning based techniques, namely learning from equivalence constraints and the intrinsic Random Forest distance. The generic approach enables for learning arbitrary user-defined concepts of similarity depending on the application. This is demonstrated with the proposed applications, including automated diagnosis and interventional suitability classification, where classification rates of up to 88.9% and 85.9% could be observed on a set of valve models from 288 and 102 patients respectively. © 2010 Copyright SPIE - The International Society for Optical Engineering.},
author = {Voigt, Ingmar and Vitanovski, Dime and Ionasec, Razvan Ioan and Tsymbal, Alexey and Georgescu, Bogdan and Zhou, S. Kevin and Huber, Martin and Navab, Nassir and Hornegger, Joachim and Comaniciu, Dorin},
booktitle = {Medical Imaging 2010: Image Processing},
doi = {10.1117/12.843972},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Learning} discriminative distance functions for valve retrieval and improved decision support in valvular heart disease},
venue = {San Diego, CA},
volume = {7623},
year = {2010}
}
@inproceedings{faucris.121179564,
abstract = {Congenital heart defect (CHD) is the most common birth defect and a frequent cause of death for children. Tetralogy of Fallot (ToF) is the most often occurring CHD which affects in particular the pulmonary valve and trunk. Emerging interventional methods enable percutaneous pulmonary valve implantation, which constitute an alternative to open heart surgery. While minimal invasive methods become common practice, imaging and non-invasive assessment tools become crucial components in the clinical setting. Cardiac computed tomography (CT) and cardiac magnetic resonance imaging (cMRI) are techniques with complementary properties and ability to acquire multiple non-invasive and accurate scans required for advance evaluation and therapy planning. In contrary to CT which covers the full 4D information over the cardiac cycle, cMRI often acquires partial information, for example only one 3D scan of the whole heart in the end-diastolic phase and two 2D planes (long and short axes) over the whole cardiac cycle. The data acquired in this way is called sparse cMRI. In this paper, we propose a regression-based approach for the reconstruction of the full 4D pulmonary trunk model from sparse MRI. The reconstruction approach is based on learning a distance function between the sparse MRI which needs to be completed and the 4D CT data with the full information used as the training set. The distance is based on the intrinsic Random Forest similarity which is learnt for the corresponding regression problem of predicting coordinates of unseen mesh points. Extensive experiments performed on 80 cardiac CT and MR sequences demonstrated the average speed of 10 seconds and accuracy of 0.1053mm mean absolute error for the proposed approach. Using the case retrieval workflow and local nearest neighbour regression with the learnt distance function appears to be competitive with respect to "black box" regression with immediate prediction of coordinates, while providing transparency to the predictions made. © 2011 SPIE.},
author = {Vitanovski, Dime and Tsymbal, Alexey and Ionasec, Razvan and Georgescu, Bogdan and Zhou, Shaohua K. and Hornegger, Joachim and Comaniciu, Dorin},
booktitle = {Medical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling},
doi = {10.1117/12.878195},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Learning} distance function for regression-based {4D} pulmonary trunk model reconstruction estimated from sparse {MRI} data},
venue = {Lake Buena Vista, FL},
volume = {7964},
year = {2011}
}
@inproceedings{faucris.217645019,
abstract = {Magnetic resonance imaging (MRI) enables 3-D imaging of anatomical structures. However, the acquisition of MR volumes with high spatial resolution leads to long scan times. To this end, we propose volumetric super-resolution forests (VSRF) to enhance MRI resolution retrospectively. Our method learns a locally linear mapping between low-resolution and high-resolution volumetric image patches by employing random forest regression. We customize features suitable for volumetric MRI to train the random forest and propose a median tree ensemble for robust regression. VSRF outperforms state-of-the-art example-based super-resolution in terms of image quality and efficiency for model training and inference on different MRI datasets. It is also superior to unsupervised methods with just a handful or even a single volume to assemble training data.
∘
× 90
∘
. Results: On synthetic data, a mean prediction error of 5.6 ± 4.5 mm is achieved. Further, we demonstrate that the trained model can be directly applied to real X-rays and show that these detections define correspondences to a respective CT volume, which allows for analytic estimation of the 11 degree of freedom projective mapping. Conclusion: We present the first tool to detect anatomical landmarks in X-ray images independent of their viewing direction. Access to this information during surgery may benefit decision making and constitutes a first step toward global initialization of 2D/3D registration without the need of calibration. As such, the proposed concept has a strong prospect to facilitate and enhance applications and methods in the realm of image-guided surgery.},
author = {Bier, Bastian and Goldmann, Florian and Zaech, Jan Nico and Fotouhi, Javad and Hegeman, Rachel and Grupp, Robert and Armand, Mehran and Osgood, Greg and Navab, Nassir and Maier, Andreas and Unberath, Mathias},
doi = {10.1007/s11548-019-01975-5},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {2D/3D registration; Anatomical landmarks; Convolutional neural networks; Landmark detection},
note = {CRIS-Team Scopus Importer:2019-05-02},
peerreviewed = {Yes},
title = {{Learning} to detect anatomical landmarks of the pelvis in {X}-rays from arbitrary views},
year = {2019}
}
@inproceedings{faucris.121324544,
address = {-},
author = {Denzler, Joachim and Beß, Rüdiger and Hornegger, Joachim and Niemann, Heinrich and Paulus, Dietrich},
booktitle = {International Conference on Intelligent Robots and Systems},
date = {1994-09-12/1994-09-16},
doi = {10.1109/IROS.1994.407405},
editor = {-},
faupublication = {yes},
pages = {89-96},
peerreviewed = {unknown},
publisher = {-},
title = {{Learning}, {Tracking} and {Recognition} of {3D} {Objects}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1994/Denzler94-LTA.pdf},
venue = {München},
year = {1994}
}
@article{faucris.229543888,
abstract = {We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suited for our framework. We derive a maximal error bound for deep nets that demonstrates that inclusion of prior knowledge results in its reduction. Furthermore, we also show experimentally that known operators reduce the number of free parameters. We apply this approach to various tasks ranging from CT image reconstruction over vessel segmentation to the derivation of previously unknown imaging algorithms. As such the concept is widely applicable for many researchers in physics, imaging, and signal processing. We assume that our analysis will support further investigation of known operators in other fields of physics, imaging, and signal processing.},
author = {Maier, Andreas and Syben-Leisner, Christopher and Stimpel, Bernhard and Würfl, Tobias and Hoffmann, Mathis and Schebesch, Frank and Fu, Weilin and Mill, Leonid and Kling, Lasse and Christiansen, Silke H.},
doi = {10.1038/s42256-019-0077-5},
faupublication = {yes},
journal = {Nature Machine Intelligence},
pages = {373-380},
peerreviewed = {Yes},
title = {{Learning} with {Known} {Operators} reduces {Maximum} {Training} {Error} {Bounds}.},
volume = {1},
year = {2019}
}
@inproceedings{faucris.245490187,
abstract = {Ischaemic heart disease is the number one cause of death world wide, which is in close relation with heart failure. If patients suffer from drug-refractory heart failure with a reduced ejection fraction, cardiac resynchronization therapy is a treatment option. For planning the procedure, precise information about the left ventricle's anatomy and scar distribution is required. The clinical gold standard to visualize scar is late gadolinium enhanced magnetic resonance imaging (LGE-MRI). The challenge arises in the myocardium segmentation of these sequences which is a pre-requisite for an accurate scar quantification. In this work, we compare a filter based approach against a learning based approach for LGE-MRI segmentation. For both approaches the segmentation workflow consists of four major steps. First, the left ventricle is detected. Second, the blood pool is estimated. Third, the endocardium is refined using scar information. Fourth, the epicardium is extracted.The proposed methods were evaluated on 100 clinical LGE-MRI data sets. For the learning based approach a 5-fold nested cross-validation is applied to evaluate the hyper-parameters. The learning based segmentation achieves slightly better results, with a Dice score of 0.82 ± 0.09 for the endocard and 0.81 ± 0.08 for the epicard.},
author = {Kurzendorfer, Tanja and Breininger, Katharina and Steidl, Stefan and Brost, Alexander and Forman, Christoph and Maier, Andreas},
booktitle = {2018 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2018 - Proceedings},
date = {2018-11-10/2018-11-17},
doi = {10.1109/NSSMIC.2018.8824478},
faupublication = {yes},
isbn = {9781538684948},
note = {CRIS-Team Scopus Importer:2020-11-20},
peerreviewed = {unknown},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
title = {{Left} {Ventricle} {Segmentation} in {LGE}-{MRI}: {Filter} {Based} vs. {Learning} {Based}},
venue = {Sydney, NSW},
year = {2018}
}
@inproceedings{faucris.222101746,
abstract = {Cardiovascular diseases are the major cause of death worldwide. Magnetic resonance imaging (MRI) is often used for the diagnosis of cardiac diseases because of its good soft tissue contrast. Furthermore, the fibrosis characterization of the myocardium can be important for accurate diagnosis and treatment planning. The clinical gold standard to visualize myocardial scarring is late gadolinium enhanced (LGE) MRI. However, the challenge arises in the accurate segmentation of the endocardial and epicardial border because of the smooth transition between the blood pool and scarred myocardium, as contrast agent accumulates in the damaged tissue and leads to hyper-enhancements. An exact segmentation, is essential for the scar tissue quantification. We propose a deep learning-based method to segment the left ventricle's endocardium and epicardium in LGE-MRI. To this end, a multi-scale fully convolutional neural network with skip-connections (U-Net) and residual units is applied to solve the multiclass segmentation problem. As a loss function, weighted cross-entropy is used. The network is trained on 70 clinical LGE MRI sequences, validated with 5, and evaluated with 26 data sets. The approach yields a mean Dice coefficient of 0.90 for the endocard and 0.87 for the epicard. The proposed method segments the endocardium and epicardium of the left ventricle fully automatically with a high accuracy.},
author = {Kurzendorfer, Tanja and Breininger, Katharina and Steidl, Stefan and Maier, Andreas and Fahrig, Rebecca},
booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
date = {2019-02-19/2019-02-21},
doi = {10.1117/12.2511610},
editor = {Bennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini},
faupublication = {yes},
isbn = {9781510625457},
keywords = {Convolutional Neural Network; Late Gadolinium Enhanced; Left Ventricle; Segmentation},
note = {CRIS-Team Scopus Importer:2019-07-12},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{Left} ventricle segmentation in {LGE}-{MRI} using multiclass learning},
venue = {San Diego, CA},
volume = {10949},
year = {2019}
}
@inproceedings{faucris.122496484,
abstract = {In interventional cardiology, three-dimensional anatomical and functional information of the cardiac chambers, e.g. the left ventricle, would have an important impact on diagnosis and therapy. With the technology of C-arm CT it is possible to reconstruct intraprocedural 3-D images from angiographic projection data. Due to the long acquisition time of several seconds, motion-related artifacts, like blurring or streaks, occur. Therefore, the heart dynamics need to be taken into account in order to improve the reconstruction results. When it comes to the evaluation of different motion estimation and compensation algorithms and techniques of motion analysis, there is still a lack of comparability of the final reconstructions and motion parameters between the research groups. Since the results are heavily dependent on the applied motion pattern and simulation parameters, the experiments are not reproducible. We try to overcome these problems by providing varying left heart ventricle phantom datasets, consisting of projection images as well as extracted surface meshes. Up to now, there are six different datasets available: one with a normal sinus rhythm, one with a normal sinus rhythm and a catheter, one with a lateral wall defect of the ventricle, two with a lateral contraction phase shift and one without any motion. The existing datasets are based on a phantom similar to the 4D XCAT phantom with a contrasted left ventricle, myocardium, and aorta. The geometry calibration and acquisition protocol from a real clinical C-arm scanner are used. A webpage is provided where the data and the necessary files are publicly available for download at conrad.stanford.edu/data/heart. © 2013 IEEE.},
author = {Müller, Kerstin and Maier, Andreas and Fischer, Peter and Bier, Bastian and Lauritsch, Günter and Schwemmer, Chris and Fahrig, Rebecca and Hornegger, Joachim},
booktitle = {2013 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC)},
date = {2013-10-27/2013-11-02},
doi = {10.1109/NSSMIC.2013.6829255},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2013.tech.IMMD.IMMD5.leftve{\_}0},
title = {{Left} {Ventricular} {Heart} {Phantom} for {Wall} {Motion} {Analysis}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Mueller13-LVH.pdf},
venue = {Seoul, South Korea},
year = {2013}
}
@inproceedings{faucris.118387984,
author = {Hanif, Suneeza and Schebesch, Frank and Jerebko, Anna and Ritschl, Ludwig and Mertelmeier, Thomas and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2017 - Algorithmen, Systeme, Anwendungen},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0{\_}55},
faupublication = {yes},
isbn = {9783662543443},
note = {UnivIS-Import:2017-07-10:Pub.2017.tech.IMMD.IMMD5.lesion},
pages = {243-248},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Lesion} {Ground} {Truth} {Estimation} for a {Physical} {Breast} {Phantom}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Hanif17-LGT.pdf},
venue = {Heidelberg},
year = {2017}
}
@inproceedings{faucris.239526734,
abstract = {Deep-learning based noise reduction algorithms have proven their success
especially for non-stationary noises, which makes it desirable to also use them
for embedded devices like hearing aids (HAs). This, however, is currently not
possible with state-of-the-art methods. They either require a lot of parameters
and computational power and thus are only feasible using modern CPUs. Or they
are not suitable for online processing, which requires constraints like
low-latency by the filter bank and the algorithm itself.
In this work, we propose a mask-based noise reduction approach. Using
hierarchical recurrent neural networks, we are able to drastically reduce the
number of neurons per layer while including temporal context via hierarchical
connections. This allows us to optimize our model towards a minimum number of
parameters and floating-point operations (FLOPs), while preserving noise
reduction quality compared to previous work. Our smallest network contains only
5k parameters, which makes this algorithm applicable on embedded devices. We
evaluate our model on a mixture of EUROM and a real-world noise database and
report objective metrics on unseen noise.},
author = {Schröter, Hendrik and Rosenkranz, Tobias and Escalante Banuelos, Alberto and Zobel, Pascal and Maier, Andreas},
booktitle = {INTERSPEECH 2020},
date = {2020-10-25/2020-10-29},
doi = {10.21437/interspeech.2020-1131},
faupublication = {yes},
keywords = {speech enhancement, noise reduction, recurrent neural networks},
peerreviewed = {unknown},
title = {{Lightweight} {Online} {Noise} {Reduction} on {Embedded} {Devices} using {Hierarchical} {Recurrent} {Neural} {Networks}},
url = {https://arxiv.org/abs/2006.13067},
venue = {Shanghai},
year = {2020}
}
@article{faucris.231901467,
abstract = {In transmission X-ray microscopy (TXM) systems, the rotation of a scanned sample might be restricted to a limited angular range to avoid collision to other system parts or high attenuation at certain tilting angles. Image reconstruction from such limited angle data suffers from artifacts due to missing data. In this work, deep learning is applied to limited angle reconstruction in TXMs for the first time. With the challenge to obtain sufficient real data for training, training a deep neural network from synthetic data is investigated. Particularly, the U-Net, the state-of-the-art neural network in biomedical imaging, is trained from synthetic ellipsoid data and multi-category data to reduce artifacts in filtered back-projection (FBP) reconstruction images.
The proposed method is evaluated on synthetic data and real scanned chlorella data in 100-degree limited angle tomography. For synthetic test data, the U-Net significantly reduces root-mean-square error (RMSE) from 2.55 X 10^{-3}/μm in the FBP reconstruction to 1.21 X 10^{-3}/μm in the U-Net reconstruction, and also improves structural similarity (SSIM) index from 0.625 to 0.920. With penalized weighted least square denoising of measured projections, the RMSE and SSIM are further improved to 1.16 X 10^{-3}/μm and 0.932, respectively.
For real test data, the proposed method remarkably improves the 3-D visualization of the subcellular structures in the chlorella cell, which indicates its important value for nano-scale imaging in biology, nanoscience and materials scienc},
author = {Huang, Yixing and Wang, Shengxiang and Guan, Yong and Maier, Andreas},
doi = {10.1107/S160057752000017X},
faupublication = {yes},
journal = {Journal of Synchrotron Radiation},
keywords = {Transmission X-Ray Microscopy; deep learning; limited angle tomography},
month = {Jan},
peerreviewed = {Yes},
title = {{Limited} {Angle} {Tomography} for {Transmission} {X}-{Ray} {Microscopy} {Using} {Deep} {Learning}},
url = {https://onlinelibrary.wiley.com/iucr/doi/10.1107/S160057752000017X},
year = {2020}
}
@inproceedings{faucris.120325964,
address = {-},
author = {Paulus, Dietrich and Hornegger, Joachim and Csink, Laszlo},
booktitle = {8. Workshop Farbbildverarbeitung},
date = {2002-10-10/2002-10-11},
editor = {Franke K.-H.},
faupublication = {yes},
pages = {3-10},
peerreviewed = {unknown},
publisher = {-},
title = {{Linear} approximation of sensitivity curve calibration},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2002/Paulus02-LAO.pdf},
venue = {Ilmenau},
year = {2002}
}
@inproceedings{faucris.108123224,
abstract = {This paper describes the acquisition, transcription and annotation of a multi-media corpus of academic spoken English, the LMELectures. It consists of two lecture series that were read in the summer term 2009 at the computer science department of the University of Erlangen- Nuremberg, covering topics in pattern analysis, machine learning and interventional medical image processing. In total, about 40 hours of high-definition audio and video of a single speaker was acquired in a constant recording environment. In addition to the recordings, the presentation slides are available in machine readable (PDF) format. The manual annotations include a suggested segmentation into speech turns and a complete manual transcription that was done using BLITZSCRIBE2, a new tool for the rapid transcription. For one lecture series, the lecturer assigned key words to each recordings; one recording of that series was further annotated with a list of ranked key phrases by five human annotators each. The corpus is available for non-commercial purpose upon request.},
author = {Riedhammer, Korbinian Thomas and Gropp, Martin and Bocklet, Tobias and Hönig, Florian Thomas and Nöth, Elmar and Steidl, Stefan},
booktitle = {Proceedings of the First Workshop on Speech, Language and Audio in Multimedia},
date = {2013-08-22/2013-08-23},
editor = {ISCA SIG on Speech and Language in Multimedia IEEE SIG on Audio and Speech Processing in Multimedia},
faupublication = {yes},
keywords = {Academic spoken English; Corpus description; E-learning},
pages = {102-107},
peerreviewed = {unknown},
publisher = {CEUR-WS},
title = {{LMELectures}: a {Multimedia} {Corpus} of {Acedemic} {Spoken} {English}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Riedhammer13-LAM.pdf},
venue = {Marseille},
year = {2013}
}
@article{faucris.121225764,
abstract = {Due to the loss of range information, projections as input data for a 3-D object recognition algorithm are expected to increase the computational complexity. In this work, however, we demonstrate that this deficiency carries potential for complexity reduction of major vision problems. We show that projections provide a reduction of feature dimensions, and lead to structures exhibiting simple combinatorial properties. The theoretical framework is embedded in a probabilistic setting which deals with uncertainties and variations of observed features. In statistics marginal densities and the assumption of independency prove to be the key tools when one encounters projections. The examples discussed in this paper include feature matching, pose estimation as well as classification of 3-D objects. The final experimental evaluation demonstrates the practical importance of the marginalization concept and independency assumptions. © 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.},
author = {Hornegger, Joachim and Welker, Volkmar and Niemann, Heinrich},
doi = {10.1016/S0031-3203(01)00122-4},
faupublication = {yes},
journal = {Pattern Recognition},
pages = {1225-1235},
peerreviewed = {Yes},
title = {{Localization} and classification based on projections},
volume = {35},
year = {2002}
}
@inproceedings{faucris.120197484,
abstract = {In X-ray Computed Tomography (CT) the measured projections and consequently the reconstructed CT images are subject to quantum and electronics noise. While noise in the projections can be well described and estimated with a corresponding physics model, the distribution of noise in the reconstructed CT images is not directly evident. Due to attenuation variations along different directions, the nature of noise in CT images is non-stationary and non-isotropic. This complicates the direct application of standard post-processing methods like bilateral filtering. In this article we describe a possibility to compute precise orientation dependent noise estimates for every pixel position. This is done by analytic propagation of projection noise estimates through indirect fan-beam filtered backprojection reconstruction. The resulting orientation dependent image noise estimates are subsequently used in adaptive bilateral filters. Taking into account the non-stationary and non-isotropic nature of noise in CT images, a reduction in image noise of about 55% compared to 39% of the standard approach is achieved with much less variability over different image regions. ©2009 IEEE.},
author = {Borsdorf, Anja and Kappler, Steffen and Raupach, Rainer and Noo, Frederic and Hornegger, Joachim},
booktitle = {2009 IEEE Nuclear Science Symposium Conference Record, NSS/MIC 2009},
doi = {10.1109/NSSMIC.2009.5402090},
faupublication = {yes},
pages = {2472-2475},
peerreviewed = {unknown},
title = {{Local} orientation-dependent noise propagation for anisotropic denoising of {CT}-{Images}},
venue = {Orlando, FL},
volume = {null},
year = {2009}
}
@inproceedings{faucris.231367218,
abstract = {Non-rigid registration is essential for a wide range of clinical applications, such as intraoperative image-guidance and postoperative follow-up assessment, and longitudinal image analysis for disease diagnosis and monitoring. Vascular structures are a rich descriptor of the organ deformation, since it permeates through all organs within body. As vasculature differs in size, shape and topology, following surgical intervention/treatment or due to disease progression, non-rigid vessel matching remains a challenging task. Recently, hybrid mixture models (HdMM) have been applied to tackle this challenge, and demonstrate significant improvements in terms of accuracy and robustness relative to the state-of-the-art. However, the smoothness constraint enforced on the deformation field with this approach only accounts for the global topology of the vasculature, resulting in a reduced capacity to accurately match localized changes to vascular structures, and preserve local topology. In this work, we proposed a modified version of HdMM by formulating an adaptive kernel, to enforce a local smoothness constraint on the deformation field, henceforth referred to as HdMMad.
The proposed HdMMad framework is evaluated with cerebral and pulmonary vasculature, acquired retrospectively. The registration results for both data sets demonstrate that the proposed approach outperforms registration algorithms also designed to preserve local topology. Using HdMMad, around 80% of the initial registration error was reduced, for both data sets.
Tw
Two sets of linguistic features are developed: The first one to estimate if a single step in a dialogue between a human being and a machine is successful or not. The second set to classify dialogues as a whole. The features are based on Part-of-Speech-Labels (POS), word statistics and properties of turns and dialogues. Experiments were carried out on the SympaFly corpus, data from a real application in the flight booking domain. A single dialogue step could be classified with an accuracy of 83 % (class-wise averaged recognition rate). The recognition rate for whole dialogues was 85%.
},
address = {Berlin, Heidelberg},
author = {Steidl, Stefan and Hacker, Christian and Ruff, Christine and Batliner, Anton and Nöth, Elmar and Haas, Jürgen},
booktitle = {Text, Speech and Dialogue, 7th International Conference, TSD 2004, Czech Republic, September 8-11, 2004, Proceedings},
date = {2004-09-08/2004-09-11},
editor = {Sojka P., Kopecek I., Pala K.},
faupublication = {yes},
pages = {629-636},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Looking} at the {Last} two {Turns}, {I}'d {Say} this {Dialogue} is {Doomed} - {Measuring} {Dialogue} {Success}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Steidl04-LAT.pdf},
venue = {Brno},
year = {2004}
}
@article{faucris.121396484,
abstract = {Visual attention allocation of adolescent girls with and without an eating disorder while viewing body images of underweight, normal-weight and overweight women was studied using eye tracking. While all girls attended more to specific body parts (e.g. hips, upper legs), eating-disordered girls showed an attentional bias towards unclothed body parts.},
author = {Horndasch, Stefanie and Kratz, Oliver and Holczinger, Anna and Heinrich, Hartmut and Hönig, Florian Thomas and Nöth, Elmar and Moll, Gunther},
doi = {10.1016/j.psychres.2011.12.029},
faupublication = {yes},
journal = {Psychiatry Research},
keywords = {Eating disorder;Attentional bias;Eye tracking},
pages = {321-323},
peerreviewed = {Yes},
title = {"{Looks} do matter"-visual attentional biases in adolescent girls with eating disorders viewing body images},
volume = {198},
year = {2012}
}
@inproceedings{faucris.111777424,
abstract = {The design of a CT detector requires a precise detector model, since building prototypes for many different proposed detector geometries is too costly. We introduce a lookup table-based simulation of scintillation detectors on X-ray photon level. It uses energy-resolved sinograms of incoming X-ray intensities as input data and generates photon counts for each channel and reading. The effects of X-ray- and optical cross-talk, temporal cross-talk between readings, Poisson noise and electronics effects are covered. The photon interaction data as well as optical cross-talk distribution are provided in the form of detector specific look-up tables. Unlike standard MonteCarlo simulations of X-ray interaction processes, our approach is capable of simulating whole sinograms in a reasonable amount of time and still offers a very high precision of the detector model. This way the influence of detector effects can be investigated in the reconstructed image data. The simulation is verified against data measured with a CT scanner and data from a fully single photon-based Monte-Carlo simulation in terms of image modulation transfer function (MTF) and detector noise power spectrum (NPS). © 2008 IEEE.},
author = {Balda, Michael and Wirth, Stefan and Niederlöhner, Daniel and Heismann, Björn and Hornegger, Joachim},
booktitle = {2008 IEEE Nuclear Science Symposium Conference Record, NSS/MIC 2008},
doi = {10.1109/NSSMIC.2008.4774168},
faupublication = {yes},
pages = {4028-4033},
peerreviewed = {unknown},
title = {{Look}-up table-based simulation of scintillation detectors in computed tomography},
venue = {Dresden},
volume = {null},
year = {2008}
}
@inproceedings{faucris.123414104,
abstract = {This paper explores the analysis of low-frequency components of continuous speech signals from people with Parkinson's disease, in order to detect changes in the spectrum that could be associated to the presence of tremor in the speech. Different time-frequency (TF) techniques are used for the characterization of the low frequency content of the speech signals, by paying special attention on the ability to work in non-stationary frameworks, due to the need for the analysis of long enough time segments, where the assumptions of stationary can not be met. The set of variables extracted from the TF representations includes centroids and the energy content of different frequency bands, along with entropy measures and nonlinear energy operators, which are used as features for the automatic detection of people with Parkinson's disease vs healthy controls. The discrimination capability of the estimated features is evaluated using three different classification strategies: GMM, GMM-UBM, and SVM. Furthermore, the information provided by different TF techniques is combined using a second classification stage. The results show that the changes in the low frequency components are able to discriminate between people with Parkinson's and healthy speakers with an accuracy of 77%, using one single sentence.},
author = {Villa-Cañas, T. and Arias-Londoño, J. D. and Orozco-Arroyave, J. R. and Vargas-Bonilla, J. F. and Nöth, Elmar},
booktitle = {16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015},
faupublication = {yes},
keywords = {Continuous speech characterization; Parkinson's disease; Pathological voice detection; Time-frequency analysis},
pages = {100-104},
peerreviewed = {unknown},
publisher = {International Speech and Communication Association},
title = {{Low}-frequency components analysis in running speech for the automatic detection of {Parkinson}'s disease},
url = {http://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84959101525&origin=inward},
year = {2015}
}
@inproceedings{faucris.113199504,
address = {New-York},
author = {Hutter, Jana and Schmitt, Peter and Gunhild, Aandal and Greiser, Andreas and Forman, Christoph and Grimm, Robert and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the Medical Image Computing and Computer-Assisted Intervention},
date = {2013-09-22/2013-09-26},
editor = {MICCAI},
faupublication = {yes},
pages = {000-000},
publisher = {Springer},
title = {{Low}-rank and {Sparse} {Matrix} {Decomposition} for {Compressed} {Sensing} reconstruction of {Magnetic} {Resonance} {4D} {Phase} {Contrast} blood flow imaging ({LoSDeCoS} {4D}-{PCI})},
venue = {Nagoya, Japan},
year = {2013}
}
@article{faucris.121154264,
abstract = {Lymph nodes have high clinical relevance and routinely need to be considered in clinical practice. Automatic detection is, however, challenging due to clutter and low contrast. In this paper, a method is presented that fully automatically detects and segments lymph nodes in 3-D computed tomography images of the chest. Lymph nodes can easily be confused with other structures, it is therefore vital to incorporate as much anatomical prior knowledge as possible in order to achieve a good detection performance. Here, a learned prior of the spatial distribution is used to model this knowledge. Different prior types with increasing complexity are proposed and compared to each other. This is combined with a powerful discriminative model that detects lymph nodes from their appearance. It first generates a number of candidates of possible lymph node center positions. Then, a segmentation method is initialized with a detected candidate. The graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross-validation on 54 CT datasets showed that for a fixed number of four false alarms per volume image, the detection rate is well more than doubled when using the spatial prior. In total, our proposed method detects mediastinal lymph nodes with a true positive rate of 52.0% at the cost of only 3.1 false alarms per volume image and a true positive rate of 60.9% with 6.1 false alarms per volume image, which compares favorably to prior work on mediastinal lymph node detection. © 2012 Elsevier B.V. All rights reserved.},
author = {Feulner, Johannes and Zhou, S. Kevin and Hammon, Matthias and Hornegger, Joachim and Comaniciu, Dorin},
doi = {10.1016/j.media.2012.11.001},
faupublication = {yes},
journal = {Medical Image Analysis},
pages = {254-270},
peerreviewed = {Yes},
title = {{Lymph} node detection and segmentation in chest {CT} data using discriminative learning and a spatial prior},
volume = {17},
year = {2012}
}
@inproceedings{faucris.121189464,
abstract = {Lymph nodes have high clinical relevance but detection is challenging as they are hard to see due to low contrast and irregular shape. In this paper, a method for fully automatic mediastinal lymph node detection in 3-D computed tomography (CT) images of the chest area is proposed. Discriminative learning is used to detect lymph nodes based on their appearance. Because lymph nodes can easily be confused with other structures, it is vital to incorporate as much anatomical knowledge as possible to achieve good detection rates. Here, a learned prior of the spatial distribution is proposed to model this knowledge. As atlas matching is generally inaccurate in the chest area because of anatomical variations, this prior is not learned in the space of a single atlas, but in the space of multiple ones that are attached to anatomical structures. During test, the priors are weighted and merged according to spatial distances. Cross-validation on 54 CT datasets showed that the prior based detector yields a true positive rate of 52.3% for seven false positives per volume image, which is about two times better than without a spatial prior. ©2010 IEEE.},
author = {Feulner, Johannes and Zhou, S. Kevin and Huber, Martin and Hornegger, Joachim and Comaniciu, Dorin and Cavallaro, Alexander Josef},
booktitle = {2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010},
doi = {10.1109/CVPR.2010.5540034},
faupublication = {yes},
pages = {2926-2932},
peerreviewed = {unknown},
publisher = {IEEE Computer Society; 1999},
title = {{Lymph} node detection in 3-{D} chest {CT} using a spatial prior probability},
venue = {San Francisco, CA},
volume = {null},
year = {2010}
}
@article{faucris.262664118,
abstract = {Background and objective: The normal swallowing process requires a complex coordination of anatomical structures driven by sensory and cranial nerves. Alterations in such coordination cause swallowing malfunctions, namely dysphagia. The dysphagia screening methods are quite subjective and experience dependent. Bearing in mind that the swallowing process and speech production share some anatomical structures and mechanisms of neurological control, this work aims to evaluate the suitability of automatic speech processing and machine learning techniques for screening of functional dysphagia. Methods: Speech recordings were collected from 46 patients with functional oropharyngeal dysphagia produced by neurological causes, and 46 healthy controls. The dimensions of speech including phonation, articulation, and prosody were considered through different speech tasks. Specific features per dimension were extracted and analyzed using statistical tests. Machine learning models were applied per dimension via nested cross-validation. Hyperparameters were selected using the AUC - ROC as optimization criterion. Results: The Random Forest in the articulation related speech tasks retrieved the highest performance measures (AUC=0.86±0.10, sensitivity=0.91±0.12) for individual analysis of dimensions. In addition, the combination of speech dimensions with a voting ensemble improved the results, which suggests a contribution of information from different feature sets extracted from speech signals in dysphagia conditions. Conclusions: The proposed approach based on speech related models is suitable for the automatic discrimination between dysphagic and healthy individuals. These findings seem to have potential use in the screening of functional oropharyngeal dysphagia in a non-invasive and inexpensive way.},
author = {Roldan-Vasco, Sebastian and Orozco-Duque, Andres and Suarez-Escudero, Juan Camilo and Orozco Arroyave, Juan Rafael},
doi = {10.1016/j.cmpb.2021.106248},
faupublication = {yes},
journal = {Computer Methods and Programs in Biomedicine},
keywords = {Dysphagia; Feature extraction; Machine learning; Speech analysis; Speech processing; Voice changes},
note = {CRIS-Team Scopus Importer:2021-08-13},
peerreviewed = {Yes},
title = {{Machine} learning based analysis of speech dimensions in functional oropharyngeal dysphagia},
volume = {208},
year = {2021}
}
@inproceedings{faucris.274471482,
author = {Rao, Disha and Maass, Nicole and Dennerlein, Frank and Maier, Andreas and Huang, Yixing},
booktitle = {Informatik aktuell},
date = {2022-06-26/2022-06-28},
doi = {10.1007/978-3-658-36932-3{\_}11},
editor = {Klaus Maier-Hein, Thomas M. Deserno, Heinz Handels, Andreas Maier, Christoph Palm, Thomas Tolxdorff},
faupublication = {yes},
isbn = {9783658369316},
note = {CRIS-Team Scopus Importer:2022-05-06},
pages = {51-56},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Machine} {Learning}-based {Detection} of {Spherical} {Markers} in {CT} {Volumes}},
venue = {Heidelberg, DEU},
year = {2022}
}
@incollection{faucris.226998952,
abstract = {Magnetic Resonance Fingerprinting (MRF) is an imaging technique acquiring unique time signals for different tissues. Although the acquisition is highly accelerated, the reconstruction time remains a problem, as the state-of-the-art template matching compares every signal with a set of possible signals. To overcome this limitation, deep learning based approaches, e.g. Convolutional Neural Networks (CNNs) have been proposed. In this work, we investigate the applicability of Recurrent Neural Networks (RNNs) for this reconstruction problem, as the signals are correlated in time. Compared to previous methods based on CNNs, RNN models yield significantly improved results using in-vivo data.},
author = {Hoppe, Elisabeth and Thamm, Florian and Körzdörfer, Gregor and Syben-Leisner, Christopher and Schirrmacher, Franziska and Nittka, Mathias and Pfeuffer, Josef and Meyer, Heiko and Maier, Andreas},
booktitle = {German Medical Data Sciences: Shaping Change – Creative Solutions for Innovative Medicine},
doi = {10.3233/SHTI190816},
editor = {Rainer Röhrig, Harald Binder, Hans-Ulrich Prokosch, Ulrich Sax, Irene Schmidtmann, Susanne Stolpe, Antonia Zapf},
faupublication = {yes},
keywords = {Artificial Neural Networks; Magnetic Resonance Fingerprinting; Magnetic Resonance Fingerprinting Reconstruction; Recurrent Neural Networks},
note = {CRIS-Team Scopus Importer:2019-09-24},
pages = {126-133},
peerreviewed = {unknown},
publisher = {IOS Press},
series = {Studies in Health Technology and Informatics},
title = {{Magnetic} {Resonance} {Fingerprinting} {Reconstruction} {Using} {Recurrent} {Neural} {Networks}},
volume = {267},
year = {2019}
}
@phdthesis{faucris.116766364,
abstract = {The fundamental motivation for all percutaneous interventions is to improve patient care by reducing the invasiveness of the procedure. An increasing number of percu- taneous interventions from biopsies, targeted drug delivery to thermal ablations are performed under magnetic resonance (MR) guidance. Its excellent soft-tissue con- trast and multiplanar imaging capabilities make MRI an attractive alternative to computed tomography or ultrasound for real-time image-guided needle placement, in particular for targets requiring a highly angulated approach and non-axial scan pla- nes. MRI further provides the unique ability to monitor spatial temperature changes in real-time.
The research efforts of this dissertation were focused on improving and simplifying the workflow of MR-guided percutaneous procedures by introducing novel image- based methods without the need for any additional equipment. For safe and efficient MR-guided percutaneous needle placement, a set of methods was developed that allows the user to: 1) plan an entire procedure, 2) directly apply this plan to skin entry site localization without further imaging, and 3) place a needle under real-time MR guidance with automatic image plane alignment along a planned trajectory with preference to the principal patient axes. Methods for enhanced MR thermometry visualization and treatment monitoring were also developed to support an effective thermal treatment facilitating the ablation of tumor tissue without damaging adjacent healthy structures.
To allow for an extensive in-vitro and in-vivo validation, the proposed methods for both needle guidance and MR thermometry were implemented in an integrated prototype. The clinical applicability was demonstrated for a wide range of MR-guided percutaneous interventions emphasizing the relevance and impact of the conducted research.
},
author = {Rothgang, Eva},
faupublication = {yes},
note = {UnivIS-Import:2016-07-26:Pub.2014.tech.IMMD.IMMD5.magnet},
peerreviewed = {automatic},
school = {Friedrich-Alexander-Universität Erlangen-Nürnberg},
title = {{Magnetic} {Resonance} {Imaging} for {Percutaneous} {Interventions}},
url = {https://www5.cs.fau.de/Forschung/Publikationen/2014/Rothgang14-MRI.pdf},
year = {2014}
}
@inproceedings{faucris.111101584,
address = {Berlin Heidelberg},
author = {Haase, Viktor and Taubmann, Oliver and Huang, Yixing and Krings, Gregor and Lauritsch, Günter and Maier, Andreas and Mertins, Alfred},
booktitle = {Bildverarbeitung für die Medizin 2016},
doi = {10.1007/978-3-662-49465-3{\_}31},
faupublication = {yes},
isbn = {978-3-662-49464-6},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.maketh},
pages = {170-175},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Make} the {Most} of {Time}: {Temporal} {Extension} of the {iTV} {Algorithm} for {4D} {Cardiac} {C}-{Arm} {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Haase16-MTM.pdf},
venue = {Berlin},
year = {2016}
}
@inproceedings{faucris.226685327,
address = {BELLINGHAM},
author = {Kaiser, N. and Fieselmann, A. and Vesal, Sulaiman and Ravikumar, Nishant and Ritschl, L. and Kappler, S. and Maier, Andreas},
booktitle = {MEDICAL IMAGING 2019: IMAGE PERCEPTION, OBSERVER PERFORMANCE, AND TECHNOLOGY ASSESSMENT},
date = {2019-02-20/2019-02-21},
doi = {10.1117/12.2513420},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-09-17},
peerreviewed = {unknown},
publisher = {SPIE-INT SOC OPTICAL ENGINEERING},
title = {{Mammographic} breast density classification using a deep neural network: assessment based on inter-observer variability},
venue = {San Diego, CA},
year = {2019}
}
@article{faucris.115403684,
abstract = {Non-homeostatic hyperphagia, which is a major contributor to obesity-related hyperalimentation, is associated with the diet's molecular composition influencing, for example, the energy content. Thus, specific food items such as snack food may induce food intake independent from the state of satiety. To elucidate mechanisms how snack food may induce non-homeostatic food intake, it was tested if manganese-enhanced magnetic resonance imaging (MEMRI) was suitable for mapping the whole brain activity related to standard and snack food intake under normal behavioral situation. Application of the MnCl2 solution by osmotic pumps ensured that food intake was not significantly affected by the treatment. After z-score normalization and a non-affine three-dimensional registration to a rat brain atlas, significantly different grey values of 80 predefined brain structures were recorded in ad libitum fed rats after the intake of potato chips compared to standard chow at the group level. Ten of these areas had previously been connected to food intake, in particular to hyperphagia (e.g. dorsomedial hypothalamus or the anterior paraventricular thalamic nucleus) or to the satiety system (e.g. arcuate hypothalamic nucleus or solitary tract); 27 areas were related to reward/addiction including the core and shell of the nucleus accumbens, the ventral pallidum and the ventral striatum (caudate and putamen). Eleven areas associated to sleep displayed significantly reduced Mn2+-accumulation and six areas related to locomotor activity showed significantly increased Mn2+-accumulation after the intake of potato chips. The latter changes were associated with an observed significantly higher locomotor activity. Osmotic pump-assisted MEMRI proved to be a promising technique for functional mapping of whole brain activity patterns associated to nutritional intake under normal behavior.},
author = {Hoch, Tobias and Kreitz, Silke and Gaffling, Simone and Pischetsrieder, Monika and Heß, Andreas},
doi = {10.1371/journal.pone.0055354},
faupublication = {yes},
journal = {PLoS ONE},
peerreviewed = {Yes},
title = {{Manganese}-{Enhanced} {Magnetic} {Resonance} {Imaging} for {Mapping} of {Whole} {Brain} {Activity} {Patterns} {Associated} with the {Intake} of {Snack} {Food} in {Ad} {Libitum} {Fed} {Rats}},
volume = {8},
year = {2013}
}
@inproceedings{faucris.120536944,
author = {Prümmer, Marcus and Nöth, Elmar and Hornegger, Joachim and Horndasch, Axel},
booktitle = {Workshops Bildverarbeitung fur die Medizin: Algorithmen - Systeme - Anwendungen, BVM 2005 - Workshop on Image Processing for Medicine: Algorithms - Systems - Applications, BVM 2005},
doi = {10.1007/3-540-26431-0{\_}99},
faupublication = {yes},
isbn = {9783540250524},
pages = {485-489},
peerreviewed = {unknown},
title = {{Man}-machine interaction for the interventional application},
venue = {Heidelberg},
year = {2005}
}
@article{faucris.241719268,
abstract = {Tree-based classifiers provide easy-to-understand outputs. Artificial neural networks (ANN) commonly outperform tree-based classifiers; nevertheless, understanding their outputs requires specialized knowledge in most cases. The highly redundant architecture of ANN is typically designed through an expensive trial-and-error scheme. We aim at (1) investigating whether using ensembles of decision trees to design the architecture of low-redundant, sparse ANN provides better-performing networks, and (2) evaluating whether such trees can be used to provide human-understandable explanations for their outputs. Information about the hierarchy of the features, and how good they are at separating subsets of samples among the classes, is gathered from each branch in an ensemble of trees. This information is used to design the architecture of a sparse multilayer perceptron network. Networks built using our method are called ForestNet. Tree branches corresponding to highly activated neurons are used to provide explanations of the networks’ outputs. ForestNets are able to handle low- and high-dimensional data, as we show on an evaluation using four datasets. Our networks consistently outperformed their respective ensemble of trees and had similar performance to their fully connected counterparts with a significant reduction of connections. Furthermore, our interpretation method seems to provide support for the ForestNet outputs. While ForestNet’s architectures do not allow them yet to capture well the intrinsic variability of visual data, they exhibit very promising results by reducing more than 98% of connections for such visual tasks. Structure similarities between ForestNets and their respective tree ensemble provide means to interpret their outputs.
Die Anbahnung einer tracheoösophagealen Ersatzstimme (TE-Stimme) ist eine Möglichkeit, Patienten nach einer totalen Laryngektomie, d.h. Kehlkopfentfernung, die Fähigkeit zu sprechen zurück zu geben. Ein Ventil zwischen Luft- und Speiseröhre erlaubt es, den Luftstrom aus der Lunge umzuleiten und Gewebeschwingungen in der Speiseröhre zur Ersatzstimmgebung zu nutzen. Die Betroffenen durchlaufen eine Therapie, in der wiederholt evaluiert werden muss, ob und wie sich ihre Ersatzstimme hinsichtlich Kriterien wie Lautstärke, Verständlichkeit oder Prosodiefähigkeit entwickelt hat. Da die Beurteilung subjektiv erfolgt und das Verfahren für Arzt und Patienten aufwändig ist, erscheint eine Automatisierung und Objektivierung in diesem Bereich sinnvoll. In unserer Arbeit untersuchen wir, wie gut tracheoösophageale Sprache von einem automatischen Spracherkennungssystem erkannt wird und ob die Ermittlung der Qualität einer Ersatzstimme zumindest teilweise automatisiert erfolgen kann. Dazu müssen die Bewertungen der Maschine und einer Vergleichsgruppe von Experten korrelieren. Im folgenden werden wir unsere ersten Ergebnisse zu diesen Arbeitsgebieten vorstellen.
},
address = {Berlin},
author = {Haderlein, Tino and Steidl, Stefan and Nöth, Elmar and Schuster, Maria},
booktitle = {Fortschritte der Akustik: Plenarvorträge und Fachbeiträge der 31. Deutschen Jahrestagung für Akustik DAGA 2005, München},
date = {2005-03-14/2005-03-17},
editor = {Fastl Hugo, Fruhmann Markus},
faupublication = {yes},
pages = {243-244},
peerreviewed = {unknown},
publisher = {Deutsche Gesellschaft für Akustik e.V.},
title = {{Menschliche} und automatische {Verständlichkeitsbewertung} bei tracheoösophagealen {Ersatzstimmen}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Haderlein05-MUA.pdf},
venue = {München},
year = {2005}
}
@inproceedings{faucris.108055684,
address = {Berlin},
author = {Prümmer, Marcus and Nöth, Elmar and Hornegger, Joachim and Horndasch, Axel},
booktitle = {Bildverarbeitung für die Medizin 2005},
date = {2005-03-13/2005-03-15},
editor = {Meinzer Hans-Peter, Handels Heinz, Horsch Alexander, Tolxdorff Thomas},
faupublication = {yes},
pages = {485-489},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Mensch}-{Maschine} {Interaktion} für den interventionellen {Einsatz}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Pruemmer05-MIF.pdf},
venue = {Berlin},
year = {2005}
}
@inproceedings{faucris.208842842,
author = {Jiang, Zhengning and Keck, Benjamin and Riess, Christian and Fischer, Daniel and Mertelmeier, Thomas and Hornegger, Joachim},
booktitle = {7th Russian-Bavarian Conference on Biomedical Engineering},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Metal} {Artifact} {Reduction} of {Biopsy} {Needles} in {Digital} {Breast} {Tomosynthesis}},
year = {2011}
}
@phdthesis{faucris.236097579,
abstract = {Single photon emission computed tomography (SPECT) is a medical imaging
modality used to visualize the distribution of radioactive tracers in a patient's body.
While SPECT's utility as a diagnostic modality has long been established, its use
for planning and managing nuclear medicine therapies has grown in recent years.
With these new applications comes a need for absolute quantitation of the amount
of radioactivity in tissues. When small, detailed structures are being imaged, a
major confounding factor for the quantification task is respiratory motion, which blurs
images and leads to underestimation. This thesis seeks to contribute new methods
for quantitation and respiratory motion management in SPECT imaging.
We first briefly describe the underlying principles that enable SPECT image formation,
as well as physical nonidealities and physiological aspects of respiratory motion
that confound it. Following this, we introduce methods for analytical and iterative
image reconstruction before surveying the techniques that have been developed
to correct for these confounding processes.
A benefit of these corrections is the enabling of absolute quantitation, and in the
next chapter we propose a quantification protocol for Lu-177, an isotope frequently
used in radionuclide therapies. After characterizing the protocol in a phantom experiment
meant to establish a parameter set offering a favorable bias-variance trade-off,
we validate the results with an in vivo patient study. We found that our protocol
delivered mean errors relative to truth in the bladder of 10.1%.
We then move to the task of respiratory motion management, the first step of
which is obtaining a surrogate signal representing a patient's respiratory state over
time. After describing five data-driven methods for extracting such a signal, we
compare their performance in a phantom experiment and with a collective of cardiac
patient scans. We then expand upon this by taking the best-performing method --
a dimensionality reduction-based approach using Laplacian Eigenmaps (LE) -- and
augment it with post-processing steps to make it fit for fully-automated operation in
clinical practice. Following this, we present results from a follow-up patient validation
on a larger collective with 67 scans indicating that the LE-based approach correlates
well with a clinically-accepted sensor-based method.
To provide an independent assessment of surrogate signal quality, we then analyze
respiratory-gated acquisitions from two types of SPECT scans used for therapy
planning: selective internal radionuclide therapy (SIRT) planning scans with Tc-99m-
MAA and dosimetry acquisitions for Lu-177-based radionuclide therapies. The results
show that data-driven LE surrogates allow recovery of meaningful respiratory motion,
and we report preliminary results indicating the type of clinical benefits that
compensating for this motion might possibly provide.
As a final contribution, we propose an algorithm to improve the robustness of respiratory
motion estimation in SPECT projections using a sequence-based estimation
scheme and a motion model driven by the surrogate signal itself. In a simulation
study, we show that our proposed Sequence-based Motion Model (S-MM) algorithm
reduces estimation variance compared to two comparison methods. Furthermore, in
a collective of 20 patient Tc-99m-MAA liver scans, S-MM reduces respiratory motion
blur more consistently and to a greater extent than the comparison methods. We
conclude the thesis with a summary and outlook of possible future work.
0.05). The mean FAZ area of the SVP was 0.43 ± 0.16 mm2, that of the ICP 0.28 ± 0.1 mm2, and that of the DCP 0.44 ± 0.12 mm2. Conclusions: Spectralis OCT II, in combination with the semiautomated vessel density software EA-Tool, showed good or even excellent ICCs in 75% of all segments of the SVP, ICP, and DCP. The ICCs for the FAZ area in the SVP, ICP, and DCP were excellent.},
author = {Hosari, Sami and Hohberger, Bettina and Theelke, Luisa and Sari, Hasan and Lucio, Marianna and Mardin, Christian Y.},
doi = {10.1159/000502458},
faupublication = {yes},
journal = {Ophthalmologica},
note = {CRIS-Team Scopus Importer:2019-09-24},
peerreviewed = {Yes},
title = {{OCT} {Angiography}: {Measurement} of {Retinal} {Macular} {Microvasculature} with {Spectralis} {II} {OCT} {Angiography} - {Reliability} and {Reproducibility}},
year = {2019}
}
@inproceedings{faucris.203849647,
abstract = {Purpose : We present a novel framework for segmenting optical coherence tomography (OCT) and OCT angiography (OCTA) that jointly uses structural and angiographic information. We term this new paradigm “OCT-OCTA segmentation,” and demonstrate its utility by segmenting Bruch’s membrane (BM) in the presence of drusen.Methods : We developed an automatic OCT-OCTA graph-cut algorithm for BM segmentation. Our algorithm’s performance was quantitatively validated by comparing it with manual segmentation in 7 eyes (6 patients; 73.8±5.7 y/o) with drusen. The algorithm was also qualitatively assessed in healthy eyes (n=13), eyes with diabetic retinopathy (n=21), early/intermediate age-related macular degeneration (AMD) (n=14), exudative AMD (n=5), geographic atrophy (GA) (n=6), and polypoidal choroidal vasculopathy (n=7).
Results : The absolute pixel-wise error between the manual and automatic segmentations had the following values: mean: 4.5±0.89um; 1st Quartile: 1.9±1.35um; 2nd Quartile: 3.9±1.90um; and 3rd Quartile: 6.3±2.67. This corresponds to a mean absolute error smaller than the optical axial resolution of our OCT system (~8-9um). In all other tested eyes, qualitative visual inspection showed BM contours that were deemed suitably accurate for use in forming en face OCT(A) projections. The algorithm’s poorest results occurred in GA patients with large areas of atrophy.
Conclusions : By leveraging both structural and angiographic information we showed that OCT-OCTA segmentation is likely to be a widely useful framework for segmenting ocular structur},
author = {Schottenhamml, Julia and Moult, Eric M. and Novais, Eduardo A. and Kraus, Martin and Lee, Byungkun and Choi, Woojhon and Ploner, Stefan and Husvogt, Lennart and Lu, Chen D. and Yiu, Patrick and Rosenfeld, Philip and Duker, Jay S. and Maier, Andreas and Waheed, Nadia K. and Fujimoto, James G.},
booktitle = {Investigative Ophthalmology & Visual Science},
date = {2017-05-07/2017-05-11},
edition = {8},
faupublication = {yes},
keywords = {oct;octa;oct angiography;layer segmentation;drusen;diabetic retinopathy},
note = {UnivIS-Import:2018-09-11:Pub.2017.tech.IMMD.IMMD5.octoct{\_}8},
pages = {645},
peerreviewed = {Yes},
publisher = {C.V. Mosby Co},
title = {{OCT}-{OCTA} {Segmentation}: a {Novel} {Framework} and an {Application} to {Segment} {Bruch}'s {Membrane} in the {Presence} of {Drusen}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Schottenhamml17-OSA.pdf},
venue = {Baltimore, MD, USA},
volume = {58},
year = {2017}
}
@inproceedings{faucris.203854260,
abstract = {In this work, a novel paradigm for segmenting optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) is presented [1]. Since it uses OCT and OCTA information jointly it is called “OCT-OCTA segmentation” and its usefulness is demonstrated by segmenting the Bruch’s Membrane (BM) in the presence of drusen. Therefore a fully automatic graph-cut algorithm was developed and evaluated by comparing the automatic segmentation results with manual segmentation in 7 eyes (6 patients; 73.8 ± 5.7 y/o) with nascent geographic atrophy and/or drusen associated geographic atrophy.
Introduction
State of the art deep learning [1] requires vast amounts of accurately labeled training data to enable high classification performance [2]. In order to obtain sufficient amounts of data, data donation is a feasible approach [3]. Yet, the data is only usable, if correct annotations are present. One way to create such annotations is crowd-sourcing via gamification. In this paper, we present an integrated training and annotation approach that allows large scale annotation of ophthalmic diseases.
Methods
We created a game called “Odin’s Eye” in order to make image classification an exciting and rewarding experience. The game has three modes that are used to slowly lead the player to the complex field of ophthalmic diseases. In order to do so, we used image data from the ODIR 2019 Challenge (https://odir2019.grand-challenge.org/dataset/). The dataset contains more than 7000 images showing healthy eye data and different pathologies.
In “Normal Mode”, the player is shown one fundus image and is asked to select whether the shown image is “normal” or shows Cataract, Macular Degeneration, Glaucoma, Retinopathy, or Myopia. After a sufficient number of correct answers, the player can access the unlabeled mode, in which the user is able to give annotation to unlabeled image. The annotations for the unlabeled images will be shown in the “Unlabeled Result”.
The “Difficult Mode” is inspired by puzzle games such as Candy Crush or Zookeeper. Here, the player is displayed various fundus images and is asked to align them such that three images showing the same pathology form either a row or a column. Once such a triplet is found, it is eliminated and new images enter the game canvas from the top. In order to make the game more challenging, a curtain enters the field of view from the top that gradually increases the pressure on the player as well as increases game difficulty via decreasing the image brightness. After each successful elimination, the curtain is raised a little and the time limit is increased. Rewarding strategies like reward animation and image shuffling are applied to achieve better user experience. The idea of using triplets is appealing as images of unknown pathology can be mixed in the game area. The player will implicitly classify such images when he tries to align them with two more images of the same class.
A leader board shows high scores in order to encourage players to compare their scores online and to compete in creating a large number of annotations.
Results
A prototype was implemented in Unity [4]. In order to test the game idea, only five prototypical images were chosen for each pathology at present. The difficulty of the game can easily be increased by increasing types of diseases. First experiences with test players confirmed that in particular the “Difficult Mode” has a very rewarding game experience. Prototypes are available as Android APK and WebGL (https://www.medicaldatadonors.org/index.php/odins-eye/). An in-game video was created to demonstrate the gameplay (https://youtu.be/UehnND9gkvY).
Conclusion
A believe that we created a challenging yet rewarding game experience. In future versions, we will make use of additional images from the ODIR 2019 dataset in order to create slowly increasing difficulty in the game to convince even expert players to keep playing Odin’s Eye.
References
[1] Maier, A., Syben, C., Lasser, T., & Riess, C. (2019). A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik, 29(2), 86-101.
[2] Bertram, C. A., Aubreville, M., Marzahl, C., Maier, A., & Klopfleisch, R. (2019). A large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor. Scientific data, 6(1), 1-9.
[3] Servadei, L., Schmidt, R., Eidelloth, C., & Maier, A. (2017, October). Medical Monkeys: A Crowdsourcing Approach to Medical Big Data. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" (pp. 87-97). Springer, Cham.
[4] Murray, J. W. (2014). C# game programming cookbook for Unity 3D. AK Peters/CRC Press},
author = {Fan, Fuxin and Qiu, Jingna and Wang, JiaWei and Valianos, Stelica and Farooq, Muhammad Muqtasid and Fu, Weilin and Kordon, Florian Johannes and Maier, Andreas},
booktitle = {Joint Conference of the GMDS & CEN-IBS 2020},
date = {2020-09-06/2020-09-09},
faupublication = {yes},
keywords = {Gamification; Medical Image Annotation; Deep Learning},
peerreviewed = {Yes},
title = {{Odin}’s {Eye} – {A} {Close} {Look} at {Gamification} of {Labelling} of {Ophthalmic} {Diseases}},
venue = {Online Streaming},
year = {2020}
}
@inproceedings{faucris.107893544,
abstract = {In traditional classification problems, the reference needed for training a classifier is given and considered to be absolutely correct. However, this does not apply to all tasks. In emotion recognition in non-acted speech, for instance, one often does not know which emotion was really intended by the speaker. Hence, the data is annotated by a group of human labelers who do not agree on one common class in most cases. Often, similar classes are confused systematically. We propose a new entropy-based method to evaluate classification results taking into account these systematic confusions. We can show that a classifier which achieves a recognition rate of "only" about 60% on a four-class-problem performs as well as our five human labelers on average.},
address = {3833 S. Texas Ave., Ste. 221 Bryan, TX 77802-4015},
author = {Steidl, Stefan and Levit, Michael and Batliner, Anton and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Proceedings of ICASSP 2005 - International Conference on Acoustics, Speech, and Signal Processing},
date = {2005-03-18/2005-03-23},
editor = {IEEE},
faupublication = {yes},
month = {Jan},
pages = {317-320},
peerreviewed = {unknown},
publisher = {Conference Managament Services, Inc.},
title = {"{Of} {All} {Things} the {Measure} is {Man}" - {Classification} of {Emotions} and {Inter}-{Labeler} {Consistency}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Steidl05-OAT.pdf},
venue = {Philadelphia, PA},
year = {2005}
}
@inproceedings{faucris.116878564,
abstract = {Convolutional neural networks (CNNs) have recently become the state-of-the-art tool for large-scale image classification. In this work we propose the use of activation features from CNNs as local descriptors for writer identification. A global descriptor is then formed by means of GMM supervector encoding, which is further improved by normalization with the KL-Kernel. We evaluate our method on two publicly available datasets: the ICDAR 2013 benchmark database and the CVL dataset. While we perform comparably to the state of the art on CVL, our proposed method yields about 0.21 absolute improvement in terms of mAP on the challenging bilingual ICDAR dataset.},
address = {Berlin},
author = {Christlein, Vincent and Bernecker, David and Maier, Andreas and Angelopoulou, Elli},
booktitle = {Pattern Recognition},
date = {2015-10-07/2015-10-10},
doi = {10.1007/978-3-319-24947-6{\_}45},
faupublication = {yes},
isbn = {978-3-319-24946-9},
note = {UnivIS-Import:2016-02-10:Pub.2015.tech.IMMD.IMMD5.offlin{\_}86},
pages = {540-552},
peerreviewed = {unknown},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {{Offline} {Writer} {Identification} {Using} {Convolutional} {Neural} {Network} {Activation} {Features}},
url = {https://www5.cs.fau.de/research/areas/computer-vision/writer-identification/offline-writer-identification-using-convolutional-neural-network-activation-features/},
venue = {Aachen},
volume = {9358},
year = {2015}
}
@inproceedings{faucris.118309224,
abstract = {Feature point tracking and detection of X-ray images is challenging due to overlapping anatomical structures of different depths, which lead to low-contrast images. Tracking of motion in X-ray sequences can support many clinical applications like motion compensation or two- or three-dimensional registration algorithms. This paper is the first to evaluate the performance of several feature tracking and detection algorithms on artificial and real X-ray image sequences, which involve rigid motion as well as external disturbances. A stand-alone application has been developed to provide an overall test bench for all algorithms, realized by OpenCV implementations. Experiments show that the Karhunen Loeve Transform-based Tracker is the most consistent and effective tracking algorithm. Considering external disturbances, template matching provides the most sufficient results. Furthermore, the influence of feature point detection methods on tracking results is shown.},
address = {Berlin Heidelberg},
author = {Klüppel, Moritz and Wang, Jian and Bernecker, David and Fischer, Peter and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2014},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}28},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.onfeat},
pages = {132-137},
publisher = {Springer},
series = {Informatik aktuell},
title = {{On} {Feature} {Tracking} in {X}-{Ray} {Images}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Klueppel14-OFT.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.208854578,
author = {Riess, Christian and Mohamed, Ashraf and Hinshaw, Waldo and Fahrig, Rebecca},
booktitle = {Medical Imaging 2015: Physics of Medical Imaging},
doi = {10.1117/12.2082354},
editor = {International Society for Optics and Photonics},
faupublication = {no},
pages = {941251},
peerreviewed = {Yes},
title = {{On} {Filtration} for {High}-{Energy} {Phase}-{Contrast} {X}-{Ray} {Imaging}},
year = {2015}
}
@article{faucris.121339944,
author = {Rothgang, Eva and Kickhefel, Antje and Roland, Jörg and Rosenberg, Christian and Hornegger, Joachim and Lorenz, Christine H.},
doi = {10.1007/s10334-009-0178-y},
faupublication = {yes},
journal = {Magnetic Resonance Materials in Physics Biology and Medicine},
pages = {390.0},
peerreviewed = {Yes},
title = {{Online} improvement of the reliability of {PRF} based temperature maps displayed during laser-induced thermotherapy of liver lesions},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Rothgang09-OIO.pdf},
volume = {22.0},
year = {2009}
}
@inproceedings{faucris.282438961,
address = {BAIXAS},
author = {Vasquez Correa, Juan and Fritsch, Julian and Orozco Arroyave, Juan Rafael and Nöth, Elmar and Magimai-Doss, Mathew},
booktitle = {INTERSPEECH 2021},
doi = {10.21437/Interspeech.2021-1084},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2022-09-30},
pages = {26-30},
peerreviewed = {unknown},
publisher = {ISCA-INT SPEECH COMMUNICATION ASSOC},
title = {{On} {Modeling} {Glottal} {Source} {Information} for {Phonation} {Assessment} in {Parkinson}'s {Disease}},
venue = {Brno},
year = {2021}
}
@inproceedings{faucris.203368159,
author = {Christlein, Vincent and Riess, Christian and Angelopoulou, Elli},
booktitle = {2010 IEEE International Workshop on Information Forensics and Security},
date = {2010-12-12/2010-12-15},
doi = {10.1109/WIFS.2010.5711472},
faupublication = {yes},
pages = {1--6},
peerreviewed = {Yes},
title = {{On} rotation invariance in copy-move forgery detection},
venue = {Seattle},
year = {2010}
}
@inproceedings{faucris.123042744,
abstract = {Quantitative estimation of water loss during physical exercise is of importance because dehydration can impair both muscular strength and aerobic endurance. A physiological indicator for deficit of total body water (TBW) might be the concentration of electrolytes in sweat. It has been shown that concentrations differ after physical exercise depending on whether water loss was replaced by fluid intake or not. However, to the best of our knowledge, this fact has not been examined for its potential to quantitatively estimate TBW loss. Therefore, we conducted a study in which sweat samples were collected continuously during two hours of physical exercise without fluid intake. A statistical analysis of these sweat samples revealed significant correlations between chloride concentration in sweat and TBW loss (r = 0.41, p < 0.01), and between sweat osmolality and TBW loss (r = 0.43, p < 0.01). A quantitative estimation of TBW loss resulted in a mean absolute error of 0.49 l per estimation. Although the precision has to be improved for practical applications, the present results suggest that TBW loss estimation could be realizable using sweat samples.},
author = {Ring, Matthias and Lohmüller, Clemens and Rauh, Manfred and Eskofier, Björn},
booktitle = {Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
date = {2015-08-25/2015-08-29},
doi = {10.1109/EMBC.2015.7320006},
editor = {IEEE},
faupublication = {yes},
pages = {7011-7014},
peerreviewed = {Yes},
title = {{On} {Sweat} {Analysis} for {Quantitative} {Estimation} of {Dehydration} during {Physical} {Exercise}},
venue = {Milan},
year = {2015}
}
@inproceedings{faucris.118748124,
abstract = {Over the last years, several methods have been proposed to guide the physician during reduction and fixation of bone fractures. Available solutions often use bulky instrumentation inside the operating room (OR). The latter ones usually consist of a stereo camera, placed outside the operative field, and optical markers directly attached to both the patient and the surgical instrumentation, held by the surgeon. Recently proposed techniques try to reduce the required additional instrumentation as well as the radiation exposure to both patient and physician. In this paper, we present the adaptation and the first implementation of our recently proposed video camera-based solution for screw fixation guidance. Based on the simulations conducted in our previous work, we mounted a small camera on a drill in order to recover its tip position and axis orientation w.r.t our custom-made drill sleeve with attached markers. Since drill-position accuracy is critical, we thoroughly evaluated the accuracy of our implementation. We used an optical tracking system for ground truth data collection. For this purpose, we built a custom plate reference system and attached reflective markers to both the instrument and the plate. Free drilling was then performed 19 times. The position of the drill axis was continuously recovered using both our video camera solution and the tracking system for comparison. The recorded data covered targeting, perforation of the surface bone by the drill bit and bone drilling. The orientation of the instrument axis and the position of the instrument tip were recovered with an accuracy of 1:60 ± 1:22° and 2:03 ± 1:36 mm respectively. © 2014 SPIE.},
address = {Proc. SPIE 9036},
author = {Magaraggia, Jessica and Kleinszig, Gerhard and Wei, Wei and Weiten, Markus and Graumann, Rainer and Angelopoulou, Elli and Hornegger, Joachim},
booktitle = {SPIE Medical Imaging 2014},
date = {2014-02-18/2014-02-20},
doi = {10.1117/12.2043508},
faupublication = {yes},
keywords = {Video-guided method, Real-time guidance, Orthopedic and Trauma Surgery, Drill Sleeve},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.onthea{\_}7},
pages = {903610-903610},
title = {{On} the {Accuracy} of a {Video}-{Based} {Drill}-{Guidance} {Solution} for {Orthopedic} and {Trauma} {Surgery}: {Preliminary} {Results}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Magaraggia14-OTA.pdf},
venue = {Town and Country Resort and Convention Center, San Diego, California},
volume = {903610},
year = {2014}
}
@inproceedings{faucris.108227504,
address = {Lisbon, Portugal},
author = {Maier, Andreas and Schafflhuber, Caroline and Bocklet, Tobias and Hönig, Florian Thomas and Kratz, Oliver and Horndasch, Stefanie and Nöth, Elmar and Moll, Gunther},
booktitle = {Pattern Recognition in Information Systems},
date = {2009-05-06/2009-05-07},
editor = {Fred Ana},
faupublication = {yes},
pages = {18-28},
peerreviewed = {Yes},
publisher = {INSTICC PRESS},
title = {{On} the {Automatic} {Classification} of {Reading} {Disorders}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Maier09-OTA.pdf},
venue = {Mailand},
year = {2009}
}
@inproceedings{faucris.212625243,
author = {Felsner, Lina and Hu, Shiyang and Ludwig, Veronika and Anton, Gisela and Maier, Andreas and Rieß, Christian},
booktitle = {Bildverarbeitung für die Medizin (BVM 2019)},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}59},
faupublication = {yes},
pages = {264-269},
peerreviewed = {Yes},
title = {{On} the {Characteristics} of {Helical} 3-{D} {X}-ray {Dark}-field {Imaging}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Felsner19-OTC.pdf},
venue = {Lübeck},
year = {2019}
}
@article{faucris.120692044,
abstract = {We observe and induce conformational switching of individual molecules via scanning tunneling microscopy (STM) at and close to room temperature. 2H-5,10,15,20-Tetrakis-(3,5-di-tert-butyl)-phenylporphyrin adsorbed on Cu(111) forms a peculiar supramolecular ordered phase in which the molecules arrange in alternating rows, with two distinct appearances in STM which are assigned to concave and convex intramolecular conformations. Around room temperature, frequent bidirectional conformational switching of individual molecules from concave to convex and vice versa is observed. From the temperature dependence, detailed insights into the energy barriers and entropic contributions of the switching processes are deduced. At 200 K, controlled STM tip-induced unidirectional switching is possible, yielding an information storage density of 4.9 × 10 bit/inch. With this contribution we demonstrate that controlled switching of individual molecules at comparably high temperatures is possible and that entropic effects can be a decisive factor in potential molecular devices at these temperatures. © 2014 American Chemical Society.},
author = {Ditze, Stefanie and Stark, Michael Werner and Buchner, Florian and Aichert, André and Jux, Norbert and Luckas, Nicola and Görling, Andreas and Hieringer, Wolfgang and Hornegger, Joachim and Steinrück, Hans-Peter and Marbach, Hubertus},
doi = {10.1021/ja411884p},
faupublication = {yes},
journal = {Journal of the American Chemical Society},
month = {Jan},
pages = {1609-1616},
peerreviewed = {Yes},
title = {{On} the energetics of conformational switching of molecules at and close to room temperature},
volume = {136},
year = {2014}
}
@inproceedings{faucris.120190444,
abstract = {Capsule Endoscopy (CE) was introduced in 2000 and has since become an established diagnostic procedure for the small bowel, colon and esophagus. For the CE examination the patient swallows the capsule, which then travels through the gastrointestinal tract under the influence of the peristaltic movements. CE is not indicated for stomach examination, as the capsule movements can not be controlled from the outside and the entire surface of the stomach can not be reliably covered. Magnetically-guided capsule endoscopy (MGCE) was introduced in 2010. For the MGCE procedure the stomach is filled with water and the capsule is navigated from the outside using an external magnetic field. During the examination the operator can control the motion of the capsule in order to obtain a sufficient number of stomach-surface images with diagnostic value. The quality of the examination depends on the skill of the operator and his ability to detect aspects of interest in real time. We present a novel computer-assisted diagnostic-procedure (CADP) algorithm for indicating gastritis pathologies in the stomach during the examination. Our algorithm is based on pre-processing methods and feature vectors that are suitably chosen for the challenges of the MGCE imaging (suspended particles, bubbles, lighting). An image is classified using an ada-boost trained classifier. For the classifier training, a number of possible features were investigated. Statistical evaluation was conducted to identify relevant features with discriminative potential. The proposed algorithm was tested on 12 video sequences stemming from 6 volunteers. A mean detection rate of 91.17% was achieved during leave-one out cross-validation. © 2011 SPIE.},
author = {Mewes, Philip and Neumann, Dominik and Juloski, Aleksandar Lj and Angelopoulou, Elli and Hornegger, Joachim},
booktitle = {Medical Imaging 2011: Computer-Aided Diagnosis},
doi = {10.1117/12.878803},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{On}-the-fly detection of images with gastritis aspects in magnetically guided capsule endoscopy},
venue = {Lake Buena Vista, FL},
volume = {7963},
year = {2011}
}
@inproceedings{faucris.110588764,
author = {Scherl, Holger and Hoppe, Stefan and Dennerlein, Frank and Lauritsch, Günter and Eckert, Wieland and Kowarschik, Markus and Hornegger, Joachim},
booktitle = {Proceedings Fully3D Meeting and HPIR Workshop},
date = {2007-07-09/2007-07-13},
editor = {..},
faupublication = {yes},
pages = {29-32},
peerreviewed = {unknown},
title = {{On}-the-fly-{Reconstruction} in {Exact} {Cone}-{Beam} {CT} using the {Cell} {Broadband} {Engine} {Architecture}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Scherl07-OIE.pdf},
venue = {Lindau},
year = {2007}
}
@article{faucris.121336644,
abstract = {The automatic recognition of children's speech is well known to be a challenge, and so is the influence of affect that is believed to downgrade performance of a speech recogniser. In this contribution, we investigate the combination of both phenomena. Extensive test runs are carried out for 1 k vocabulary continuous speech recognition on spontaneous motherese, emphatic, and angry children's speech as opposed to neutral speech. The experiments address the question how specific emotions influence word accuracy. In a first scenario, "emotional" speech recognisers are compared to a speech recogniser trained on neutral speech only. For this comparison, equal amounts of training data are used for each emotion-related state. In a second scenario, a "neutral" speech recogniser trained on large amounts of neutral speech is adapted by adding only some emotionally coloured data in the training process. The results show that emphatic and angry speech is recognised best—even better than neutral speech—and that the performance can be improved further by adaptation of the acoustic and linguistic models. In order to show the variability of emotional speech, we visualise the distribution of the four emotion-related states in the MFCC space by applying a Sammon transformation.},
author = {Steidl, Stefan and Batliner, Anton and Seppi, Dino and Schuller, Björn},
doi = {10.1155/2010/783954},
faupublication = {yes},
journal = {EURASIP Journal on Audio, Speech, and Music Processing},
peerreviewed = {Yes},
title = {{On} the {Impact} of {Children}'s {Emotional} {Speech} on {Acoustic} and {Language} {Models}},
url = {http://downloads.hindawi.com/journals/asmp/2010/783954.pdf},
volume = {2010},
year = {2010}
}
@inproceedings{faucris.203723460,
author = {Luckner, Christoph and Schebesch, Frank and Syben-Leisner, Christopher and Mertelmeier, Thomas and Maier, Andreas and Ritschl, Ludwig},
booktitle = {Proceedings of the Fifth International Conference on Image Formation in X-Ray Computed Tomography},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.onthei{\_}5},
pages = {147-150},
peerreviewed = {unknown},
title = {{On} the {Influence} of {Acquisition} {Angle} and {Slice} {Thickness} on the in-plane {Spatial} {Resolution} of {Calcifications} in {Digital} {Breast} {Tomosynthesis}},
venue = {Salt Lake City, USA},
year = {2018}
}
@inproceedings{faucris.121474584,
address = {-},
author = {Nöth, Elmar and Batliner, Anton and Warnke, Volker and Haas, Jürgen and Boros, Manuela and Buckow, Jan-Constantin and Huber, Richard and Gallwitz, Florian and Nutt, Matthias and Niemann, Heinrich},
booktitle = {Proc. ESCA Workshop on Dialogue and Prosody},
date = {1999-09-01/1999-09-03},
editor = {ESCA},
faupublication = {yes},
pages = {25-34},
publisher = {-},
title = {{On} the {Use} of {Prosody} in {Automatic} {Dialogue} {Understanding}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Noeth99-OTU.pdf},
venue = {Eindhoven},
year = {1999}
}
@inproceedings{faucris.260369806,
abstract = {Model based iterative reconstruction (MBIR) has attracted a lot of attention in X-ray computed tomography (CT). A strength of MBIR over classical filtered backprojection is its ability to apply constraints over the voxel values, which can be critical to improve image quality. Given that the linear attenuation coefficient of X-rays is non-negative, applying a non-negativity constraint appears very natural. Indeed, most MBIR-related publications in CT invoke it. However, there is little to no information in the literature on the intrinsic value of the non-negativity constraint. In this work, we shed light on this question in the context of two challenging imaging scenarios: (i) heavy truncation, (ii) photon starvation due to a metal implant. Real CT data sets are used, and the effect of the constraint is examined in terms of image similarity and closeness to a preferred ground truth. Additionally, convergence properties are examined. The reconstruction is performed using a provably converging algorithm applied with a large number of iterations to nearly reach convergence, and is also performed using ordered subsets to obtain a result in a manner that is more practical for clinical routine applications. Our results show that the non-negativity constraint can be both beneficial and detrimental depending on the imaging scenario. However, the observed differences tend to be much smaller than the overall level of inaccuracy in the image. We also find that the non-negativity constraint can prevent divergence when using ordered subsets, but this gain does not translate into a satisfactory reconstruction. Altogether, we conclude that strong value for the non-negativity constraint is difficult to demonstrate. This constraint could thus be discarded in favor of other constraints or utilization of algorithms that cannot handle it.
∘ . ORCA-SPY was field-tested on Lake Stechlin in Brandenburg Germany under laboratory conditions with a focus on localization. During the field test, 3889 localization events were observed with an average error of 29.19 ∘ and a median error of 17.54 ∘ . ORCA-SPY was deployed successfully during the DeepAL fieldwork 2022 expedition (DLFW22) in Northern British Columbia, with a mean average error of 20.01 ∘ and a median error of 11.01 ∘ across 503 localization events. ORCA-SPY is an open-source and publicly available software framework, which can be adapted to various recording conditions as well as animal species.},
author = {Hauer, Christopher and Nöth, Elmar and Barnhill, Alexander and Maier, Andreas and Guthunz, Julius and Hofer, Heribert and Cheng, Rachael Xi and Barth, Volker and Bergler, Christian},
doi = {10.1038/s41598-023-38132-7},
faupublication = {yes},
journal = {Scientific Reports},
note = {CRIS-Team Scopus Importer:2023-07-21},
peerreviewed = {Yes},
title = {{ORCA}-{SPY} enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation},
volume = {13},
year = {2023}
}
@article{faucris.287327434,
abstract = {Acoustic identification of vocalizing individuals opens up new and deeper insights into animal communications, such as individual-/group-specific dialects, turn-taking events, and dialogs. However, establishing an association between an individual animal and its emitted signal is usually non-trivial, especially for animals underwater. Consequently, a collection of marine species-, array-, and position-specific ground truth localization data is extremely challenging, which strongly limits possibilities to evaluate localization methods beforehand or at all. This study presents ORCA-SPY, a fully-automated sound source simulation, classification and localization framework for passive killer whale (Orcinus orca) acoustic monitoring that is embedded into PAMGuard, a widely used bioacoustic software toolkit. ORCA-SPY enables array- and position-specific multichannel audio stream generation to simulate real-world ground truth killer whale localization data and provides a hybrid sound source identification approach integrating ANIMAL-SPOT, a state-of-the-art deep learning-based orca detection network, followed by downstream Time-Difference-Of-Arrival (TDOA) localization. ORCA-SPY was evaluated on simulated multichannel underwater audio streams including various killer whale vocalization events within a large-scale experimental setup benefiting from previous real-world fieldwork experience. Across all 58,320 embedded vocalizing killer whale events, subject to various hydrophone array geometries, call types, distances, and noise conditions responsible for a signal-to-noise ratio varying from -14.2dB to 3dB, a detection rate of 94.0 % was achieved with an average localization error of 7.01°. ORCA-SPY was field-tested on the lake Stechlin under laboratory conditions with a focus on localization. During the field test, 3889 localization events were observed with an average error of 29.19° and a median error of 17.54°. ORCA-SPY was deployed successfully at the DeepAL fieldwork 2022 expedition (DLFW22) in Northern British Columbia, with a mean average error of 20.01° and a median error of 11.01° across 503 localization events. ORCA-SPY is an open-source and publicly available software framework, which can be adapted to various recording conditions as well as animal species.},
author = {Hauer, Christopher and Nöth, Elmar and Barnhill, Alexander and Maier, Andreas and Guthunz, Julius and Hofer, Heribert and Cheng, Rachael Xi and Barth, Volker and Bergler, Christian},
faupublication = {yes},
journal = {Scientific Reports},
peerreviewed = {Yes},
title = {{ORCA}-{SPY}: {Killer} {Whale} {Sound} {Source} {Simulation} and {Detection}, {Classification} and {Localization} in {PAMGuard} {Utilizing} {Integrated} {Deep} {Learning} {Based} {Segmentation}},
volume = {UNDER REVIEW},
year = {2023}
}
@inproceedings{faucris.272154753,
author = {Bergler, Christian and Barnhill, Alexander and Perrin, Dominik and Schmitt, Manuel and Maier, Andreas and Nöth, Elmar},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2022},
date = {2022-09-18/2022-09-22},
doi = {10.21437/interspeech.2022-846},
faupublication = {yes},
keywords = {Killer Whale, Deep Learning, Call Type, Generative Adversarial Networks},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{ORCA}-{WHISPER}: {An} {Automatic} {Killer} {Whale} {Sound} {Type} {Generation} {Toolkit} {Using} {Deep} {Learning}},
venue = {Incheon, Korea},
year = {2022}
}
@article{faucris.120194844,
abstract = {A known problem in endoscopic surgery (especially with flexible video endoscopes) is the absence of a stable horizon in endoscopic images displayed on a monitor. With our "ENDOrientation" approach, image rectification, even in non-rigid endoscopic surgery (particularly NOTES), can be realized with a tiny MEMS tri-axial inertial sensor placed on the tip of an endoscope. This sensor measures the impact of gravity on each of the three orthogonal accelerometer axes in real time. After an initial calibration and temporal filtering of these three data steams, the rotation angle of an endoscope can be estimated directly. The achievable sampling rate of the inertial sensor is above the usual endoscopic video frame rate of 25 Hz; the rotation accuracy is approximately one degree. The image rectification can be performed in real time by digitally rotating the endoscopic video signal. Improvements and benefits have been evaluated in animal studies: coordination and movement of different instruments was rated to be much more intuitive with a stable horizon on endoscopic images. The recorded time stamps and position tracks clearly support this observation. © 2010 by Walter de Gruyter.},
author = {Höller, Kurt Emmerich and Schneider, Armin and Jahn, Jasper and Gutierrez, Javier and Wittenberg, Thomas and Meining, Alexander and Von Delius, Stefan and Hornegger, Joachim and Feussner, Hubertus},
doi = {10.1515/BMT.2010.032},
faupublication = {yes},
journal = {Biomedizinische Technik},
pages = {211-217},
peerreviewed = {Yes},
title = {{Orientation} of endoscopic images: {Rectification} by gravity},
volume = {55},
year = {2010}
}
@inproceedings{faucris.122597024,
address = {Berlin Heidelberg},
author = {Köhler, Thomas and Haase, Sven and Bauer, Sebastian and Wasza, Jakob and Kilgus, Thomas and Maier-Hein, Lena and Feußner, Hubertus and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2014},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.outlie{\_}5},
pages = {84-89},
publisher = {Springer},
title = {{Outlier} {Detection} for {Multi}-{Sensor} {Super}-{Resolution} in {Hybrid} 3-{D} {Endoscopy}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Koehler14-ODF.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.203709495,
abstract = {This paper proposes a novel method to deal with overexposure for C-arm CT reconstruction. The proposed method is based on recent progress of one bit compressive sensing (1bit-CS), which is to recover sparse signals from sign measurements. Overexposure could be regarded as a kind of sign information, thus the application of 1bit-CS to overexposure correction in CT reconstruction is expected. This method is evaluated on a phantom and its promising performance implies potential application on clinical data.},
address = {Berlin},
author = {Huang, Xiaolin and Xia, Yan and Huang, Yixing and Hornegger, Joachim and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin: Algorithmen-Systeme-Anwendungen},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0},
editor = {Klaus Hermann Maier-Hein, geb. Fritzsche, Thomas Martin Deserno, geb. Lehmann, Heinz Handels,Thomas Tolxdorff},
faupublication = {yes},
isbn = {978-3-662-54344-3},
keywords = {Overexposure; Mixed One-bit; Compressive Sensing},
note = {UnivIS-Import:2018-09-06:Pub.2017.tech.IMMD.IMMD5.overex},
pages = {50-55},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Overexposure} {Correction} by {Mixed} {One}-bit {Compressive} {Sensing} for {C}-{Arm} {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Huang17-OCB.pdf},
venue = {Heidelberg},
year = {2017}
}
@inproceedings{faucris.118785084,
author = {Preuhs, Alexander and Berger, Martin and Xia, Yan and Maier, Andreas and Hornegger, Joachim and Fahrig, Rebecca},
booktitle = {Bildverarbeitung für die Medizin 2015},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-17:Pub.2015.tech.IMMD.IMMD5.overex{\_}3},
pages = {35-40},
title = {{Over}-{Exposure} {Correction} in {CT} {Using} {Optimization}-{Based} {Multiple} {Cylinder} {Fitting}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Preuhs15-OCI.pdf},
venue = {Lübeck},
year = {2015}
}
@inproceedings{faucris.117770664,
abstract = {Human palmprints contain biometric features that can be used to identify an individual. These features can be used for example in user verification applications. This paper presents a user verification system using palmprint identification. The image of the palm is captured using a web camera. Then the features used for palmprint identification is extracted using line detection and local standard deviation. The proposed system is evaluated by asking 40 subjects to act as users (10 subject as registered users and 30 non-registered users). Our experiments show that the system can achieve accuracy rate of up to 98% with no false acceptance and 2% false rejection rate. The average time required to perform a user verification is 340 ms.},
author = {Prakoso, Bagas Sakamulia and Timotius, Ivanna and Setyawan, Iwan},
booktitle = {The 1st International Conference on Information Technology, Computer and Electrical Engineering (ICITACEE 2014)},
doi = {10.1109/ICITACEE.2014.7065733},
faupublication = {no},
keywords = {palmprint identification; line detection; local standard deviation; user verification.},
pages = {155 - 159},
peerreviewed = {unknown},
title = {{Palmprint} {Identification} for {User} {Verification} based on {Line} {Detection} and {Local} {Standard} {Deviation}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7065733},
venue = {Semarang},
year = {2014}
}
@article{faucris.283163079,
abstract = {Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.},
author = {Wilm, Frauke and Fragoso, Marco and Marzahl, Christian and Qiu, Jingna and Puget, Chloe and Diehl, Laura and Bertram, Christof A. and Klopfleisch, Robert and Maier, Andreas and Breininger, Katharina and Aubreville, Marc},
doi = {10.1038/s41597-022-01692-w},
faupublication = {yes},
journal = {Scientific Data},
note = {CRIS-Team Scopus Importer:2022-10-14},
peerreviewed = {Yes},
title = {{Pan}-tumor {CAnine} {cuTaneous} {Cancer} {Histology} ({CATCH}) dataset},
volume = {9},
year = {2022}
}
@article{faucris.307879728,
abstract = {The success of immuno-oncology treatments promises long-term cancer remission for an increasing number of patients. The response to checkpoint inhibitor drugs has shown a correlation with the presence of immune cells in the tumor and tumor microenvironment. An in-depth understanding of the spatial localization of immune cells is therefore critical for understanding the tumor's immune landscape and predicting drug response. Computer-aided systems are well suited for efficiently quantifying immune cells in their spatial context. Conventional image analysis approaches are often based on color features and therefore require a high level of manual interaction. More robust image analysis methods based on deep learning are expected to decrease this reliance on human interaction and improve the reproducibility of immune cell scoring. However, these methods require sufficient training data and previous work has reported low robustness of these algorithms when they are tested on out-of-distribution data from different pathology labs or samples from different organs. In this work, we used a new image analysis pipeline to explicitly evaluate the robustness of marker-labeled lymphocyte quantification algorithms depending on the number of training samples before and after being transferred to a new tumor indication. For these experiments, we adapted the RetinaNet architecture for the task of T-lymphocyte detection and employed transfer learning to bridge the domain gap between tumor indications and reduce the annotation costs for unseen domains. On our test set, we achieved human-level performance for almost all tumor indications with an average precision of 0.74 in-domain and 0.72–0.74 cross-domain. From our results, we derive recommendations for model development regarding annotation extent, training sample selection, and label extraction for the development of robust algorithms for immune cell scoring. By extending the task of marker-labeled lymphocyte quantification to a multi-class detection task, the pre-requisite for subsequent analyses, e.g., distinguishing lymphocytes in the tumor stroma from tumor-infiltrating lymphocytes, is met.},
author = {Wilm, Frauke and Ihling, Christian and Méhes, Gábor and Terracciano, Luigi and Puget, Chloé and Klopfleisch, Robert and Schüffler, Peter and Aubreville, Marc and Maier, Andreas and Mrowiec, Thomas and Breininger, Katharina},
doi = {10.1016/j.jpi.2023.100301},
faupublication = {yes},
journal = {Journal of Pathology Informatics},
keywords = {Deep learning; Domain adaptation; Immuno-oncology; Immunohistochemistry; Transfer learning; Tumor-infiltrating lymphocytes},
month = {Jan},
note = {CRIS-Team Scopus Importer:2023-07-21},
peerreviewed = {Yes},
title = {{Pan}-tumor {T}-lymphocyte detection using deep neural networks: {Recommendations} for transfer learning in immunohistochemistry},
volume = {14},
year = {2023}
}
@inproceedings{faucris.203724022,
abstract = {The Papoulis-Gerchberg (P-G) algorithm is widely
used for extrapolation of band-limited signals. It is applicable to
limited angle tomography as well since typical imaged objects in
computed tomography have a limited spatial extent, which means
that the Fourier transforms of the objects can be considered
band-limited signals. In computed tomography, some other bandlimitation properties have been discovered as well, which are
referred to as data consistency conditions. For example, the
Fourier transform of a parallel-beam sinogram has an empty
double-wedge region. The Chebyshev-Fourier transform of a
parallel-beam sinogram only has nonzero values inside a wedge
region and these values form a checkerboard pattern, which is
Helgason-Ludwig consistency condition. In this paper, we propose
two P-G algorithms to restore missing data in limited angle tomography using the above two consistency conditions. Numerical
experiments on the Shepp-Logan phantom demonstrate that they
can reduce streaks better than the conventional P-G algorithm.
physical HL) was reduced. Conclusion: The PFF leads to voxel-wise half-lives, which are more plausible than those resulting from SF. However, one has to admit that voxel-wise fitting generally leads to considerable deviations from the organ-averaged TIA as obtained by conventional whole-organ evaluation. Unfortunately, we did not have ground-truth TIA of our patient data and proper ground-truth could even be impossible to obtain. Nevertheless, there are strong indicators that particle filtering can be used for reducing voxel-wise TAC noise.},
author = {Götz, Theresa and Götz, Th I. and Lang, E. W. and Schmidkonz, Christian and Maier, Andreas and Kuwert, Torsten and Ritt, Philipp},
doi = {10.1016/j.zemedi.2019.10.005},
faupublication = {yes},
journal = {Zeitschrift für Medizinische Physik},
keywords = {Dosimetry; Nuclear medicine; Time-activity-curve; Voxelwise},
note = {CRIS-Team Scopus Importer:2019-12-27},
peerreviewed = {Yes},
title = {{Particle} filter de-noising of voxel-specific time-activity-curves in personalized {177Lu} therapy},
year = {2019}
}
@inproceedings{faucris.106699604,
abstract = {Deep learning technologies such as convolutional neural networks (CNN) provide powerful methods for image recognition and have recently been employed in the field of automated carcinoma detection in confocal laser endomicroscopy (CLE) images. CLE is a (sub-)surface microscopic imaging technique that reaches magnifications of up to 1000x and is thus suitable for in vivo structural tissue analysis. In this work, we aim to evaluate the prospects of a priorly developed deep learning-based algorithm targeted at the identification of oral squamous cell carcinoma with regard to its generalization to further anatomic locations of squamous cell carcinomas in the area of head and neck. We applied the algorithm on images acquired from the vocal fold area of five patients with histologically verified squamous cell carcinoma and presumably healthy control images of the clinically normal contra-lateral vocal cord. We find that the network trained on the oral cavity data reaches an accura},
author = {Aubreville, Marc and Goncalves, Miguel and Knipfer, Christian and Oetter, Nicolai and Würfl, Tobias and Neumann, Helmut and Stelzle, Florian and Bohr, Christopher and Maier, Andreas},
booktitle = {Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018)},
date = {2018-01-19/2018-01-21},
doi = {10.5220/0006534700270034},
editor = {Sheldon Wiebe, Hugo Gamboa,Ana Fred, Sergi Bermúdez i Badia},
faupublication = {yes},
isbn = {978-989-758-278-3},
month = {Jan},
pages = {27-34},
peerreviewed = {Yes},
publisher = {SCITEPRESS – Science and Technology Publications, Lda},
title = {{Patch}-based {Carcinoma} {Detection} on {Confocal} {Laser} {Endomicroscopy} {Images} - {A} {Cross}-{Site} {Robustness} {Assessment}},
url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006534700270034},
venue = {Funchal},
year = {2018}
}
@inproceedings{faucris.118748784,
author = {Haase, Sven and Wasza, Jakob and Safak, Mustafa and Kilgus, Thomas and Maier-Hein, Lena and Feußner, Hubertus and Hornegger, Joachim},
booktitle = {2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.patchb},
pages = {509-512},
title = {{Patch} based {Specular} {Reflection} {Removal} for {Range} {Images} in {Hybrid} 3-{D} {Endoscopy}},
venue = {Beijing, China},
year = {2014}
}
@inproceedings{faucris.118749004,
author = {Xia, Yan and Bauer, Sebastian and Maier, Andreas and Berger, Martin and Hornegger, Joachim},
booktitle = {Proceedings of the third international conference on image formation in x-ray computed tomography},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.patien{\_}1},
pages = {414-417},
title = {{Patient}-bounded {Extrapolation} for {3D} {Region} of {Interest} {Reconstruction} in {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Xia14-PEF.pdf},
venue = {Salt Lake City, UT, USA},
year = {2014}
}
@article{faucris.118453324,
abstract = {Purpose: Three-dimensional (3D) volume-of-interest (VOI) imaging with C-arm systems provides anatomical information in a predefined 3D target region at a considerably low x-ray dose. However, VOI imaging involves laterally truncated projections from which conventional reconstruction algorithms generally yield images with severe truncation artifacts. Heuristic based extrapolation methods, e.g., water cylinder extrapolation, typically rely on techniques that complete the truncated data by means of a continuity assumption and thus appear to be ad-hoc. It is our goal to improve the image quality of VOI imaging by exploiting existing patient-specific prior information in the workflow. Methods: A necessary initial step prior to a 3D acquisition is to isocenter the patient with respect to the target to be scanned. To this end, low-dose fluoroscopic x-ray acquisitions are usually applied from anteriorposterior (AP) and medio-lateral (ML) views. Based on this, the patient is isocentered by repositioning the table. In this work, we present a patient-bounded extrapolation method that makes use of these noncollimated fluoroscopic images to improve image quality in 3D VOI reconstruction. The algorithm first extracts the 2D patient contours from the noncollimated AP and ML fluoroscopic images. These 2D contours are then combined to estimate a volumetric model of the patient. Forward-projecting the shape of the model at the eventually acquired C-arm rotation views gives the patient boundary information in the projection domain. In this manner, we are in the position to substantially improve image quality by enforcing the extrapolated line profiles to end at the known patient boundaries, derived from the 3D shape model estimate. Results: The proposed method was evaluated on eight clinical datasets with different degrees of truncation. The proposed algorithm achieved a relative root mean square error (rRMSE) of about 1.0% with respect to the reference reconstruction on nontruncated data, even in the presence of severe truncation, compared to a rRMSE of 8.0% when applying a state-of-the-art heuristic extrapolation technique. Conclusions: The method we proposed in this paper leads to a major improvement in image quality for 3D C-arm based VOI imaging. It involves no additional radiation when using fluoroscopic images that are acquired during the patient isocentering process. The model estimation can be readily integrated into the existing interventional workflow without additional hardware.},
author = {Xia, Yan and Bauer, Sebastian and Maier, Andreas and Berger, Martin and Hornegger, Joachim},
doi = {10.1118/1.4914135},
faupublication = {yes},
journal = {Medical Physics},
keywords = {computed tomography; extrapolation; fluoroscopic image; truncation correction; volume of interest imaging},
note = {UnivIS-Import:2015-07-08:Pub.2015.tech.IMMD.IMMD5.patien},
pages = {1787-1796},
peerreviewed = {Yes},
title = {{Patient}-bounded extrapolation using low-dose priors for volume-of-interest imaging in {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Xia15-PEU.pdf},
volume = {42},
year = {2015}
}
@article{faucris.110585244,
abstract = {Hemodynamic simulations are of increasing interest for the assessment of aneurysmal rupture risk and treatment planning. Achievement of accurate simulation results requires the usage of several patient-individual boundary conditions, such as a geometric model of the vasculature but also individualized inflow conditions.We propose the automatic estimation of various parameters for boundary conditions for computational fluid dynamics (CFD) based on a single 3D rotational angiography scan, also showing contrast agent inflow. First the data are reconstructed, and a patient-specific vessel model can be generated in the usual way. For this work, we optimize the inflow waveform based on two parameters, the mean velocity and pulsatility. We use statistical analysis of the measurable velocity distribution in the vessel segment to estimate the mean velocity. An iterative optimization scheme based on CFD and virtual angiography is utilized to estimate the inflow pulsatility. Furthermore, we present methods to automatically determine the heart rate and synchronize the inflow waveform to the patient's heart beat, based on time-intensity curves extracted from the rotational angiogram. This will result in a patient-individualized inflow velocity curve.The proposed methods were evaluated on two clinical datasets. Based on the vascular geometries, synthetic rotational angiography data was generated to allow a quantitative validation of our approach against ground truth data. We observed an average error of approximately [Formula: see text] for the mean velocity, [Formula: see text] for the pulsatility. The heart rate was estimated very precisely with an average error of about [Formula: see text], which corresponds to about 6 ms error for the duration of one cardiac cycle. Furthermore, a qualitative comparison of measured time-intensity curves from the real data and patient-specific simulated ones shows an excellent match.The presented methods have the potential to accurately estimate patient-specific boundary conditions from a single dedicated rotational scan.},
author = {Bögel, Marco and Gehrisch, Sonja and Redel, Thomas and Rohkohl, Christopher and Dörfler, Arnd and Maier, Andreas and Kowarschik, Markus and Hölter, Philip},
doi = {10.1007/s11548-016-1367-6},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
note = {EVALuna2:23010},
pages = {1061-9},
peerreviewed = {unknown},
title = {{Patient}-individualized boundary conditions for {CFD} simulations using time-resolved {3D} angiography},
volume = {11},
year = {2016}
}
@inproceedings{faucris.108054804,
address = {Moscow, Russia},
author = {Adelt, André and Schaller, Christian and Penne, Jochen and Hornegger, Joachim},
booktitle = {Proceedings of the 4th Russian-Bavarian Conference on Biomedical Engineering},
date = {2008-07-08/2008-07-09},
editor = {Bauernschmitt Robert, Chaplygin Yuri, Feußner Hubertus, Gulyaev Yuri, Hornegger Joachim, Mayr Ernst, Navab Nassir, Schookin Sergey, Umnyashkin Sergei},
faupublication = {yes},
pages = {202-207},
peerreviewed = {unknown},
publisher = {MIET},
title = {{Patient} positioning using 3-{D} surface registration},
venue = {Moscow Institute of Electronic Technology, Zeleonograd},
year = {2008}
}
@book{faucris.121187924,
abstract = {As decisions in cardiology increasingly rely on non-invasive methods, fast and precise image analysis tools have become a crucial component of the clinical workflow. Especially when dealing with complex cardiovascular disorders, such as valvular heart disease, advanced imaging techniques have the potential to significantly improve treatment outcome as well as to reduce procedure risks and related costs. We are developing patient-specific cardiac models, estimated from available multi-modal images, to enable advanced clinical applications for the management of cardiovascular disease. In particular, a novel physiological model of the complete heart, including the chambers and valvular apparatus is introduced, which captures a large spectrum of morphological, dynamic and pathological variations. To estimate the patient-specific model parameters from four-dimensional cardiac images, we have developed a robust learning-based framework. The model-driven approach enables a multitude of advanced clinical applications. Gold standard clinical methods, which manually process 2D images, can be replaced with fast, precise, and comprehensive model-based quantification to enhance cardiac analysis. For emerging percutaneous and minimal invasive valve interventions, cardiac surgeons and interventional cardiologists can substantially benefit from automated patient selection and virtual valve implantation techniques. Furthermore, the complete cardiac model enables for patient-specific hemodynamic simulations and blood flow analysis. Extensive experiments demonstrated the potential of these technologies to improve treatment of cardiovascular disease. © 2010 Springer-Verlag Berlin Heidelberg.},
address = {Heidelberg},
author = {Ionasec, Razvan and Voigt, Ingmar and Mihalef, Viorel and Grbic, Sasa and Vitanovski, Dime and Wang, Yabin and Zheng, Yefeng and Hornegger, Joachim and Navab, Nassir and Georgescu, Bogdan and Comaniciu, Dorin},
doi = {10.1007/978-3-642-15835-3{\_}2},
faupublication = {yes},
isbn = {978-3-642-15834-6},
note = {UnivIS-Import:2015-04-16:Pub.2010.tech.IMMD.IMMD5.patien},
pages = {14-24},
peerreviewed = {Yes},
publisher = {Springer-verlag},
series = {Lecture Notes in Computer Science},
title = {{Patient}-specific modeling of the heart: {Applications} to cardiovascular disease management},
volume = {null},
year = {2010}
}
@book{faucris.120189344,
abstract = {Patient-specific models of the heart physiology have become powerful instruments able to improve the diagnosis and treatment of cardiac disease. A systemic representation of the whole organ is required to capture the complex functional and hemodynamical interdependencies among the anatomical structures. We propose a novel framework for personalized modeling of the left-side heart that integrates comprehensive data of the morphology, function and hemodynamics. Patient-specific fluid dynamics are computed over the entire cardiac cycle using embedded boundary and ghost fluid methods, constrained by the dynamics of highly detailed anatomical models. Personalized boundary conditions are determined by estimating cardiac shape and motion from 4D TEE images through robust discriminative learning methods. Qualitative and quantitative validation of the computed blood dynamics is performed against Doppler echocardiography measurements, following an original methodology. Results showed a high agreement between simulation and ground truth and a correlation of r = 0.85 (p < 0.0002675). To the best of our knowledge, this is the first time that computational fluid dynamics are simulated on a systemic and comprehensive patient-specific model of the heart and validated against routinely acquired clinical ground truth. © 2011 Springer-Verlag Berlin Heidelberg.},
address = {Heidelberg},
author = {Voigt, Ingmar and Mansi, Tommaso and Mihalef, Viorel and Ionasec, Razvan and Calleja, Anna and Assoumou Mengue, Etienne and Sharma, Puneet and Houle, Helene and Georgescu, Bogdan and Hornegger, Joachim and Comaniciu, Dorin},
doi = {10.1007/978-3-642-21028-0{\_}44},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2011.tech.IMMD.IMMD5.patien},
pages = {341-349},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Patient}-{Specific} {Model} of {Left} {Heart} {Anatomy}, {Dynamics} and {Hemodynamics} from {4D} {TEE}: {A} {First} {Validation} {Study}},
volume = {null},
year = {2011}
}
@inproceedings{faucris.230589022,
abstract = {In many global tasks English is used as an international language. As a consequence, non-native speakers of the English language often communicate with other non-native speakers. An example is the Air Traffic Control (ATC) service which directs aircrafts on the ground and through controlled airspace. It is of course essential that there is a perfect understanding between the pilot and the ground-based controller to prevent collisions and to organize air traffic efficiently. Aviation English already accommodates non-native speakers of English by providing guidelines for wording and phraseology. To avoid confusion, for example, letters and numbers are spelled according to the international spelling alphabet provided by the International Civil Aviation Organization (ICAO). However, the ability to speak and understand English still has a high impact on communication success.
In this paper, we present a corpus that was recorded in the context of the ATC phraseology training system PATSY, the prototype of which was presented at the Show&Tell session at Interspeech 2015. The corpus consists of basic ATC utterances by speakers of 16 different mother tongues. Furthermore, "Please Call Stella" and part of "The Rainbow Passage" were recorded twice for every speaker with different biases. We plan on using this data to study the entrainment effect, which was observed for conversations by Levitan and Hirschberg. Preliminary results on basic ATC utterances show a moderate correlation between the speakers' self-assessment and the GoP (Goodness of Pronunciation) score.
++},
year = {1995}
}
@book{faucris.106533064,
address = {Erlangen},
editor = {Hornegger, Joachim and Höller, Kurt Emmerich and Spiegel, Martin and Niedermeier, Hans-Peter},
faupublication = {yes},
isbn = {978-3-00-031916-7},
note = {UnivIS-Import:2015-05-08:Pub.2010.tech.IMMD.IMMD5.rectif},
publisher = {Kloster Banz},
title = {{Pattern} {Recognition} in {Medical} and {Health} {Engineering} '10},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Hoeller10-ROE.pdf},
year = {2010}
}
@book{faucris.119448824,
address = {Erlangen},
editor = {Hornegger, Joachim and Höller, Kurt Emmerich and Ritt, Philipp and Borsdorf, Anja and Niedermeier, Hans-Peter},
faupublication = {yes},
isbn = {3-921713-34-X},
note = {UnivIS-Import:2015-07-08:Pub.2008.tech.IMMD.IMMD5.patter{\_}7},
publisher = {Union Aktuell},
title = {{Pattern} {Recognition} in {Medical} and {Health} {Engineering}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Hornegger08-PRI.pdf},
volume = {1},
year = {2008}
}
@book{faucris.119645504,
address = {Braunschweig},
author = {Paulus, Dietrich and Hornegger, Joachim},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
publisher = {Vieweg},
title = {{Pattern} {Recognition} of {Images} and {Speech} in {C}++},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Paulus97-PRO.pdf},
year = {1997}
}
@inproceedings{faucris.120324204,
abstract = {
In this paper, we report on classification results for emotional user states (4 classes, German database of children interacting with a pet robot). Starting with 5 emotion labels per word, we obtained chunks with different degrees of prototypicality. Six sites computed acoustic and linguistic features independently from each other. A total of 4232 features were pooled together and grouped into 10 low level descriptor types. For each of these groups separately and for all taken together, classification results using Support Vector Machines are reported for 150 features each with the highest individual Information Gain Ratio, for a scale of prototypicality. With both acoustic and linguistic features, we obtained a relative improvement of up to 27.6%, going from low to higher prototypicality.
},
address = {Brisbane},
author = {Seppi, Dino and Batliner, Anton and Schuller, Björn and Steidl, Stefan and Vogt, Thurid and Wagner, Johannes and Devillers, Laurence and Vidrascu, Laurence and Amir, Noam and Aharonson, Vered},
booktitle = {Proceedings of Interspeech},
date = {2008-10-22/2008-10-26},
editor = {ISCA},
faupublication = {yes},
keywords = {emotion; prototypes; feature types; automatic classification},
pages = {601-604},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{Patterns}, {Prototypes}, {Performance}: {Classifying} {Emotional} {User} {States}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Seppi08-PPP.pdf},
venue = {Brisbane},
year = {2008}
}
@inproceedings{faucris.121110704,
author = {Daum, Volker and Hahn, Dieter and Hornegger, Joachim and Kuwert, Torsten},
booktitle = {Proceedings of the MICCAI Workshop on Probabilistic Models For Medical Image Analysis},
date = {2009-09-20},
editor = {Wells William, Joshi Sarang, Pohl Kilian},
faupublication = {yes},
pages = {127-138},
peerreviewed = {unknown},
title = {{PCA} {Regularized} {Nonrigid} {Registration} for {PET}/{MRI} {Attenuation} {Correction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Daum09-PRN.pdf},
venue = {London},
year = {2009}
}
@inproceedings{faucris.121386144,
address = {Berlin, New York},
author = {Maier, Andreas and Haderlein, Tino and Schuster, Maria and Nöth, Elmar},
booktitle = {Proc. 41st Annual Meeting of the Society for Biomedical Technologies of the Association for Electrical, Electronic & Information Technologies (BMT 2007)},
date = {2007-09-26/2007-09-29},
editor = {CD-Rom},
faupublication = {yes},
pages = {no pagination},
peerreviewed = {Yes},
publisher = {De Gruyter},
title = {{PEAKS}-{A} {Platform} for {Evaluation} and {Analysis} of all {Kinds} of {Speech} {Disorders}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Maier07-PAP.pdf},
venue = {Aachen},
year = {2007}
}
@article{faucris.113164744,
author = {Maier, Andreas and Haderlein, Tino and Eysholdt, Ulrich and Rosanowski, Frank and Batliner, Anton and Schuster, Maria and Nöth, Elmar},
faupublication = {yes},
journal = {Speech Communication},
pages = {425-437},
peerreviewed = {Yes},
title = {{PEAKS} - {A} system for the automatic evaluation of voice and speech disorders},
url = {http://www.sciencedirect.com/science?{\_}ob=ArticleURL&{\_}udi=B6V1C-4VGWNSX-1&{\_}user=616145&{\_}rdoc=1&{\_}fmt=&{\_}orig=search&{\_}sort=d&view=c&{\_}acct=C000032322&{\_}version=1&{\_}urlVersion=0&{\_}userid=616145&md5=7591e91b78964fbc94b7c17f2ebf4eeb},
volume = {51.0},
year = {2009}
}
@inproceedings{faucris.113215784,
address = {Heidelberg},
author = {Maier, Andreas and Haderlein, Tino and Nöth, Elmar and Schuster, Maria},
booktitle = {Telemed 2008 Proceedings},
date = {2008-06-12/2008-06-15},
editor = {Schug S., Engelmann U.},
faupublication = {yes},
pages = {104-107},
peerreviewed = {Yes},
publisher = {Akademische Verlagsgesellschaft, Aka GmbH},
title = {{PEAKS}: {Ein} {Client}-{Server}-{Internetportal} zur {Bewertung} der {Aussprache}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Maier08-PEC.pdf},
venue = {Heidelberg},
year = {2008}
}
@inproceedings{faucris.122934504,
abstract = {Screening and diagnosis of breast cancer with Digital Breast Tomosynthesis (DBT) and Mammography are increasingly supported by algorithms for automatic post-processing. The pectoral muscle, which dorsally delineates the breast tissue towards the chest wall, is an important anatomical structure for navigation. Along with the nipple and the skin, the pectoral muscle boundary is often used for reporting the location of breast lesions. It is visible in mediolateral oblique (MLO) views where it is well approximated by a straight line. Here, we propose two machine learning-based algorithms to robustly detect the pectoral muscle in MLO views from DBT and mammography. Embedded into the Marginal Space Learning framework, the algorithms involve the evaluation of multiple candidate boundaries in a hierarchical manner. To this end, we propose a novel method for candidate generation using a Hough-based approach. Experiments were performed on a set of 100 DBT volumes and 95 mammograms from different clinical cases. Our novel combined approach achieves competitive accuracy and robustness. In particular, for the DBT data, we achieve significantly lower deviation angle error and mean distance error than the standard approach. The proposed algorithms run within a few seconds. © 2014 Springer International Publishing Switzerland.},
author = {Ghesu, Florin-Cristian and Wels, Michael and Jerebko, Anna and Sühling, Michael and Hornegger, Joachim and Kelm, B. Michael},
booktitle = {Medical Computer Vision. Large Data in Medical Imaging},
date = {2013-09-26/2013-09-26},
doi = {10.1007/978-3-319-05530-5{\_}15},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.pector},
pages = {148-157},
publisher = {Springer Verlag},
series = {Lecture Notes on Computer Science},
title = {{Pectoral} {Muscle} {Detection} in {Digital} {Breast} {Tomosynthesis} and {Mammography}},
venue = {Nagoya, Japan},
volume = {8331},
year = {2014}
}
@inproceedings{faucris.215851892,
abstract = {Fluoroscopy is used in a wide variety of examinations and procedures to diagnose or treat patients in modern pediatric medicine. Although these image guided interventions have many advantages in treating pediatric patients, understanding the deterministic and long term stochastic effects of ionizing radiation are of particular importance for this patient demographic. Therefore, quantitative estimation and visualization of radiation exposure distribution, and dose accumulation over the course of a procedure, is crucial for intra-procedure dose tracking and long term monitoring for risk assessment. Personalized pediatric models are necessary for precise determination of patient-X-ray interactions. One way to obtain such a model is to collect data from a population of pediatric patients, establish a population based generative pediatric model and use the latter for skin dose estimation. In this paper, we generate a population model for pediatric patient using data acquired by two RGB-D cameras from different views. A generative atlas was established using template registration. We evaluated the registered templates and generative atlas by computing the mean vertex error to the associated point cloud. The evaluation results show that the mean vertex error reduced from 25.2 ± 12.9 mm using an average surface model to 18.5 ± 9.4mm using specifically estimated pediatric surface model using the generated atlas. Similarly, the dose estimation error was halved from 10.6 ± 8.5% using the average surface model to 5.9 ± 9.3% using the personalized surface estimates.
Mapping Arbitrary Symbol Sets Is Very Easy) with which it is possible to create efficient online modules for automatic symbol mapping. Our framework is solely based on statistical methods for training and run-time and has been optimized for P2G conversion in the context of spoken inquiries to the Semantic Web, an issue researched in the SmartWeb project (https://www.dfki.de/web/forschung/projekte-publikationen/projekte/projekt/smartweb/). MASSIVE systems can be trained using a pronunciation lexicon, the output of a phone recognizer or any other suitable set of corresponding symbol strings. Successful tests have been performed on German and English data sets.
In C-arm computed tomography there are
certain constraints due to the data acquisition process which can cause
limited raw data. The reconstructed image’s quality may significantly
decrease depending on these constraints. To compensate for severely
under-sampled projection data during reconstruction, special algorithms
have to be utilized, more robust to such ill-posed problems.
In
the past few years it has been shown that reconstruction algorithms
based on the theory of compressed sensing are able to handle incomplete
data sets quite well. In this paper, the iterative iTV reconstruction
method by Ludwig Ritschl et al. is analyzed regarding it’s elimination
capabilities of image artifacts caused by incomplete raw data with
respect to the settings of it’s various parameters.
The
evaluation of iTV and the data dependency of iterative reconstruction’s
parameters is conducted in two stages. First, projection data with
severe angular under-sampling is acquired using an analytical phantom.
Proper reconstruction parameters are selected by analyzing the
reconstruction results from a set of proposed parameters. In a second
step multiple phantom data sets are acquired with limited angle geometry
and a small number of projections.
The iTV reconstructions of
these data sets are compared to short-scan FDK and SART reconstruction
results, highlighting the distinct data dependence of the iTV
reconstruction parameters.
},
address = {Berlin Heidelberg},
author = {Amrehn, Mario and Maier, Andreas and Dennerlein, Frank and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2015},
date = {2015-03-15/2015-03-17},
doi = {10.1007/978-3-662-46224-9},
faupublication = {yes},
isbn = {978-3-662-46223-2},
keywords = {health; medicine; image processing; reconstruction; segmentation; pattern recognition; machine learning},
note = {UnivIS-Import:2018-09-06:Pub.2015.tech.IMMD.IMMD5.portab{\_}4},
pages = {131-136},
peerreviewed = {Yes},
publisher = {Vieweg+Teubner Verlag},
title = {{Portability} of {TV}-{Regularized} {Reconstruction} {Parameters} to {Varying} {Data} {Sets}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Amrehn15-POT.pdf},
venue = {Lübeck},
year = {2015}
}
@inproceedings{faucris.120182524,
abstract = {Minimally invasive catheter ablation of electric foci, performed in electrophysiology labs, is an attractive treatment option for atrial fibrillation (AF)-in particular if drug therapy is no longer effective or tolerated. There are different strategies to eliminate the electric foci inducing the arrhythmia. Independent of the particular strategy, it is essential to place transmural lesions. The impact of catheter contact force on the generated lesion quality has been investigated recently, and first results are promising. There are different approaches to measure catheter-tissue contact. Besides traditional haptic feedback, there are new technologies either relying on catheter tip-to-tissue contact force or on local impedance measurements at the tip of the catheter. In this paper, we present a novel tool for post-procedural ablation point evaluation and visualization of contact force characteristics. Our method is based on localizing ablation points set during AF ablation procedures. The 3-D point positions are stored together with lesion specific catheter contact force (CF) values recorded during the ablation. The force records are mapped to the spatial 3-D positions, where the energy has been applied. The tracked positions of the ablation points can be further used to generate a 3-D mesh model of the left atrium (LA). Since our approach facilitates visualization of different force characteristics for post-procedural evaluation and verification, it has the potential to improve outcome by highlighting areas where lesion quality may be less than desired. © 2012 SPIE.},
author = {Koch, Martin and Brost, Alexander and Kiraly, Attila P. and Strobel, Norbert and Hornegger, Joachim},
booktitle = {Medical Imaging 2012: Computer-Aided Diagnosis},
doi = {10.1117/12.912315},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Post}-procedural evaluation of catheter contact force characteristics},
venue = {San Diego, CA},
volume = {8315},
year = {2012}
}
@inproceedings{faucris.115867224,
author = {Pasluosta, Cristian Federico and Barth, Jens and Gaßner, Heiko and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn},
booktitle = {88th Congress of the Deutschen Gesellschaft für Neurologie mit Fortbildungsakademie (DGN)},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Postural} {Instability} {Inference} in {Parkinson}'s {Disease} {Patients} {Using} {Wearable} {Sensors}},
venue = {Düsseldorf},
year = {2015}
}
@inproceedings{faucris.123924504,
abstract = {Continuous precipitation is a promising process to generate nanoparticles with tailored properties. One challenge is to predict the PSD by considering all fluid dynamical, physiochemical and thermodynamical process parameters. A CFD-based approach using DNS in combination with Lagrangian Particle Tracking is applied coupled with micromixing and population balance models. The simulated flow field is validated by optical measurement methods (PIV and LIF). Whereas the mean particle size in dependence of the Re-number (over 6 orders of magnitude) can be predicted by a 1D approach, prediction of the complete PSD needs information from the fully resolved 3D fluid flow field.},
author = {Peukert, Wolfgang and Gradl, Johannes and Schwertfirm, Florian and Schwarzer, Hans-Christoph and Manhart, Michael},
faupublication = {yes},
keywords = {precipitation; continuous; mixing; prediction; simulation;},
pages = {799-804},
peerreviewed = {unknown},
title = {{Precipitation} of nanoparticles: {A} coupled {LIF} / {PIV}, {DNS} and {PBE} approach for prediction of the particle size distribution ({PSD})},
url = {https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=27344447739&origin=inward},
year = {2005}
}
@article{faucris.123354264,
abstract = {Mixing is a key parameter to tailor the particle size distribution (PSD) in nanoparticle precipitation. In this study we present two model approaches to simulate the impact of mixing on the PSD, using barium sulfate as exemplary material. In the first model, we combine a Lagrangian micromixing model with the population balance equation. This approach was found successful in predicting the influence of mixing on mean particle sizes but fails to predict the shape and width of the PSD. This is attributed to the neglect of spatial and temporal fluctuations in that model. Therefore, an improved CFD-based approach using direct numerical simulation (DNS) in combination with Lagrangian particle tracking strategy is applied. We found that the full DNS-approach, coupled to the population balance and a derived micromixing model, is capable of predicting the full PSD in nanoparticle precipitation. © 2006 Elsevier B.V. All rights reserved.},
author = {Peukert, Wolfgang and Gradl, Johannes and Schwarzer, Hans-Christoph and Schwertfirm, Florian and Manhart, Michael},
doi = {10.1016/j.cep.2005.11.012},
faupublication = {yes},
journal = {Chemical Engineering and Processing},
keywords = {Direct numeric simulation; Micromixing; Nanoparticle precipitation; Population balance; Supersaturation},
pages = {908-916},
peerreviewed = {Yes},
title = {{Precipitation} of nanoparticles in a {T}-mixer: {Coupling} the particle population dynamics with hydrodynamics through direct numerical simulation},
volume = {45},
year = {2006}
}
@inproceedings{faucris.122598124,
abstract = {Coronary computed tomography angiography (CCTA) allows for non-invasive identification and grading of stenoses by evaluating the degree of narrowing of the blood-filled vessel lumen. Recently, methods have been proposed that simulate coronary blood flow using computational fluid dynamics (CFD) to compute the fractional flow reserve non-invasively. Both grading and CFD rely on a precise segmentation of the vessel lumen from CCTA.We propose a novel, model-guided segmentation approach based on a Markov random field formulation with convex priors which assures the preservation of the tubular structure of the coronary lumen. Allowing for various robust smoothness terms, the approach yields very accurate lumen segmentations even in the presence of calcified and non-calcified plaques. Evaluations on the public Rotterdam segmentation challenge demonstrate the robustness and accuracy of our method: on standardized tests with multi-vendor CCTA from 30 symptomatic patients, we achieve superior accuracies as compared to both state-of-the-art methods and medical experts.},
address = {Cambridge, MA, USA},
author = {Lugauer, Felix and Zheng, Yefeng and Hornegger, Joachim and Kelm, B. Michael},
booktitle = {Medical Computer Vision: Algorithms for Big Data},
date = {2014-09-18/2014-09-18},
doi = {10.1007/978-3-319-13972-2{\_}13},
faupublication = {yes},
isbn = {978-3-319-13971-5},
keywords = {CCTA; Lumen segmentation; Markov random field; Tubular surface},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.precis},
pages = {137-147},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {{Precise} {Lumen} {Segmentation} in {Coronary} {Computed} {Tomography} {Angiography}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Lugauer14-PLS.pdf},
venue = {Cambridge, MA, USA},
year = {2014}
}
@inproceedings{faucris.203854588,
author = {Syben-Leisner, Christopher and Stimpel, Bernhard and Breininger, Katharina and Würfl, Tobias and Fahrig, Rebecca and Dörfler, Arnd and Maier, Andreas},
booktitle = {Proceedings of the 5th International Conference on Image Formation in X-ray Computed Tomography},
faupublication = {yes},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.precis{\_}0},
pages = {386-390},
peerreviewed = {unknown},
title = {{Precision} {Learning}: {Reconstruction} {Filter} {Kernel} {Discretization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Syben18-PLR.pdf},
venue = {Salt Lake City, Utha, USA},
year = {2018}
}
@inproceedings{faucris.203725131,
author = {Maier, Andreas and Schebesch, Frank and Syben-Leisner, Christopher and Würfl, Tobias and Steidl, Stefan and Choi, Jang-Hwan and Fahrig, Rebecca},
booktitle = {2018 24rd International Conference on Pattern Recognition (ICPR)},
doi = {10.1109/icpr.2018.8545553},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.precis{\_}5},
pages = {183-188},
peerreviewed = {unknown},
title = {{Precision} {Learning}: {Towards} {Use} of {Known} {Operators} in {Neural} {Networks}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Maier18-PLT.pdf},
venue = {Beijing, China},
year = {2018}
}
@inproceedings{faucris.230008438,
abstract = {In order to ensure trouble-free operation, prediction of hardware failures is essential. This applies especially to medical systems. Our goal is to determine hardware which needs to be exchanged before failing. In this work, we focus on predicting failures of head/neck coils using image-related measurements. Thus, we aim to solve a classification problem with two classes, normal and broken coil. To solve this problem, we use data of two different levels. One level refers to one-dimensional features per individual coil channel on which we found a fully connected neural network to perform best. Furthermore, we use matrix features representing the state of an entire coil to train another neural network on. This ensemble of two networks and combining them using a Random Forest improves the prediction results even further. Thus, combining insights of both trained models allows us to determine the coil's condition with an F-score of 94.14% and an accuracy of 99.09%.},
author = {Kuhnert, Nadine and Pflueger, Lea and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2020},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}28},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Prediction} of {MRI} {Hardware} {Failures} based on {Image} {Features} using {Ensemble} {Learning}},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.230971127,
abstract = {Already before systems malfunction one has to know if hardware components will fail in near future in order to counteract in time. Thus, unplanned downtime is ought to be avoided. In medical imaging, maximizing the system's uptime is crucial for patients' health and healthcare provider's daily business. We aim to predict failures of Head/Neck coils used in Magnetic Resonance Imaging (MRI) by training a statistical model on sequential data collected over time. As image features depend on the coil's condition, their deviations from the normal range already hint to future failure. Thus, we used image features and their variation over time to predict coil damage. After comparison of different time series classification methods we found Long Short Term Memorys (LSTMs) to achieve the highest F-score of 86.43% and to tell with 98.33% accuracy if hardware should be replaced.
},
author = {Kuhnert, Nadine and Pflueger, Lea and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin},
date = {2020-03-15/2020-03-17},
doi = {10.1007/978-3-658-29267-6{\_}27},
faupublication = {yes},
keywords = {Time Series Classification; LSTM; Classification; Time Series Prediction},
peerreviewed = {unknown},
title = {{Prediction} of {MRI} {Hardware} {Failures} based on {Image} {Features} using {Time} {Series} {Classification}},
venue = {Berlin},
year = {2020}
}
@inproceedings{faucris.118750544,
address = {Heidelberg},
author = {Taubmann, Oliver and Wasza, Jakob and Forman, Christoph and Fischer, Peter and Wetzl, Jens and Maier, Andreas and Hornegger, Joachim},
booktitle = {Proceedings of the 28th International Congress and Exhibition},
faupublication = {yes},
keywords = {Respiratory Motion; Motion Modeling; Motion Prediction; External Surrogate},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.predic{\_}9},
pages = {33-34},
publisher = {Springer},
series = {International Journal of Computer Assisted Radiology and Surgery},
title = {{Prediction} of {Respiration}-{Induced} {Internal} 3-{D} {Deformation} {Fields} {From} {Dense} {External} 3-{D} {Surface} {Motion}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Taubmann14-POR.pdf},
venue = {Fukuoka, Japan},
volume = {9},
year = {2014}
}
@inproceedings{faucris.120779164,
author = {Wetzl, Jens and Forman, Christoph and Maier, Andreas and Hornegger, Joachim and Zenge, Michael O.},
booktitle = {Proceedings of the 23rd Annual Meeting of the ISMRM (ISMRM 2015)},
faupublication = {yes},
note = {UnivIS-Import:2015-07-08:Pub.2015.tech.IMMD.IMMD5.predic},
pages = {4523},
title = {{Prediction} of the {Benefit} of {Motion}-{Compensated} {Reconstruction} for {Whole}-{Heart} {Coronary} {MRI}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Wetzl15-POT.pdf},
venue = {Toronto, Canada},
year = {2015}
}
@article{faucris.120498664,
abstract = {Nanoparticle precipitation is an interesting process to generate particles with tailored properties. In this study we investigate the impact of various process steps such as solid formation, mixing and agglomeration on the resulting particle size distribution (PSD) as representative property using barium sulfate as exemplary material. Besides the experimental investigation, process simulations were carried out by solving the full 1D population balance equation coupled to a model describing the micromixing kinetics based on a finite-element Galerkin h-p-method. This combination of population balance and micromixing model was applied successfully to predict the influence of mixing on mean sizes (good quantitative agreement between experimental data and simulation results are obtained) and gain insights into nanoparticle precipitation: The interfacial energy was identified to be a critical parameter in predicting the particle size, poor mixing results in larger particles and the impact of agglomeration was found to increase with supersaturation due to larger particle numbers. Shear-induced agglomeration was found to be controllable through the residence time in turbulent regions and the intensity of turbulence, necessary for intense mixing but undesired due to agglomeration. By this approach, however, the distribution width is underestimated which is attributed to the large spectrum of mixing histories of fluid elements on their way through the mixer. Therefore, an improved computational fluid dynamics-based approach using direct numerical simulation with a Lagrangian particle tracking strategy is applied in combination with the coupled population balance-micromixing approach. We found that the full DNS-approach, coupled to the population balance and micromixing model is capable of predicting not only the mean sizes but the full PSD in nanoparticle precipitation. © 2005 Elsevier Ltd. All rights reserved.},
author = {Peukert, Wolfgang and Schwarzer, Hans-Christoph and Schwertfirm, Florian and Manhart, Michael and Schmid, Hans-Joachim},
doi = {10.1016/j.ces.2004.11.064},
faupublication = {yes},
journal = {Chemical Engineering Science},
keywords = {Computational fluid dynamics; Direct numerical simulation; Micromixing; Nanoparticle; Population balance; Precipitation},
pages = {167-181},
peerreviewed = {Yes},
title = {{Predictive} simulation of nanoparticle precipitation based on the population balance equation},
volume = {61},
year = {2006}
}
@book{faucris.119614044,
author = {Jelinek, Fred and Nöth, Elmar},
doi = {10.1007/3-540-48239-3},
faupublication = {yes},
isbn = {9783540664949},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{Preface}},
volume = {1692},
year = {1999}
}
@inproceedings{faucris.203854940,
author = {Bayer, Siming and Schaffert, Roman and Ravikumar, Nishant and Maier, Andreas and Fahrig, Rebecca and Ostermeier, Martin and Tong, Xiaoguang and Wang, Hu},
booktitle = {Bildverarbeitung für die Medizin 2018},
date = {2018-03-11/2018-03-13},
doi = {10.1007/978-3-662-56537-7{\_}48},
faupublication = {yes},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.prelim{\_}3},
pages = {163-168},
peerreviewed = {Yes},
publisher = {Springer Berlin Heidelberg},
title = {{Preliminary} {Study} {Investigating} {Brain} {Shift} {Compensation} using {3D} {CBCT} {Cerebral} {Vascular} {Images}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Bayer18-PSI.pdf},
venue = {Erlangen},
year = {2018}
}
@article{faucris.224166780,
abstract = {The article concerns the interpretation of the principal components of the spectrogram of the speech signal and its application to the description of dysarthric speech. Each principal component is a linear combination of the frame spectra. We show that the first principal component of the spectrogram is closely related to the long-term average spectrum (LTAS) and the second principal component is the difference of two weighted sums of frame spectra reporting open and close vowel frame spectra respectively. We investigate articulation deficits in dysarthric speakers via cues obtained from principal components of the spectrogram of connected speech because long-term average spectra have been claimed to inform about speaker settings of the vocal tract.},
author = {Kacha, Abdellah and Grenez, Francis and Orozco Arroyave, Juan Rafael and Schoentgen, Jean},
doi = {10.1016/j.csl.2019.07.001},
faupublication = {yes},
journal = {Computer Speech and Language},
keywords = {Dysarthric speech; Long-term average spectrum; Principal component analysis; Spectrogram},
month = {Jan},
note = {CRIS-Team Scopus Importer:2019-08-09},
pages = {114-122},
peerreviewed = {unknown},
title = {{Principal} component analysis of the spectrogram of the speech signal: {Interpretation} and application to dysarthric speech},
volume = {59},
year = {2020}
}
@inproceedings{faucris.279668463,
abstract = {In current clinical practice, examinations of the carotid artery bifurcation are commonly carried out with Computed Tomography Angiography (CTA) or contrast-enhanced Magnetic Resonance Angiography (ceMRA). Quantitative information about vessel morphology, extracted from segmentations, is promising for diagnosis of vessel pathologies. However, both above-mentioned techniques require the administration of contrast media. In contrary, non-ce MRA methods such as Time-of-Flight (TOF) provide fully non-invasive imaging without any exogenous contrast agent. The diagnostic value of TOF MRA, however, for assessment of the carotid bifurcation area can be hampered due to its susceptibility to irregular blood flow patterns. Conventional methods for lumen segmentation are very sensitive to such signal voids and produce inaccurate results. In this work, a novel, fully automatic 3D segmentation algorithm is proposed which uses prior knowledge about irregular flow patterns. The presented technique has been successfully tested on eleven volunteer datasets as well as in a patient case, offering the comparison to CTA images. The sensitivity could be increased by 29.2% to 85.6% compared to standard level set methods. The root mean squared error in diameter measurements was reduced from 4.85mm to 1.44 mm.},
author = {Hutter, Jana and Hofmann, Hannes and Grimm, Robert and Greiser, Andreas and Saake, Marc and Hornegger, Joachim and Dörfler, Arnd and Schmitt, Peter},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2012-10-05/2012-10-05},
doi = {10.1007/978-3-642-33418-4{\_}63},
editor = {Georg Langs, Le Lu, Bjoern H. Menze, Georg Langs, Zhuowen Tu, Bjoern H. Menze, Nicholas Ayache, Hervé Delingette, Antonio Criminisi, Albert Montillo, Polina Golland, Kensaku Mori},
faupublication = {yes},
isbn = {9783642334177},
note = {CRIS-Team Scopus Importer:2022-08-05},
pages = {511-518},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{Prior}-based automatic segmentation of the carotid artery lumen in {TOF} {MRA} ({PASCAL})},
venue = {FRA},
volume = {7511 LNCS},
year = {2012}
}
@article{faucris.212542934,
abstract = {Rotational coronary angiography using C-arm angiography systems enables intra-procedural 3-D imaging that is considered beneficial for diagnostic assessment and interventional guidance. Despite previous efforts, rotational angiography was not yet successfully established in clinical practice for coronary artery procedures due to challenges associated with substantial intra-scan respiratory and cardiac motion. While gating handles cardiac motion during reconstruction, respiratory motion requires compensation. State-of-the-art algorithms rely on 3-D / 2-D registration that requires an uncompensated reconstruction of sufficient quality. To overcome this limitation, we investigate two prior-free respiratory motion estimation methods based on the optimization of: 1) epipolar consistency conditions (ECCs) and 2) a task-based auto-focus measure (AFM). The methods assess redundancies in projection images or impose favorable properties of 3-D space, respectively, and are used to estimate the respiratory motion of the coronary arteries within rotational angiograms. We evaluate our algorithms on the publicly available CAVAREV benchmark and on clinical data. We quantify reductions in error due to respiratory motion compensation using a dedicated reconstruction domain metric. Moreover, we study the improvements in image quality when using an analytic and a novel temporal total variation regularized algebraic reconstruction algorithm. We observed substantial improvement in all figures of merit compared with the uncompensated case. Improvements in image quality presented as a reduction of double edges, blurring, and noise. Benefits of the proposed corrections were notable even in cases suffering little corruption from respiratory motion, translating to an improvement in the vessel sharpness of (6.08 ± 4.46)% and (14.7 ± 8.80)% when the ECC-based and the AFM-based compensation were applied. On the CAVAREV data, our motion compensation approach exhibits an improvement of (27.6 ± 7.5)% and (97.0 ± 17.7)% when the ECC and AFM were used, respectively. At the time of writing, our method based on AFM is leading the CAVAREV scoreboard. Both motion estimation strategies are purely image-based and accurately estimate the displacements of the coronary arteries due to respiration. While current evidence suggests the superior performance of AFM, future work will further investigate the use of ECC in the context of angiography as they solely rely on geometric calibration and projection-domain images.
},
author = {Unberath, Mathias and Taubmann, Oliver and Aichert, André and Achenbach, Stephan and Maier, Andreas},
doi = {10.1109/TMI.2018.2806310},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
note = {EVALuna2:35976},
pages = {1999-2009},
peerreviewed = {Yes},
title = {{Prior}-{Free} {Respiratory} {Motion} {Estimation} in {Rotational} {Angiography}},
volume = {37},
year = {2018}
}
@inproceedings{faucris.124052984,
author = {Morgner, Philipp and Müller, Christian and Ring, Matthias and Eskofier, Björn and Riess, Christian and Armknecht, Frederik and Benenson, Zinaida},
booktitle = {Proceedings of the 22nd European Symposium on Research in Computer Security (ESORICS 2017)},
doi = {10.1007/978-3-319-66399-9{\_}18},
faupublication = {yes},
pages = {324-343},
peerreviewed = {Yes},
title = {{Privacy} {Implications} of {Room} {Climate} {Data}},
url = {https://faui1-files.cs.fau.de/filepool/publications/esorics2017{\_}privacy{\_}room{\_}climate.pdf},
venue = {Oslo},
year = {2017}
}
@article{faucris.108065584,
abstract = {
The ‘traditional’ first two dimensions in emotion research are VALENCE and AROUSAL. Normally, they are obtained by using elicited, acted data. In this paper, we use realistic, spontaneous speech data from our ‘AIBO’ corpus (human-robot communication, children interacting with Sony’s AIBO robot). The recordings were done in a Wizard-of-Oz scenario: the children believed that AIBO obeys their commands; in fact, AIBO followed a fixed script and often disobeyed. Five labellers annotated each word as belonging to one of eleven emotion-related states; seven of these states which occurred frequently enough are dealt with in this paper. The confusion matrices of these labels were used in a Non-Metrical Multi-dimensional Scaling to display two dimensions; the first we interpret as VALENCE, the second, however, not as AROUSAL but as INTERACTION, i.e., addressing oneself (angry, joyful) or the communication partner (motherese, reprimanding). We show that it depends on the specifity of the scenario and on the subjects’ conceptualizations whether this new dimension can be observed, and discuss impacts on the practice of labelling and processing emotional data. Two-dimensional solutions based on acoustic and linguistic features that were used for automatic classification of these emotional states are interpreted along the same lines.
},
author = {Batliner, Anton and Steidl, Stefan and Hacker, Christian and Nöth, Elmar},
doi = {10.1007/s11257-007-9039-4},
faupublication = {yes},
journal = {User Modeling and User-Adapted Interaction},
keywords = {emotion; speech; dimensions; categories; annotation; data-driven; non- metrical multi-dimensional scaling},
pages = {175-206},
peerreviewed = {Yes},
title = {{Private} emotions versus social interaction: a data-driven approach towards analysing emotion in speech},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Batliner08-PEV.pdf},
volume = {18.0},
year = {2008}
}
@inproceedings{faucris.107895964,
abstract = {
The ‘traditional’ first two dimensions in emotion research are AROUSAL and VALENCE. Normally, they are obtained by using elicited, acted data. In this paper, we use realistic, spontaneous speech data from our ‘AIBO’ corpus (human-robot communication, children interacting with Sony’s AIBO robot). TherecordingsweredoneinaWizard-of-Ozscenario: the children believed that AIBO obeys their commands; in fact, AIBO followed a fixed script and often disobeyed. The emotional annotations of five labellers, transformed into a confusion matrix, were used in a non-metrical multi-dimensional scaling to display two dimensions, the first being VALENCE, the second, however, not AROUSAL but INTERACTION, i.e., addressing oneself (angry, joyful) or the communication partner (motherese, reprimanding). We show that it depends on the specifity of the scenario and on the subjects’ conceptualizations whether this new dimension can be observed, and discuss impacts on the practice of labelling and processing emotional data.
},
author = {Batliner, Anton and Steidl, Stefan and Hacker, Christian and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Adapting the Interaction Style to Affective Factors},
date = {2005-07-25},
editor = {Carberry Sandra, de Rosis Fiorella},
faupublication = {yes},
keywords = {emotion; categories; dimensions; annotation; non-metrical multi-dimensional scaling},
pages = {1-8},
peerreviewed = {Yes},
title = {{Private} {Emotions} vs. {Social} {Interaction} - towards {New} {Dimensions} in {Research} on {Emotion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Batliner05-PEV.pdf},
venue = {Edinburgh},
year = {2005}
}
@inproceedings{faucris.121443784,
address = {-},
author = {Hornegger, Joachim and Niemann, Heinrich and Shimshoni, Ilan},
booktitle = {3D Image Analysis and Synthesis '96},
date = {1996-11-18/1996-11-19},
editor = {Girod B., Niemann Heinrich, Seidel H.-P.},
faupublication = {yes},
pages = {73-80},
peerreviewed = {unknown},
publisher = {Infix},
title = {{Probabilistic} {Methods} for 3-{D} {Object} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1996/Hornegger96-PMF.pdf},
venue = {Erlangen},
year = {1996}
}
@article{faucris.120208924,
abstract = {This paper introduces a uniform statistical framework for both 3-D and 2-D object recognition using intensity images as input data. The theoretical part provides a mathematical tool for stochastic modeling. The algorithmic part introduces methods for automatic model generation, localization, and recognition of objects. 2-D images are used for learning the statistical appearance of 3-D objects; both the depth information and the matching between image and model features are missing for model generation. The implied incomplete data estimation problem is solved by the Expectation Maximization algorithm. This leads to a novel class of algorithms for automatic model generation from projections. The estimation of pose parameters corresponds to a non-linear maximum likelihood estimation problem which is solved by a global optimization procedure. Classification is done by the Bayesian decision rule. This work includes the experimental evaluation of the various facets of the presented approach. An empirical evaluation of learning algorithms and the comparison of different pose estimation algorithms show the feasibility of the proposed probabilistic framework.},
author = {Hornegger, Joachim and Niemann, Heinrich},
doi = {10.1023/A:1026515828914},
faupublication = {yes},
journal = {International Journal of Computer Vision},
pages = {229-251},
peerreviewed = {Yes},
title = {{Probabilistic} modeling and recognition of 3-{D} objects},
volume = {39},
year = {2000}
}
@incollection{faucris.107978464,
address = {London},
author = {Hornegger, Joachim and Paulus, Dietrich and Niemann, Heinrich},
booktitle = {Computer Vision and Applications},
doi = {10.1016/B978-012379777-3/50016-9},
faupublication = {yes},
isbn = {978-0-12-379777-3},
pages = {517-540},
peerreviewed = {unknown},
publisher = {Academic Press},
title = {{Probabilistic} {Modeling} in {Computer} {Vision}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Hornegger99-PMI.pdf},
volume = {2.0},
year = {2000}
}
@inproceedings{faucris.111027664,
address = {-},
author = {Haas, Jürgen and Hornegger, Joachim and Niemann, Heinrich},
booktitle = {Proceedings of the International Workshop on Speech and Computer},
date = {1998-10-26/1998-10-29},
editor = {SPECOM'99},
faupublication = {yes},
pages = {151-158},
peerreviewed = {unknown},
publisher = {-},
title = {{Probabilistic} {Semantic} {Analysis} {In} {Restricted} {Domains}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1998/Haas98-PSA.pdf},
venue = {St. Petersburg},
year = {1998}
}
@inproceedings{faucris.108242464,
address = {Berlin},
author = {Haas, Jürgen and Hornegger, Joachim and Huber, Richard and Niemann, Heinrich},
booktitle = {Mustererkennung 1997},
date = {1997-09-15/1997-09-17},
doi = {10.1007/978-3-642-60893-3{\_}28},
editor = {Paulus E., Wahl F.},
faupublication = {yes},
isbn = {978-3-540-63426-3},
pages = {270-277},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Probabilistic} semantic analysis of speech},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Haas97-PSA.pdf},
venue = {Braunschweig},
year = {1997}
}
@article{faucris.114952684,
abstract = {Classical surgery is being overtaken by minimally invasive and transcatheter procedures. As there is no direct view or access to the affected anatomy, advanced imaging techniques such as 3D C-arm computed tomography (CT) and C-arm fluoroscopy are routinely used in clinical practice for intraoperative guidance. However, due to constraints regarding acquisition time and device configuration, intraoperative modalities have limited soft tissue image quality and reliable assessment of the cardiac anatomy typically requires contrast agent, which is harmful to the patient and requires complex acquisition protocols. We propose a probabilistic sparse matching approach to fuse high-quality preoperative CT images and nongated, noncontrast intraoperative C-arm CT images by utilizing robust machine learning and numerical optimization techniques. Thus, high-quality patient-specific models can be extracted from the preoperative CT and mapped to the intraoperative imaging environment to guide minimally invasive procedures. Extensive quantitative experiments on 95 clinical datasets demonstrate that our model-based fusion approach has an average execution time of 1.56 s, while the accuracy of 5.48 mm between the anchor anatomy in both images lies within expert user confidence intervals. In direct comparison with image-to-image registration based on an open-source state-of-the-art medical imaging library and a recently proposed quasi-global, knowledge-driven multi-modal fusion approach for thoracic-abdominal images, our model-based method exhibits superior performance in terms of registration accuracy and robustness with respect to both target anatomy and anchor anatomy alignment errors.},
author = {Neumann, Dominik and Grbic, Sasa and John, Matthias and Navab, Nassir and Hornegger, Joachim and Ionasec, Razvan},
doi = {10.1109/TMI.2014.2343936},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
keywords = {Anatomical overlay; computed tomography (CT); model-based cardiac image registration; Procedure guidance},
note = {UnivIS-Import:2015-04-02:Pub.2015.tech.IMMD.IMMD5.probab},
pages = {49-60},
peerreviewed = {Yes},
title = {{Probabilistic} {Sparse} {Matching} for {Robust} {3D}/{3D} {Fusion} in {Minimally} {Invasive} {Surgery}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Neumann15-PSM.pdf},
volume = {34},
year = {2015}
}
@inproceedings{faucris.121157124,
abstract = {Fundus imaging is one of themost commonly used modalities for examining retinal structures. The images are mostly analyzed by physicians. These diagnoses are subjective with a high rate of inter-observer variability, therefore an automated or a computer aided diagnosis is needed to speed up the monotonous screening process and to provide objective measurements. In this article we present an automatic algorithm for localization of the optic disk center in fundus images. The application field of the algorithm is preprocessing for further algorithms such as segmentation of the optic disk boundary, vessel tracking etc. The algorithm is evaluated using the DRIVE database and our own public high resolution image database. The tests show a localization error less than 0.2 optic disk diameter (ODD) in case of the high resolution database, and less than 0.35 ODD in case of the lower resolution DRIVE database. © 2012 Institute of Telecommunica.},
author = {Budai, Attila and Laurik, Lenke and Hornegger, Joachim and Somfai, Gábor M. and Michelson, Georg},
booktitle = {2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012},
faupublication = {yes},
pages = {568-571},
peerreviewed = {unknown},
title = {{Probability} map based localization of optic disk},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-84863946233&origin=inward},
venue = {Vienna},
volume = {null},
year = {2012}
}
@article{faucris.211594230,
abstract = {Probe-based confocal laser endomicroscopy (CLE) is an innovative technique for real-time, non-invasive analysis of the surface epithelium. While being successfully used for diagnosis by experts, this method has not yet been established in clinical routine, partly due to the lack of standards and criteria for classifying various lesions. Our aim was to determine the diagnostic value and inter-rater reliability of CLE in detecting malignant lesions of the vocal cords. 58 video sequences were extracted from the probe-based CLE (GastroFlex probe with a Cellvizio® laser system) examinations of 3 patients with squamous cell carcinomas and 4 patients with benign alterations of the vocal folds. Two ENT surgeons, who were blinded to the histological result, were asked to identify the sequences representing a carcinoma. We showed an accuracy, sensitivity, specificity, PPV and NPV of 91.38-96.55%, 100%, 87.8-95.2%, 77.27-89.47% and 100%, respectively, with an inter-rater reliability of k = 0.89 ("almost perfect agreement"). Probe-based CLE is a promising method for diagnosis and assessment of vocal fold lesions in vivo. Our results suggest that, with adequate training, the diagnostic value of this technique can be improved and potentially provide important information during oncological surgery.},
author = {Goncalves, Miguel and Aubreville, Marc and Mueller, Sarina K. and Sievert, Matti and Maier, Andreas and Iro, Heinrich and Bohr, Christopher},
doi = {10.14639/0392-100X-2121},
faupublication = {yes},
journal = {Acta Otorhinolaryngologica Italica},
month = {Jan},
peerreviewed = {Yes},
title = {{Probe}-based confocal laser endomicroscopy in detecting malignant lesions of vocal folds.},
year = {2019}
}
@book{faucris.210051534,
author = {Wilke, Peter},
editor = {Institut für Mathematische Maschinen und Datenverarbeitung der Universität Erlangen-Nürnberg},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Programmierhandbuch} für {NeuroGraph} {Version} 3.0},
year = {1994}
}
@misc{faucris.123239204,
author = {Wilke, Peter and Schneider, Hans Jürgen and Völk, Andreas},
faupublication = {yes},
note = {UnivIS-Import:2016-06-23:Pub.1985.tech.IMMD.IMMD2.{\_}progr},
peerreviewed = {No},
title = {{Programmiersprachen} mit {Mengenkonzept} für unkonventionelle {Hardware}},
year = {1985}
}
@inproceedings{faucris.118785304,
author = {Lorch, Benedikt and Berger, Martin and Hornegger, Joachim and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2015},
faupublication = {yes},
note = {UnivIS-Import:2015-04-17:Pub.2015.tech.IMMD.IMMD5.projec},
pages = {59-64},
title = {{Projection} and {Reconstruction}-{Based} {Noise} {Filtering} {Methods} in {Cone} {Beam} {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Lorch15-PAR.pdf},
venue = {Lübeck},
year = {2015}
}
@inproceedings{faucris.111056704,
address = {Lübeck},
author = {Lu, Yanye and Manhart, Michael and Taubmann, Oliver and Zobel, Tobias and Yang, Qiao and Choi, Jang-Hwan and Wu, Meng and Dörfler, Arnd and Fahrig, Rebecca and Ren, Qiushi and Hornegger, Joachim and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2015},
date = {2015-03-15/2015-03-17},
doi = {10.1007/978-3-662-46224-9{\_}25},
faupublication = {yes},
isbn = {978-3-662-46223-2},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.projec{\_}7},
pages = {137-142},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Projection}-{Based} {Denoising} {Method} for {Photon}-{Counting} {Energy}-{Resolving} {Detectors}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Lu15-PDM.pdf},
venue = {Lübeck, Germany},
year = {2015}
}
@inproceedings{faucris.111133704,
author = {Lu, Yanye and Geret, Jan and Unberath, Mathias and Manhart, Michael and Ren, Qiushi and Fahrig, Rebecca and Hornegger, Joachim and Maier, Andreas},
booktitle = {The 13th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.projec{\_}5},
pages = {448-451},
peerreviewed = {unknown},
title = {{Projection}-based {Material} {Decomposition} by {Machine} {Learning} using {Image}-based {Features} for {Computed} {Tomography}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Lu15-PMD.pdf},
venue = {Newport, Rhode Island, USA},
year = {2015}
}
@inproceedings{faucris.222101248,
abstract = {The potential benefit of hybrid X-ray and MR imaging in the interventional environment is large due to the combination of fast imaging with high contrast variety. However, a vast amount of existing image enhancement methods requires the image information of both modalities to be present in the same domain. To unlock this potential, we present a solution to image-to-image translation from MR projections to corresponding x-ray projection images. The approach is based on a state-of-the-art image generator network that is modified to fit the specific application. Furthermore, we propose the inclusion of a gradient map in the loss function to allow the network to emphasize high-frequency details in image generation. Our approach is capable of creating x-ray projection images with natural appearance. Additionally, our extensions show clear improvement compared to the baseline method.},
author = {Stimpel, Bernhard and Syben-Leisner, Christopher and Würfl, Tobias and Breininger, Katharina and Lommen, Jonathan and Dörfler, Arnd and Maier, Andreas},
booktitle = {Progress in Biomedical Optics and Imaging - Proceedings of SPIE},
date = {2019-02-19/2019-02-21},
doi = {10.1117/12.2512195},
editor = {Bennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini},
faupublication = {yes},
isbn = {9781510625457},
note = {CRIS-Team Scopus Importer:2019-07-12},
peerreviewed = {unknown},
publisher = {SPIE},
title = {{Projection} image-to-image translation in hybrid x-ray/{MR} imaging},
venue = {San Diego, CA},
volume = {10949},
year = {2019}
}
@article{faucris.230599432,
abstract = {Hybrid X-ray and magnetic resonance (MR) imaging promises large potential in interventional medical imaging applications due to the broad variety of contrast of MRI combined with fast imaging of X-ray-based modalities. To fully utilize the potential of the vast amount of existing image enhancement techniques, the corresponding information from both modalities must be present in the same domain. For image-guided interventional procedures, X-ray fluoroscopy has proven to be the modality of choice. Synthesizing one modality from another in this case is an ill-posed problem due to ambiguous signal and overlapping structures in projective geometry. To take on these challenges, we present a learning-based solution to MR to X-ray projection-to-projection translation. We propose an image generator network that focuses on high representation capacity in higher resolution layers to allow for accurate synthesis of fine details in the projection images. Additionally, a weighting scheme in the loss computation that favors high-frequency structures is proposed to focus on the important details and contours in projection imaging. The proposed extensions prove valuable in generating X-ray projection images with natural appearance. Our approach achieves a deviation from the ground truth of only 6% and structural similarity measure of 0.913 ± 0.005. In particular the high frequency weighting assists in generating projection images with sharp appearance and reduces erroneously synthesized fine details.
consisting of more than 3.0 x 105 points with a computation time of less than 5 ms.
The third part of this work is concerned with patient-specific respiratory motion
models. The thesis proposes machine learning techniques to generate a continuous
motion model that features the ability to automatically differentiate between
thoracic and abdominal breathing as well as to quantitatively analyze the
patient’s respiration magnitude. By using purposely developed surface registration
schemes, these models are then brought in congruence with body surface data
acquired by range imaging sensors. This allows for respiratory motion compensated
patient positioning that reduces the alignment error observed with conventional
approaches by a factor of 3 to less than 4.0mm. Further, this approach allows
to automatically derive a multi-dimensional respiration surrogate that yields a correlation
coefficient greater than 0.97 compared to commonly employed invasive or
semi-automatic approaches and that can be computed in 20 ms.
The fourth part concludes this thesis with a summary of the presented methods
and results, as well as an outlook regarding future research directions and
challenges towards clinical translation.
The development of wearable sensors has opened the door for long-term assessment of movement disorders. However, there is still a need for developing methods suitable to monitor motor symptoms in and outside the clinic. The purpose of this paper was to investigate deep learning as a method for this monitoring. Deep learning recently broke records in speech and image classification, but it has not been fully investigated as a potential approach to analyze wearable sensor data.
We collected data from ten patients with idiopathic Parkinson’s disease using inertial measurement units. Several motor tasks were expert-labeled and used for classification. We specifically focused on the detection of bradykinesia. For this, we compared standard machine learning pipelines with deep learning based on convolutional neural networks. Our results showed that deep learning outperformed other state-of-the-art machine learning algorithms by at least 4.6 % in terms of classification rate. We contribute a discussion of the advantages and disadvantages of deep learning for sensor-based movement assessment and conclude that deep learning is a promising method for this field.
},
author = {Eskofier, Björn and Lee, Sunghoon I. and Daneault, Jean-Francois and Golabchi, Fatemeh N. and Ferreira-Carvalho, Gabriela and Vergara-Diaz, Gloria and Sapienza, Stefano and Costante, Gianluca and Klucken, Jochen and Kautz, Thomas and Bonato, Paolo},
booktitle = {Proceedings of the 38th IEEE Engineering in Medicine and Biology Society Conference (EMBC 2016)},
date = {2016-08-16/2016-08-20},
faupublication = {yes},
pages = {655-658},
peerreviewed = {unknown},
title = {{Recent} {Machine} {Learning} {Advancements} in {Sensor}-{Based} {Mobility} {Analysis}: {Deep} {Learning} for {Parkinson}’s {Disease} {Assessment}},
venue = {Orlando, USA},
year = {2016}
}
@article{faucris.108029724,
abstract = {
More than a decade has passed since research on automatic recognition of emotion from speech has become a new eld of research in line with its `big brothers' speech and speaker recognition. This article attempts to provide a short overview on where we are today, how we got there and what this can reveal us on where to go next and how we could arrive there. In a rst part, we address the basic phenomenon reflecting the last fteen years, commenting on databases, modelling and annotation, the unit of analysis and prototypicality. We then shift to automatic processing including discussions on features, classification, robustness, evaluation, and implementation and system integration. From there we go to the first comparative challenge on emotion recognition from speech - the INTERSPEECH 2009 Emotion Challenge, organised by (part of) the authors, including the description of the Challenge's database, Sub-Challenges, participants and their approaches, the winners, and the fusion of results to the actual learnt lessons before we finally address the ever-lasting problems and future promising attempts.
},
author = {Schuller, Björn and Batliner, Anton and Steidl, Stefan and Seppi, Dino},
doi = {10.1016/j.specom.2011.01.011},
faupublication = {yes},
journal = {Speech Communication},
keywords = {emotion; affect; automatic classification; feature types; feature selection; noise robustness; adaptation; standardisation; usability; evaluation},
pages = {1062-1087},
peerreviewed = {Yes},
title = {{Recognising} realistic emotions and affect in speech: {State} of the art and lessons learnt from the first challenge},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Schuller11-RRE.pdf},
volume = {53},
year = {2011}
}
@inproceedings{faucris.115625224,
abstract = {The paper describes prosodic annotation procedures of the GOPOLIS Slovenian speech data database and methods for automatic classification of different prosodic events. Several statistical parameters concerning duration and loudness of words, syllables and allophones were computed for the Slovenian language, for the first time on such a large amount of speech data. The evaluation of the annotated data showed a close match between automatically determined syntactic-prosodic boundary marker positions and those obtained by a rule-based approach.},
author = {Mihelic, France and Gros, Jerneia and Nöth, Elmar and Warnke, Volker},
faupublication = {yes},
month = {Jan},
pages = {165-170},
peerreviewed = {unknown},
publisher = {Springer-verlag},
title = {{Recognition} and labelling of prosodic events in {Slovenian} speech},
volume = {1902},
year = {2000}
}
@article{faucris.121308044,
abstract = {We present a comprehensive study on the effect of reverberation and background noise on the recognition of nonprototypical emotions from speech. We carry out our evaluation on a single, well-defined task based on the FAU Aibo Emotion Corpus consisting of spontaneous children's speech, which was used in the INTERSPEECH 2009 Emotion Challenge, the first of its kind. Based on the challenge task, and relying on well-proven methodologies from the speech recognition domain, we derive test scenarios with realistic noise and reverberation conditions, including matched as well as mismatched condition training. As feature extraction based on supervised Nonnegative Matrix Factorization (NMF) has been proposed in automatic speech recognition for enhanced robustness, we introduce and evaluate different kinds of NMF-based features for emotion recognition. We conclude that NMF features can significantly contribute to the robustness of state-of-the-art emotion recognition engines in practical application scenarios where different noise and reverberation conditions have to be faced.},
author = {Weninger, Felix and Schuller, Björn and Batliner, Anton and Steidl, Stefan and Seppi, Dino},
doi = {10.1155/2011/838790},
faupublication = {yes},
journal = {EURASIP Journal on Advances in Signal Processing},
pages = {1-16},
peerreviewed = {Yes},
title = {{Recognition} of {Non}-{Prototypical} {Emotions} in {Reverberated} and {Noisy} {Speech} by {Non}-{Negative} {Matrix} {Factorization}},
url = {http://downloads.hindawi.com/journals/asp/2011/838790.pdf},
volume = {2011},
year = {2011}
}
@inproceedings{faucris.120180764,
abstract = {In X-ray imaging, a reduction of the field of view (FOV) is proportional to a reduction in radiation dose. The resulting truncation, however, is incompatible with conventional tomographic reconstruction algorithms. This problem has been studied extensively. Very recently, a novel method for region of interest (ROI) reconstruction from truncated projections with neither the use of prior knowledge nor explicit extrapolation has been published, named Approximated Truncation Robust Algorithm for Computed Tomography (ATRACT). It is based on a decomposition of the standard ramp filter into a 2D Laplace filtering (local operation) and a 2D Radon-based filtering step (non-local operation). The 2D Radon-based filtering that involves many interpolations complicates the filtering procedure in ATRACT, which essentially limits its practicality. In this paper, an optimization for this shortcoming is presented. That is to apply ATRACT in one dimension, which implies that we decompose the standard ramp filter into the 1D Laplace filter and a 1D convolutionbased filter. The convolution kernel was determined numerically by computing the 1D impulse response of the standard ramp filtering coupled with the second order anti-derivative operation. The proposed algorithm was evaluated by using a reconstruction benchmark test, a real phantom and a clinical data set in terms of spatial resolution, computational efficiency as well as robustness of correction quality. The evaluation outcomes were encouraging. The proposed algorithm showed improvement in computational performance with respect to the 2D ATRACT algorithm and furthermore maintained reconstructions of high accuracy in presence of data truncation. © 2013 SPIE.},
author = {Xia, Yan and Maier, Andreas and Hofmann, Hannes and Dennerlein, Frank and Müller, Kerstin and Hornegger, Joachim},
booktitle = {Medical Imaging 2013: Physics of Medical Imaging},
doi = {10.1117/12.2007484},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Reconstruction} from truncated projections in cone-beam {CT} using an efficient {1D} filtering},
venue = {Lake Buena Vista, FL},
volume = {8668},
year = {2013}
}
@inproceedings{faucris.107904544,
author = {Hoffmann, Matthias and Brost, Alexander and Jakob, Carolin and Koch, Martin and Bourier, Felix and Kurzidim, Klaus and Hornegger, Joachim and Strobel, Norbert},
booktitle = {Proc. SPIE 8671, Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling},
date = {2013-02-09},
doi = {10.1117/12.2006346},
editor = {David R. Holmes, Ziv R. Yaniv},
faupublication = {yes},
pages = {86712F-86712F-8},
title = {{Reconstruction} method for curvilinear structures from two views},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Hoffmann13-RMF.pdf},
venue = {Lake Buena Vista (Orlando Area), Florida, USA},
year = {2013}
}
@article{faucris.121086284,
abstract = {Grating-based X-ray dark-field imaging is a novel technique for obtaining image contrast for object structures at size scales below setup resolution. Such an approach appears particularly beneficial for medical imaging and nondestructive testing. It has already been shown that the dark-field signal depends on the direction of observation. However, up to now, algorithms for fully recovering the orientation dependence in a tomographic volume are still unexplored. In this publication, we propose a reconstruction method for grating-based X-ray dark-field tomography, which models the orientation- dependent signal as an additional observable from a standard tomographic scan. In detail, we extend the tomographic volume to a tensorial set of voxel data, containing the local orientation and contributions to dark-field scattering. In our experiments, we present the first results of several test specimens exhibiting a heterogeneous composition in microstructure, which demonstrates the diagnostic potential of the metho},
author = {Bayer, Florian and Hu, Shiyang and Maier, Andreas and Weber, Thomas and Anton, Gisela and Michel, Thilo and Riess, Christian},
doi = {10.1073/pnas.1321080111},
faupublication = {yes},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
keywords = {Anisotropic scattering; Grating interferometer; Microstructure orientation; X-ray phase contrast},
note = {UnivIS-Import:2015-04-14:Pub.2014.nat.dphy.PI.LEPDF.recons},
pages = {12699-12704},
peerreviewed = {Yes},
title = {{Reconstruction} of scalar and vectorial components in {X}-ray dark-field tomography},
volume = {111},
year = {2014}
}
@inproceedings{faucris.244440459,
author = {Felsner, Lina and Würfl, Tobias and Syben-Leisner, Christopher and Roser, Philipp and Preuhs, Alexander and Maier, Andreas and Riess, Christian},
booktitle = {The 6th International Conference on Image Formation in X-Ray Computed Tomography},
date = {2020-08-03/2020-08-07},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Reconstruction} of {Voxels} with {Position}- and {Angle}-{Dependent} {Weightings}},
venue = {Online meeting},
year = {2020}
}
@phdthesis{faucris.114856984,
abstract = {Today, magnetic resonance imaging (MRI) is an essential clinical imaging modality and routinely used for orthopedic, neurological, cardiovascular, and oncological diagnosis.
The relatively long scan times lead to two limitations in oncological MRI.
Firstly, in dynamic contrast-enhanced MRI (DCE-MRI), spatial and temporal resolution have to be traded off against each other.
Secondly, conventional acquisition techniques are highly susceptible to motion artifacts. As an example, in DCE-MRI of the liver, the imaging volume spans the whole abdomen and the scan must take place within a breath-hold to avoid respiratory motion. Dynamic imaging is achieved by performing multiple breath-hold scans before and after the injection of contrast agent. In practice, this requires patient cooperation, exact timing of the contrast agent injection, and limits the temporal resolution to about 10 seconds.
This thesis addresses both challenges by combining a radial k-space sampling technique with advanced reconstruction algorithms for higher temporal resolution and improved respiratory motion management.
A novel reconstruction technique, golden-angle radial sparse parallel MRI (GRASP),
enables performing DCE-MRI at simultaneously high spatial and temporal resolution.
Iterative gradient-based and alternating optimization techniques were implemented and evaluated.
GRASP is based on a single, continuous scan during free breathing, allowing for a simplified and more patient-friendly examination workflow.
The technique is augmented by an automatic detection of the contrast agent bolus arrival and by incorporating variable temporal resolution.
These proposed extensions reduce the number of generated image volumes, resulting in faster reconstruction and post-processing.
The radial trajectory also allows to extract a respiratory signal directly from the scan data. This self-gating property can be used for dynamic imaging in such a way that different, time-averaged phases of respiration are retrospectively reconstructed from a free-breathing scan. Automated algorithms for deriving, processing, and applying the self-gating signal were developed.
The clinical relevance of self-gating was demonstrated by generating a motion model to correct for respiratory motion in a simultaneous positron emission tomography (PET) examination on hybrid PET/MRI scanners. This approach reduces the motion blur and, thus, improves tracer uptake quantification in moving lesions, while avoiding an increased noise level as it would be the case for conventional gating techniques.
In conclusion, the presented advanced reconstruction techniques help to improve the spatio-temporal resolution as well as the robustness with respect to motion of dynamic radial MRI. The effectiveness of the proposed methods was supported by numerous studies in patient settings, showing that non-Cartesian k-space sampling can be advantageous in a variety of applications.
},
author = {Kuhnert, Nadine and Barth, Karl and Maass, Nicole and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin},
faupublication = {yes},
keywords = {Segmentation Result; Metal Artifact; Metal Object; Segmentation Approach; Initial Segmentation},
peerreviewed = {unknown},
title = {{Reduction} of {Metal} {Artifacts} using a {New} {Segmentation} {Approach}},
year = {2016}
}
@inproceedings{faucris.276489296,
abstract = {Metal artifact reduction (MAR) is crucial for the diagnostic value, as metal artifacts tremendously impair the image quality of a CT scan. Existing techniques are time-consuming. Most MAR methods contain a metal object segmentation step and the resulting image quality highly depends on the validity of the segmentation. However, segmenting the metal parts correctly still poses a non-trivial problem. We present a novel approach of an automatic, object independent segmentation which starts with the state-of-the-art segmentation. This is improved by applying graph cut onto every projection. We extend the graph cut idea by more information and apply knowledge about the distance, a classification probability and a bias to the edges as well as a similarity measure of pixels to their direct neighbors. By additionally considering global consistency, we receive a more precise segmentation result. For the evaluation, our new segmentation approach was combined with the frequency split MAR (FSMAR). The resulting CT images yielded higher image quality compared with the standard threshold-based FSMAR.},
author = {Kuhnert, Nadine and Maass, Nicole and Barth, Karl and Maier, Andreas},
booktitle = {Informatik aktuell},
date = {2016-03-13/2016-03-15},
doi = {10.1007/978-3-662-49465-3{\_}18},
editor = {Thomas M. Deserno, Heinz Handels, Thomas Tolxdorff, Hans-Peter Meinzer},
faupublication = {yes},
isbn = {9783662494646},
note = {CRIS-Team Scopus Importer:2022-06-05},
pages = {92-97},
peerreviewed = {unknown},
publisher = {Kluwer Academic Publishers},
title = {{Reduction} of metal artifacts using a new segmentation approach: {Extension} of graph cuts for a more precise segmentation used in metal artifact reduction},
venue = {Berlin, DEU},
year = {2017}
}
@article{faucris.117703124,
abstract = {Purpose: To combine weighted iterative reconstruction with self-navigated free-breathing coronary magnetic resonance angiography for retrospective reduction of respiratory motion artifacts. Methods: One-dimensional self-navigation was improved for robust respiratory motion detection and the consistency of the acquired data was estimated on the detected motion. Based on the data consistency, the data fidelity term of iterative reconstruction was weighted to reduce the effects of respiratory motion. In vivo experiments were performed in 14 healthy volunteers and the resulting image quality of the proposed method was compared to a navigator-gated reference in terms of acquisition time, vessel length, and sharpness. Result: Although the sampling pattern of the proposed method contained 60% more samples with respect to the reference, the scan efficiency was improved from 39.5±10.1% to 55.1±9.1%. The improved self-navigation showed a high correlation to the standard navigator signal and the described weighting efficiently reduced respiratory motion artifacts. Overall, the average image quality of the proposed method was comparable to the navigator-gated reference. Conclusion: Self-navigated coronary magnetic resonance angiography was successfully combined with weighted iterative reconstruction to reduce the total acquisition time and efficiently suppress respiratory motion artifacts. The simplicity of the experimental setup and the promising image quality are encouraging toward future clinical evaluation. © 2014 Wiley Periodicals, Inc.},
author = {Forman, Christoph and Piccini, Davide and Grimm, Robert and Hutter, Jana and Hornegger, Joachim and Zenge, Michael O.},
doi = {10.1002/mrm.25321},
faupublication = {yes},
journal = {Magnetic Resonance in Medicine},
keywords = {Compressed sensing; Coronary magnetic resonance angiography; Motion suppression; Weighted iterative reconstruction},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.reduct},
pages = {1-11},
peerreviewed = {Yes},
title = {{Reduction} of {Respiratory} {Motion} {Artifacts} for {Free}-{Breathing} {Whole}-{Heart} {Coronary} {MRA} by {Weighted} {Iterative} {Reconstruction}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Forman14-ROR.pdf},
volume = {0},
year = {2014}
}
@article{faucris.234501596,
abstract = {Zusammenfassung
Metallartefakte
stellen eine große Herausforderung für das Messen mit
Röntgen-Computertomographie dar. Dieser Beitrag stellt die Methode der
multipositionalen Datenfusion zur Reduktion von Metallartefakten vor.
Dazu werden mehrere Scans desselben Objekts bei unterschiedlicher
Objekt-positionierung durchgeführt, aufeinander registriert und zur
Fusion gemeinsam unter Betrachtung eines lokalen Gütemaßes
rekonstruiert. In praxisnahen Experimenten wird der Mehrwert der Methode
gezeigt. Insbesondere wird dargestellt, wie mit wenig Aufwand und ohne
Vorwissen Kunststoffstrukturen trotz starker Metallartefakte sichtbar
gemacht werden können, womit das Verfahren ein Alleinstellungsmerkmal
gegenüber den existierenden Metallartefaktreduktionsverfahren aufweist.
Abstract
Metal
artifacts represent a major challenge for measuring with X-ray computed
tomography. This paper presents a method for multipositional data
fusion for the reduction of metal artifacts. For this purpose, several
scans of the same object are performed with different object
positioning, registered on each other and then reconstructed together
using a local quality measure. The added value of the method is
demonstrated in practical experiments. In particular, it is shown how
plastic structures can be made visible despite strong metal artifacts
with little effort and without prior knowledge, giving the method a
unique selling point compared to existing metal artefact reduction
methods.
},
author = {Herl, Gabriel and Hiller, Jochen and Kasperl, Stefan and Maier, Andreas},
doi = {10.1515/teme-2019-0137.},
faupublication = {yes},
journal = {Technisches Messen},
keywords = {X-ray computed tomography; CT; metal artifact reduction; multipositional data fusion},
pages = {101–110},
peerreviewed = {Yes},
title = {{Reduktion} von {Metallartefakten} durch multipositionale {Datenfusion} in der industriellen {Röntgen}-{Computertomographie}},
url = {https://www.degruyter.com/view/j/teme.2020.87.issue-2/teme-2019-0137/teme-2019-0137.xml},
volume = {87},
year = {2019}
}
@inproceedings{faucris.106940944,
author = {Aichert, André and Maass, Nicole and Deuerling-Zheng, Yu and Berger, Martin and Manhart, Michael and Hornegger, Joachim and Maier, Andreas and Dörfler, Arnd},
booktitle = {Proceedings of the third international conference on image formation in x-ray computed tomography},
faupublication = {yes},
keywords = {GRK-1773},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.redund{\_}1},
pages = {333-337},
title = {{Redundancies} in {X}-ray images due to the epipolar geometry for transmission imaging},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Aichert14-RIX.pdf},
venue = {Salt Lake City, UT, USA},
year = {2014}
}
@inproceedings{faucris.203365631,
author = {Riess, Christian and Pfaller, Sven and Angelopoulou, Elli},
booktitle = {New Trends in Image Analysis and Processing - ICIAP 2015 Workshops - ICIAP 2015 International Workshops: BioFor, CTMR, RHEUMA, ISCA, MADiMa, SBMI, and QoEM},
date = {2015-09-07/2015-09-08},
doi = {10.1007/978-3-319-23222-5{\_}1},
faupublication = {yes},
pages = {3--10},
peerreviewed = {Yes},
title = {{Reflectance} {Normalization} in {Illumination}-{Based} {Image} {Manipulation} {Detection}},
venue = {Genoa},
year = {2015}
}
@phdthesis{faucris.114858304,
abstract = {C-arm based flat-detector computed tomography (FDCT) is a promising approach for neurovascular diagnosis and intervention since it facilitates proper analysis of surgical implants and intra-procedural guidance. In the majority of endovascular treatments, intra-procedural updates of the imaged object often are restricted to a small diagnostic region of interest (ROI). Such targeted ROI is often the region of intervention that contains device/vessel specific information such as stent expansion or arterial wall apposition. Following the principle of as low as reasonably achievable (ALARA), it is highly desirable to reduce unnecessary peripheral doses outside an ROI by using physical X-ray collimation, leading to substantial reduction of patient dose. However, such a technique gives rise to severely truncated projections from which conventional reconstruction algorithms generally yield images with strong truncation artifacts.
The primary research goal of this thesis, therefore, lies on the algorithmic development of various truncation artifact reduction techniques that are dedicated for different imaging scenarios. First, a new data completion method is proposed that utilizes sinogram consistency conditions to estimate the missing sinogram. Although it is only extended to a 2D fan-beam geometry, preliminary results suggest the method is promising regarding truncation artifact reduction and attenuation coefficient recovery. Thereafter, three algorithms are presented, which either follow the analytic filtered backprojection (FBP) frame or are by construction in an iterative manner. They are capable of generating a 3D image from transaxially truncated data and thus appear to be closer to clinical applications. The first approach is the refinement of an existing truncation robust algorithm – ATRACT, which is implicitly effective with respect to severely truncated data. In this thesis, ATRACT is modified to more practically-useful reconstruction methods by expressing its expensive non-local filter as an efficient 1D/2D analytic convolution. The second approach is targeted to particular imaging applications that require an ROI with high image quality for diagnosis, and also a surrounding region with the relatively low resolution for orientation. To accomplish this task, an interleaved acquisition strategy that acquires both a sparse set of global non-truncated data and a dense set of truncated data is presented, along with three associated algorithms. The third approach is an attempt to exploit low-dose patient-specific prior knowledge for the extrapolation of truncated projections. The comparative evaluation clearly depicts the algorithmic performance of all investigated 3D methods under a uniform evaluation framework. In general, ATRACT appears to be more robust than the explicit water cylinder extrapolation in severe truncation case. Contrary to the heuristic methods, the techniques that come with either a sparse set of global data or prior knowledge achieve the ROI reconstructions in a more accurate and robust manner. The decision on which method should be selected relies on multiple factors, but the presented results could be used as the first indicator for the ease of such selection.
Purpose
Morphological changes to
anatomy resulting from invasive surgical procedures or pathology,
typically alter the surrounding vasculature. This makes it useful as a
descriptor for feature-driven image registration in various clinical
applications. However, registration of vasculature remains challenging,
as vessels often differ in size and shape, and may even miss branches,
due to surgical interventions or pathological changes. Furthermore,
existing vessel registration methods are typically designed for a
specific application. To address this limitation, we propose a generic
vessel registration approach useful for a variety of clinical
applications, involving different anatomical regions.
Methods
A
probabilistic registration framework based on a hybrid mixture model,
with a refinement mechanism to identify missing branches (denoted as
HdMM+) during vasculature matching, is introduced. Vascular structures
are represented as 6-dimensional hybrid point sets comprising spatial
positions and centerline orientations, using Student’s t-distributions to model the former and Watson distributions for the latter.
Results
The proposed framework is
evaluated for intraoperative brain shift compensation, and monitoring
changes in pulmonary vasculature resulting from chronic lung disease.
Registration accuracy is validated using both synthetic and patient
data. Our results demonstrate, HdMM+ is able to reduce more than 85%" role="presentation">85%
of the initial error for both applications, and outperforms the
state-of-the-art point-based registration methods such as coherent point
drift and Student’s t-distribution mixture model, in terms of mean surface distance, modified Hausdorff distance, Dice and Jaccard scores.
Conclusion
The proposed registration
framework models complex vascular structures using a hybrid
representation of vessel centerlines, and accommodates intricate
variations in vascular morphology. Furthermore, it is generic and
flexible in its design, enabling its use in a variety of clinical
applications.
},
author = {Bayer, Siming and Zhai, Zhiwei and Strumia, Maddalena and Tong, Xiaoguang and Gao, Ying and Staring, Marius and Stoel, Berend and Fahrig, Rebecca and Arya, Nabavi and Maier, Andreas and Ravikumar, Nishant},
doi = {10.1007/s11548-019-02007},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Non-rigid registration; Point matching; Brain shift; Pulmonary vascular diseases},
pages = {1–10},
peerreviewed = {Yes},
title = {{Registration} of vascular structures using a hybrid mixture model},
url = {https://link.springer.com/article/10.1007/s11548-019-02007-y},
year = {2019}
}
@inproceedings{faucris.118751644,
abstract = {The detection of organs from full-body PET images is a challenging task due to the high noise and the limited amount of anatomical information of PET imaging. The knowledge of organ locations can support many clinical applications like image registration or tumor detection. This paper is the first to propose an organ localization framework tailored on the challenges of PET. The algorithm involves intensity normalization, feature extraction and regression forests. Linear and nonlinear intensity normalization methods are compared theoretically and experimentally. From the normalized images, long-range spatial context visual features are extracted. A regression forest predicts the organ bounding boxes. Experiments show that percentile normalization is the best preprocessing method. The algorithm is evaluated on 25 clinical images with a spatial resolution of 5 mm. With 13.8mm mean absolute bounding box error, it achieves state-of-the-art results.},
address = {Berlin Heidelberg},
author = {Fischer, Peter and Daum, Volker and Hahn, Dieter and Prümmer, Marcus and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2014},
date = {2014-03-16/2014-03-18},
doi = {10.1007/978-3-642-54111-7{\_}70},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.regres{\_}5},
pages = {384-389},
publisher = {Springer},
series = {Informatik aktuell},
title = {{Regression} {Forest}-{Based} {Organ} {Detection} in {Normalized} {PET} {Images}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Fischer14-RFO.pdf},
venue = {Aachen},
year = {2014}
}
@inproceedings{faucris.121388344,
abstract = {
We report on a thoroughly processed and annotated German emotional speech database (children interacting with Sony’s Aibo robot): 51 children, some 48 k words, 9.2 hours of speech, 5 labellers, word-based annotation of emotional user states. Several additional annotations as well as a mapping onto higher units of different granularity have been carried out. The database will eventually be made available for scientific use; in the licensing agreement, we plan to include mandatory benchmark constellations in order to make a comparison across sites possible.
},
address = {Marrakesh},
author = {Batliner, Anton and Steidl, Stefan and Nöth, Elmar},
booktitle = {Proc. of a Satellite Workshop of LREC 2008 on Corpora for Research on Emotion and Affect},
date = {2008-05-26},
editor = {Devillers Laurence, Martin Jean-Claude, Cowie Roddy, Douglas-Cowie Ellen, Batliner Anton},
faupublication = {yes},
pages = {28-31},
peerreviewed = {Yes},
publisher = {LREC},
title = {{Releasing} a thoroughly annotated and processed spontaneous emotional database: the {FAU} {Aibo} {Emotion} {Corpus}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Batliner08-RAT.pdf},
venue = {Marrakesh},
year = {2008}
}
@inproceedings{faucris.121796224,
abstract = {Natural input dialog systems for entering address data in modern GPS units demand a significantly more robust extraction of slot information. In previous work, prosody was used to detect phrase boundaries (PB) which separate particular address parts. Only input without filler words was used. In this work, carrier sentences are allowed. A boosting approach provides twenty strong prosodic features which model the characteristic of PBs. We introduce the concept of a prosodically marked word boundary (PMB), which enables a better location of the provided information in natural input. Our results on a dataset of 5883 input samples reveal that about 67% of the found PBs indicate a PMB, while most of the remaining boundaries occur within compound words.},
author = {Kaufhold, Caroline and Stemmer, Georg and Nöth, Elmar},
faupublication = {yes},
keywords = {prosody;phrase boundary detection;multi-slot input modality},
month = {Jan},
pages = {259-267},
peerreviewed = {unknown},
publisher = {Springer-verlag},
title = {{Reliable} {Detection} of {Important} {Word} {Boundaries} {Using} {Prosodic} {Features}},
volume = {6836},
year = {2011}
}
@inproceedings{faucris.110345224,
abstract = {In this paper, we propose a novel methodology for the computation of reliable confidence intervals and significance tests for measures of linguistic complexity, inspired by ideas from bootstrapping and cross-validation. As an illustration, we apply the new method to the detection of early symptoms of Alzheimer's disease in the novels of Iris Murdoch, showing that most of the differences observed in previous work are not signficant and can indeed be accounted for by sampling variation.},
address = {Birmingham, UK},
author = {Evert, Stephanie and Wankerl, Sebastian and Nöth, Elmar},
booktitle = {Proceedings of the Corpus Linguistics 2017 Conference},
faupublication = {yes},
keywords = {LNRE, lexical statistics},
peerreviewed = {unknown},
title = {{Reliable} measures of syntactic and lexical complexity: {The} case of {Iris} {Murdoch}},
url = {http://purl.org/stefan.evert/PUB/EvertWankerlNoeth2017.pdf},
venue = {Birmingham},
year = {2017}
}
@inproceedings{faucris.203725975,
author = {Schneider, Manuel and Lugauer, Felix and Janas, Gemini and Nickel, Dominik and Dale, Brian M. and Kiefer, Berthold and Maier, Andreas and Bashir, Mustafa R.},
booktitle = {Proceedings of the Joint Annual Meeting ISMRM-ESMRMB},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.repeat},
pages = {536},
peerreviewed = {unknown},
title = {{Repeatability} and {Reproducibility} of a {New} {Method} for {Quantifying} {Triglyceride} {Saturation} {Using} {Bipolar} {Multi}-{Echo} {MRI}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Schneider18-RAR.pdf},
venue = {Paris, France},
year = {2018}
}
@inproceedings{faucris.120327064,
address = {-},
author = {Hornegger, Joachim and Tomasi, Carlo},
booktitle = {Proceedings of the 7th International Conference on Computer Vision (ICCV)},
date = {1999-09-20/1999-09-25},
editor = {IEEE},
faupublication = {no},
pages = {914-919},
peerreviewed = {unknown},
publisher = {IEEE Computer Society Press},
title = {{Representation} {Issues} in the {ML} {Estimation} of {Camera} {Motion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Hornegger99-RII.pdf},
venue = {Corfu},
year = {1999}
}
@inproceedings{faucris.108110464,
author = {Bernecker, David and Riess, Christian and Christlein, Vincent and Angelopoulou, Elli and Hornegger, Joachim},
booktitle = {Pattern Recognition},
date = {2013-09-06},
doi = {10.1007/978-3-642-40602-7{\_}42},
editor = {Weickert Joachim, Hein Matthias, Schiele Bernt},
faupublication = {yes},
pages = {395-404},
peerreviewed = {Yes},
title = {{Representation} {Learning} for {Cloud} {Classification}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Bernecker13-RLF.pdf},
venue = {Saarbrücken},
year = {2013}
}
@incollection{faucris.241909456,
abstract = {Automatic writer identification is a common problem in document analysis. State-of-the-art methods typically focus on the feature extraction step with traditional or deep-learning-based techniques. In retrieval problems, re-ranking is a commonly used technique to improve the results. Re-ranking refines an initial ranking result by using the knowledge contained in the ranked result, e. g., by exploiting nearest neighbor relations. To the best of our knowledge, re-ranking has not been used for writer identification/retrieval. A possible reason might be that publicly available benchmark datasets contain only few samples per writer which makes a re-ranking less promising. We show that a re-ranking step based on k-reciprocal nearest neighbor relationships is advantageous for writer identification, even if only a few samples per writer are available. We use these reciprocal relationships in two ways: encode them into new vectors, as originally proposed, or integrate them in terms of query-expansion. We show that both techniques outperform the baseline results in terms of mAP on three writer identification datasets.
},
author = {Gündel, Sebastian and Setio, Arnaud A.A. and Ghesu, Florin-Cristian and Grbic, Sasa and Georgescu, Bogdan and Maier, Andreas and Comaniciu, Dorin},
doi = {10.1016/j.media.2021.102087},
faupublication = {yes},
journal = {Medical Image Analysis},
keywords = {label noise; robust loss function; multi-task learning; chest radiography abnormality classification},
peerreviewed = {Yes},
title = {{Robust} {Classification} from {Noisy} {Labels}: {Integrating} {Additional} {Knowledge} for {Chest} {Radiography} {Abnormality} {Assessment}},
year = {2021}
}
@inproceedings{faucris.121954844,
author = {Haderlein, Tino and Hönig, Florian Thomas and Jassens, Frank and Mahlberg, Lea and Nöth, Elmar and Wolff von Gudenberg, Alexander},
booktitle = {Aktuelle phoniatrisch-pädaudiologische Aspekte 2015},
doi = {10.3205/15dgpp29},
faupublication = {yes},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.robust{\_}91},
pages = {70-72},
title = {{Robustes} {Echtzeit}-{Feedback} für die gebundene, weiche {Sprechtechnik} in der {Stottertherapie}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Haderlein15-REF.pdf},
venue = {Oldenburg (Oldenburg)},
year = {2015}
}
@article{faucris.121143484,
abstract = {We present a fabrication process for freely suspended membranes consisting of bi- and trilayer graphene grown on silicon carbide. The procedure, involving photoelectrochemical etching, enables the simultaneous fabrication of hundreds of arbitrarily shaped membranes with an area up to 500 μm(2) and a yield of around 90%. Micro-Raman and atomic force microscopy measurements confirm that the graphene layer withstands the electrochemical etching and show that the membranes are virtually unstrained. The process delivers membranes with a cleanliness suited for high-resolution transmission electron microscopy (HRTEM) at atomic scale. The membrane, and its frame, is very robust with respect to thermal cycling above 1000 °C as well as harsh acidic or alkaline treatment.},
author = {Waldmann, Daniel and Butz, Benjamin and Bauer, Sebastian and Englert, Jan and Jobst, Johannes and Ullmann, Konrad and Fromm, Felix and Ammon, Maximilian Michael and Enzelberger-Heim, Michael and Hirsch, Andreas and Maier, Sabine and Schmuki, Patrik and Seyller, Thomas and Spiecker, Erdmann and Weber, Heiko B. and Spiecker, Erdmann},
doi = {10.1021/nn401037c},
faupublication = {yes},
journal = {ACS nano},
pages = {4441-4448},
peerreviewed = {unknown},
title = {{Robust} graphene membranes in a silicon carbide frame},
volume = {7},
year = {2013}
}
@inproceedings{faucris.313471878,
abstract = {Standardized image rotation is essential to improve reading performance in interventional X-ray imaging. To minimize user interaction and streamline the 2D imaging workflow, we present a new automated image rotation method. Image rotation can follow two steps: First, an anatomy specific centerline image is predicted which depicts the desired anatomical axis to be aligned vertically after rotation. In a second step, the necessary rotation angle is calculated from the orientation of the predicted line image. We propose an end-to-end trainable model with the Hough transform (HT) and a differentiable spatial-to-angular transform (DSAT) embedded as known operators. This model allows to robustly regress a rotation angle while maintaining an explainable inner structure and allows to be trained with both a centerline segmentation and angle regression loss. The proposed method is compared to a Hu moments-based method on anterior-posterior X-ray images of spine, knee, and wrist. For the wrist images, the HT based method reduces the mean absolute angular error (MAE) from 9. 28 ∘ using the Hu moments-based method to 3. 54 ∘. Similar results for the spinal and knee images can be reported. Furthermore, a large improvement of the 90 th percentile of absolute angular error by a factor of 3 indicates a better robustness and reduction of outliers for the proposed method.},
author = {Bachmaier, Magdalena and Rohleder, Maximilian and Swartman, Benedict and Privalov, Maxim and Maier, Andreas and Kunze, Holger},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2023-10-08/2023-10-12},
doi = {10.1007/978-3-031-43990-2{\_}42},
editor = {Hayit Greenspan, Hayit Greenspan, Anant Madabhushi, Parvin Mousavi, Septimiu Salcudean, James Duncan, Tanveer Syeda-Mahmood, Russell Taylor},
faupublication = {yes},
isbn = {9783031439896},
keywords = {Hough Transform; Image Rotation; Machine Learning},
note = {CRIS-Team Scopus Importer:2023-11-03},
pages = {446-455},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Robust} {Hough} and {Spatial}-{To}-{Angular} {Transform} {Based} {Rotation} {Estimation} for {Orthopedic} {X}-{Ray} {Images}},
venue = {Vancouver, BC, CAN},
volume = {14226 LNCS},
year = {2023}
}
@inproceedings{faucris.118785524,
address = {Berlin Heidelberg},
author = {Hoffmann, Matthias and Müller, Simone and Kurzidim, Klaus and Strobel, Norbert and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2015},
doi = {10.1007/978-3-662-46224-9{\_}6},
faupublication = {yes},
isbn = {978-3-662-46223-2},
note = {UnivIS-Import:2015-04-17:Pub.2015.tech.IMMD.IMMD5.robust{\_}3},
pages = {23-28},
publisher = {Springer},
series = {Informatik aktuell},
title = {{Robust} {Identification} of {Contrasted} {Frames} in {Fluoroscopic} {Images}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Hoffmann15-RIO.pdf},
venue = {Lüubeck},
year = {2015}
}
@inproceedings{faucris.119899164,
abstract = {Clinical applications of computational cardiac models require precise personalization, i.e. fitting model parameters to capture patient's physiology. However, due to parameter non-identifiability, limited data, uncertainty in the clinical measurements, and modeling assumptions, various combinations of parameter values may exist that yield the same quality of fit. Hence, there is a need for quantifying the uncertainty in estimated parameters and to ascertain the uniqueness of the found solution. This paper presents a stochastic method to estimate the parameters of an image-based electromechanical model of the heart and their uncertainty due to noise in measurements. First, Bayesian inference is applied to fully estimate the posterior probability density function (PDF) of the model. To that end, Markov Chain Monte Carlo sampling is used, which is made computationally tractable by employing a fast surrogate model based on Polynomial Chaos Expansion, instead of the true forward model. Then, we use the mean-shift algorithm to automatically find the modes of the PDF and select the most likely one while being robust to noise. The approach is used to estimate global active stress and passive stiffness from invasive pressure and image-based volume quantification. Experiments on eight patients showed that not only our approach yielded goodness of fits equivalent to a well-established deterministic method, but we could also demonstrate the non-uniqueness of the problem and report uncertainty estimates, crucial information for subsequent clinical assessments of the personalized models.},
address = {Boston, USA},
author = {Neumann, Dominik and Tommaso, Mansi and Georgescu, Bogdan and Kamen, Ali and Kayvanpour, Elham and Amr, Ali and Sedaghat-Hamedani, Farbod and Haas, Jan and Katus, Hugo and Meder, Benjamin and Hornegger, Joachim and Comaniciu, Dorin},
booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2014},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.robust{\_}8},
pages = {9-16},
publisher = {Springer},
title = {{Robust} {Image}-{Based} {Estimation} of {Cardiac} {Tissue} {Parameters} and {Their} {Uncertainty} from {Noisy} {Data}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Neumann14-RIE.pdf},
venue = {Cambridge, MA},
year = {2014}
}
@inproceedings{faucris.120184504,
abstract = {Diagnosis and treatment of coronary diseases depends on the data acquired during angiographic investigations. To provide better assistance for angiographic procedures, a segmentation of the lumen is required. A new algorithm for vessel centerline computation and lumen segmentation in 2D projection coronary angiograms is presented. Centerlines are extracted by a graph-based optimization technique, which searches for paths with minimal costs. The search starts from a source point, which is automatically set by the proposed algorithm. A new objective function for determining the costs of the graph edges is proposed. It consists of the response from the medialness filter and is regularized by the centerline potential function. In the medialness filter a vessel cross-section is represented by a 1D profile parameterized by center position and radius. The medialness filter at a point optimizes a gradient-based response over the profile radius. The proposed centerline potential function defines likeliness of each point of the image to be a centerline. Both the medialness filter and the centerline potential function are multi-scale. The entire lumen segmentation is achieved by the radii extracted during the medialness response computation. Application to clinical data shows that the presented algorithm segments coronary lumen with good accuracy and allows for subsequent assessment of the quantitative characteristics (i.e. diameter, curvature, etc.) of the vessels. © 2012 SPIE.},
author = {Polyanskaya, Maria and Schwemmer, Chris and Linarth, Andre Guilherme and Lauritsch, Günter and Hornegger, Joachim},
booktitle = {Medical Imaging 2012: Image Processing},
doi = {10.1117/12.911130},
faupublication = {yes},
pages = {-},
peerreviewed = {Yes},
title = {{Robust} lumen segmentation of coronary arteries in {2D} angiographic images},
venue = {San Diego, CA},
volume = {8314},
year = {2012}
}
@article{faucris.216831967,
abstract = {When a measurement falls outside the quantization or measurable range, it becomes saturated and cannot be used in conventional signal recovery methods. Aiming at acquiring information from noisy saturated and regular measurements, we in this paper propose a new signal recovery method called mixed one-bit compressive sensing (M1bit-CS) and develop an efficient algorithm in the framework of alternating direction methods of multipliers. Numerical experiments on one-dimensional symmetric signals and two-dimensional image reconstruction from computed tomography verify the effectiveness of M1bit-CS on signal recovery from saturated measurements.},
author = {Huang, Xiaolin and Yang, Haiyan and Huang, Yixing and Shi, Lei and He, Fan and Maier, Andreas and Yan, Ming},
doi = {10.1016/j.sigpro.2019.04.011},
faupublication = {yes},
journal = {Signal Processing},
keywords = {Compressive sensing; Image reconstruction; One-bit; Signal recovery},
note = {CRIS-Team Scopus Importer:2019-05-02},
pages = {161-168},
peerreviewed = {Yes},
title = {{Robust} mixed one-bit compressive sensing},
volume = {162},
year = {2019}
}
@inproceedings{faucris.121230824,
address = {Berlin Heidelberg},
author = {Neumann, Dominik and Grbic, Sasa and John, Matthias and Navab, Nassir and Hornegger, Joachim and Ionasec, Razvan},
booktitle = {MICCAI 2013},
date = {2013-09-22/2013-09-26},
doi = {10.1007/978-3-642-40811-3{\_}22},
editor = {Mori Kensaku, Sakuma Ichiro, Sato Yoshinobu, Barillot Christian, Navab Nassir},
faupublication = {yes},
pages = {171-178},
publisher = {Springer},
title = {{Robust} {Model}-based {3D}/{3D} {Fusion} using {Sparse} {Matching} for {Minimally} {Invasive} {Surgery}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Neumann13-RM3.pdf},
venue = {Nagoya, Japan},
year = {2013}
}
@article{faucris.110788744,
author = {Köhler, Thomas and Huang, Xiaolin and Schebesch, Frank and Aichert, André and Maier, Andreas and Hornegger, Joachim},
doi = {10.1109/TCI.2016.2516909},
faupublication = {yes},
journal = {IEEE Transactions on Computational Imaging},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.robust},
pages = {42-58},
peerreviewed = {Yes},
title = {{Robust} {Multiframe} {Super}-{Resolution} {Employing} {Iteratively} {Re}-{Weighted} {Minimization}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Kohler16-RMS.pdf},
volume = {2},
year = {2016}
}
@inproceedings{faucris.111353704,
author = {Ghesu, Florin-Cristian and Georgescu, Bogdan and Grbic, Sasa and Maier, Andreas and Hornegger, Joachim and Comaniciu, Dorin},
booktitle = {Medical Image Computing and Computer-Assisted Intervention MICCAI 2017},
date = {2017-09-11/2017-09-13},
doi = {10.1007/978-3-319-66182-7{\_}23},
faupublication = {yes},
isbn = {9783319661810},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.robust{\_}1},
pages = {194-202},
peerreviewed = {unknown},
publisher = {Springer Verlag},
title = {{Robust} {Multi}-{Scale} {Anatomical} {Landmark} {Detection} in {Incomplete} {3D}-{CT} {Data}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Ghesu17-RMA.pdf},
venue = {Quebec, Canada},
volume = {10433 LNCS},
year = {2017}
}
@article{faucris.232333681,
abstract = {In minimally invasive procedures, the clinician relies on image guidance to observe and navigate the operation site. In order to show structures which are not visible in the live X-ray images, such as vessels or planning annotations, X-ray images can be augmented with pre-operatively acquired images. Accurate image alignment is needed and can be provided by 2-D/3-D registration. In this paper, a multi-view registration method based on the point-to-plane correspondence model is proposed. The correspondence model is extended to be independent of the used camera coordinates and different multi-view registration schemes are introduced and compared. Evaluation is performed for a wide range of clinically relevant registration scenarios. We show for different applications that registration using correspondences from both views simultaneously provides accurate and robust registration, while the performance of the other schemes varies considerably. Our method also outperforms the state-of-the-art method for cerebral angiography registration, achieving a capture range of 18 mm and an accuracy of 0.22 & x00B1;0.07 mm. Furthermore, investigations on the minimum angle between the views are performed in order to provide accurate and robust registration, while minimizing the obstruction to the clinical workflow. We show that small angles around 30 & x00B0; are sufficient to provide reliable registration results.},
author = {Schaffert, Roman and Wang, Jian and Fischer, Peter and Maier, Andreas and Borsdorf, Anja},
doi = {10.1109/TMI.2019.2922931},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
month = {Jan},
note = {CRIS-Team WoS Importer:2020-01-24},
pages = {161-174},
peerreviewed = {Yes},
title = {{Robust} {Multi}-{View} 2-{D}/3-{D} {Registration} {Using} {Point}-{To}-{Plane} {Correspondence} {Model}},
volume = {39},
year = {2020}
}
@inproceedings{faucris.246527408,
abstract = {In computed tomography (CT), automatic exposure control (AEC) is frequently used to reduce radiation dose exposure to patients. For organ-specific AEC, a preliminary CT reconstruction is necessary to estimate organ shapes for dose optimization, where only a few projections are allowed for real-time reconstruction. In this work, we investigate the performance of automated transform by manifold approximation (AUTOMAP) in such applications. For proof of concept, we investigate its performance on the MNIST dataset first, where the dataset containing all the 10 digits are randomly split into a training set and a test set. We train the AUTOMAP model for image reconstruction from 2 projections or 4 projections directly. The test results demonstrate that AUTOMAP is able to reconstruct most digits well with a false rate of 1.6% and 6.8% respectively. In our subsequent experiment, the MNIST dataset is split in a way that the training set contains 9 digits only while the test set contains the excluded digit only, for instance "2". In the test results, the digit "2"s are falsely predicted as "3" or "5" when using 2 projections for reconstruction, reaching a false rate of 94.4%. For the application in medical images, AUTOMAP is also trained on patients' CT images. The test images reach an average root-mean-square error of 290 HU. Although the coarse body outlines are well reconstructed, some organs are misshaped.
areas. Hence, the main purpose of this paper is to reduce streak artifacts at various scales. We propose the scale-space anisotropic total variation (ssaTV) algorithm, which is derived from wTV, in two different implementations. The first implementation (ssaTV-1) utilizes an anisotropic gradient-like operator which uses 2s neighboring pixels along the streaks’ normal direction at each scale s. The second implementation (ssaTV-2) makes use of anisotropic down-sampling and up-sampling operations, similarly oriented along the streaks’ normal direction, to apply TV regularization at various scales. Experiments on numerical and clinical data demonstrate that both ssaTV algorithms reduce streak artifacts more effectively and efficiently than wTV, particularly when using multiple scale},
author = {Huang, Yixing and Taubmann, Oliver and Huang, Xiaolin and Haase, Viktor and Lauritsch, Günter and Maier, Andreas},
doi = {10.1109/TRPMS.2018.2824400},
faupublication = {yes},
journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
keywords = {limited angle tomography; total variation; scale-space; anisotropic},
note = {UnivIS-Import:2018-09-05:Pub.2018.tech.IMMD.IMMD5.scales},
pages = {307-314},
peerreviewed = {Yes},
title = {{Scale}-{Space} {Anisotropic} {Total} {Variation} for {Limited} {Angle} {Tomography}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Huang18-SAT.pdf},
volume = {2},
year = {2018}
}
@article{faucris.114008224,
abstract = {Purpose: Recently, a reconstruction algorithm for region of interest (ROI) imaging in C-arm CT was published, named Approximate Truncation Robust Algorithm for Computed Tomography (ATRACT). Even in the presence of substantial data truncation, the algorithm is able to reconstruct images without the use of explicit extrapolation or prior knowledge. However, the method suffers from a scaling and offset artifact in the reconstruction. Hence, the reconstruction results are not quantitative. It is our goal to reduce the scaling and offset artifact so that Hounsfield unit (HU) values can be used for diagnosis. Methods: In this paper, we investigate two variants of the ATRACT method and present the analytical derivations of these algorithms in the Fourier domain. Then, we propose an empirical correction measure that can be applied to the ATRACT algorithm, to effectively compensate the scaling and offset issue. The proposed method is evaluated on ten clinical datasets in the presence of different degrees of artificial truncation. Results: With the proposed correction approach, we achieved an average relative root-mean-square error (rRMSE) of 2.81 % with respect to non-truncated Feldkamp, Davis, and Kress reconstruction, even for severely truncated data. The rRMSE is reduced to as little as 10 % of the image reconstructed without the scaling calibration. Conclusions: The reconstruction results show that ROI reconstruction of high accuracy can be achieved since the scaling and offset artifact are effectively eliminated by the proposed method. With this improvement, the HU values may be used for post-processing operations such as bone or soft tissue segmentation if some tolerance is accepted. © 2014 CARS.},
author = {Xia, Yan and Dennerlein, Frank and Bauer, Sebastian and Hofmann, Hannes and Hornegger, Joachim and Maier, Andreas},
doi = {10.1007/s11548-014-0978-z},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Dose reduction; Region of interest imaging; Scaling calibration; Truncation correction},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.scalin},
pages = {345-356},
peerreviewed = {unknown},
title = {{Scaling} calibration in region of interest reconstruction with the {1D} and {2D} {ATRACT} algorithm},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Xia14-SCI.pdf},
volume = {9},
year = {2014}
}
@inproceedings{faucris.120331024,
author = {Xia, Yan and Maier, Andreas and Dennerlein, Frank and Hornegger, Joachim},
booktitle = {Proceedings Bildverarbeitung für die Medizin 2013},
date = {2013-03-03/2013-03-05},
doi = {10.1007/978-3-642-36480-8},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {104-109},
title = {{Scaling} {Calibration} in the {ATRACT} {Algorithm}},
venue = {Heidelberg, Germany},
year = {2013}
}
@inproceedings{faucris.247507649,
abstract = {Introduction
With the rise of deep learning [1], we see a dramatic need of curated and annotated medical image data. In particular, in volumetric images, such annotations are extremely costly, as each slice has to be outlined individually to generate ground truth for the training of deep learning algorithms. Recently, a new initiative was founded that aims at encouraging patients to donate their medical image data [2]. In particular, this initiative also asks for permission to crowd-source the data annotation. This forms a basis to generate sufficient data for large-scale training of deep learning algorithms in medical image analysis.
Methods
In order to encourage users to perform annotations, we explore gamification. In particular, we selected the setup of a racing game to generate an exciting user experience. The main idea is that the user is driving a race car across a volumetric image slice. In order to create tracks automatically, a simple segmentation method is required. For the first experiments, we chose thresholding to separate fore- and background. Then, we select the largest connected component and perform image processing to automatically extract a closed edge contour. As guidance, checkpoints are spread over the preliminary organ outline to guide the player in equidistant steps along the extracted contour. Based on edge detection [3], a score consisting of accumulated edge pixels is determined automatically as feedback for the player. In order to create a more challenging game experience, additional moving obstacles were added to the course. During driving the player creates a closed contour that is then transmitted from the game client to the server’s database.
Results
The game was implemented in Unity3D [4] and released as Android APK Installer (https://www.medicaldatadonors.org/index.php/scan-racer/). We chose Google Firebase to store segmentation results on the server (https://firebase.google.com). ScanRacer creates a challenging, yet rewarding experience for the user. Experienced players are able to create segmentation contours close to the correct segmentation outline. Yet detailed annotations still pose a challenge in this setup which will be addressed by the addition of further game elements. In contrast to many other serious games, the fun component of ScanRacer is very high as reported by test players. A gameplay teaser video demonstrates this in detail. (https://www.youtube.com/watch?v=JNmEGLCyf6w)
Conclusion
ScanRacer offers a unique experience for players for volumetric image segmentation. The game is was implemented in Unity3D and is available for free download. Sources can be shared at request.
References
[1] Maier, A., Syben, C., Lasser, T., & Riess, C. (2019). A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik, 29(2), 86-101.
[2] Servadei, L., Schmidt, R., Eidelloth, C., & Maier, A. (2017, October). Medical Monkeys: A Crowdsourcing Approach to Medical Big Data. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" (pp. 87-97). Springer, Cham.
[3] Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence, (6), 679-698. [4] Murray, J. W. (2014). C# game programming cookbook for Unity 3D. AK Peters/CRC Press
We deal with the topic of segmenting emotion-related (emotional/affective) episodes into adequate units for analysis and automatic processing/classification—a topic that has not been addressed adequately so far. We concentrate on speech and illustrate promising approaches by using a database with children’s emotional speech. We argue in favour of the word as basic unit and map sequences of words on both syntactic and “emotionally consistent” chunks and report classification performances for an exhaustive modelling of our data by mapping word-based paralinguistic emotion labels onto three classes representing valence (positive, neutral, negative), and onto a fourth rest (garbage) class.
},
author = {Batliner, Anton and Seppi, Dino and Steidl, Stefan and Schuller, Björn},
doi = {10.1155/2010/782802},
faupublication = {yes},
journal = {Advances in Human-Computer Interaction},
peerreviewed = {Yes},
title = {{Segmenting} into adequate units for automatic recognition of emotion-related episodes: a speech-based approach},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Batliner10-SIA.pdf},
volume = {2010},
year = {2010}
}
@inproceedings{faucris.203710099,
abstract = {C-arm cone-beam CT systems have an increasing popularity in the clinical environment due to their highly flexible scan trajectories. Recent work used these systems to acquire images of the knee joint under weight-bearing conditions. During the scan, the patient is in a standing or in a squatting position and is likely to show involuntary motion, which corrupts image reconstruction. The state-of-the-art fully automatic motion compensation relies on fiducial markers for motion estimation. Due to the not reproducible horizontal trajectory, the system has to be calibrated with a calibration phantom before or after each scan. In this work we present a method to incorporate a self-calibration into the existing motion compensation framework without the need of prior geometric calibration. Quantitative and qualitative evaluations on a numerical phantom as well as clinical data, show superior results compared to the current state-of-the-art method. Moreover, the clinical workflow is improved, as a dedicated system calibration for weight-bearing acquisitions is no longer required.},
address = {Springer},
author = {Syben-Leisner, Christopher and Bier, Bastian and Berger, Martin and Aichert, André and Fahrig, Rebecca and Gold, Garry and Levenston, Marc and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen.},
date = {2017-03-12/2017-03-14},
doi = {10.1007/978-3-662-54345-0},
faupublication = {yes},
isbn = {978-3-662-54344-3},
note = {UnivIS-Import:2018-09-06:Pub.2017.tech.IMMD.IMMD5.selfca{\_}1},
pages = {56-61},
peerreviewed = {unknown},
publisher = {Springer-Verlag},
title = {{Self}-{Calibration} and {Simultaneous} {Motion} {Estimation} for {C}-arm {CT} using {Fiducial} {Markers}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Syben17-SAS.pdf},
venue = {Heidelberg},
year = {2017}
}
@inproceedings{faucris.107988364,
author = {Forman, Christoph and Aksoy, Murat and Straka, Matus and Hornegger, Joachim and Bammer, Roland},
booktitle = {Proceedings of the 18th Annual Meeting of ISMRM & ESMRMB},
date = {2010-05-01/2010-05-07},
editor = {International Society for Magnetic Resonance in Medicine (ISMRM)},
faupublication = {yes},
pages = {5025.0},
peerreviewed = {unknown},
title = {{Self}-{Encoded} {Marker} {Design} for {Adaptive} {Optical} {Real}-{Time} {Motion} {Correction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Forman10-SMD.pdf},
venue = {Stockholm},
year = {2010}
}
@article{faucris.121173624,
abstract = {The tracking and compensation of patient motion during a magnetic resonance imaging (MRI) acquisition is an unsolved problem. For brain MRI, a promising approach recently suggested is to track the patient using an in-bore camera and a checkerboard marker attached to the patient's forehead. However, the possible tracking range of the head pose is limited by the fact that the locally attached marker must be entirely visible inside the camera's narrow field of view (FOV). To overcome this shortcoming, we developed a novel self-encoded marker where each feature on the pattern is augmented with a 2-D barcode. Hence, the marker can be tracked even if it is not completely visible in the camera image. Furthermore, it offers considerable advantages over the checkerboard marker in terms of processing speed, since it makes the correspondence search of feature points and marker-model coordinates, which are required for the pose estimation, redundant. The motion correction with the novel self-encoded marker recovered a rotation of 18° around the principal axis of the cylindrical phantom in-between two scans. After rigid registration of the resulting volumes, we measured a maximal error of 0.39 mm and 0.15° in translation and rotation, respectively. In in vivo experiments, the motion compensated images in scans with large motion during data acquisition indicate a correlation of 0.982 compared to a corresponding motion-free reference. © 2011 Elsevier B.V.},
author = {Forman, Christoph and Aksoy, Murat and Hornegger, Joachim and Bammer, Roland},
doi = {10.1016/j.media.2011.05.018},
faupublication = {yes},
journal = {Medical Image Analysis},
pages = {708-719},
peerreviewed = {Yes},
title = {{Self}-encoded marker for optical prospective head motion correction in {MRI}},
volume = {15},
year = {2011}
}
@inproceedings{faucris.121417604,
author = {Forman, Christoph and Aksoy, Murat and Hornegger, Joachim and Bammer, Roland},
booktitle = {Lecture Notes in Computer Science},
date = {2010-09-20/2010-09-24},
editor = {Jiang Tianzi, Navab Nassir, Pluim Josien, Viergever Max},
faupublication = {yes},
pages = {259-266},
peerreviewed = {unknown},
title = {{Self}-encoded {Marker} for {Optical} {Prospective} {Head} {Motion} {Correction} in {MRI}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Forman10-SEM.pdf},
venue = {Beijing},
year = {2010}
}
@article{faucris.114100404,
abstract = {Accurate localization and uptake quantification of lesions in the chest and abdomen using PET imaging is challenged by respiratory motion occurring during the exam. This work describes how a stack-of-stars MRI acquisition on integrated PET/MRI systems can be used to derive a high-resolution motion model, how many respiratory phases need to be differentiated, how much MRI scan time is required, and how the model is employed for motion-corrected PET reconstruction. MRI self-gating is applied to perform respiratory gating of the MRI data and simultaneously acquired PET raw data. After gated PET reconstruction, the MRI motion model is used to fuse the individual gates into a single, motion-compensated volume with high signal-to-noise ratio (SNR). The proposed method is evaluated in vivo for 15 clinical patients. The gating requires 5-7 bins to capture the motion to an average accuracy of 2 mm. With 5 bins, the motion-modeling scan can be shortened to 3-4 min. The motion-compensated reconstructions show significantly higher accuracy in lesion quantification in terms of standardized uptake value (SUV) and different measures of lesion contrast compared to ungated PET reconstruction. Furthermore, unlike gated reconstructions, the motion-compensated reconstruction does not lead to SNR loss.},
author = {Grimm, Robert and Fürst, Sebastian and Souvatzoglou, Michael and Forman, Christoph and Hutter, Jana and Dregely, Isabel and Ziegler, Sibylle and Kiefer, Berthold and Hornegger, Joachim and Block, Kai Tobias and Nekolla, Stephan G.},
doi = {10.1016/j.media.2014.08.003},
faupublication = {yes},
journal = {Medical Image Analysis},
keywords = {Motion compensation; MRI; PET/MRI; Respiratory gating; Respiratory motion},
note = {UnivIS-Import:2015-03-09:Pub.2015.tech.IMMD.IMMD5.selfga},
pages = {110-120},
peerreviewed = {Yes},
title = {{Self}-gated {MRI} motion modeling for respiratory motion compensation in integrated {PET}/{MRI}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Grimm15-SMM.pdf},
volume = {19},
year = {2015}
}
@inproceedings{faucris.107939084,
author = {Grimm, Robert and Fürst, Sebastian and Dregely, Isabel and Forman, Christoph and Hutter, Jana and Ziegler, Sibylle and Nekolla, Stephan G. and Kiefer, Berthold and Schwaiger, Markus and Hornegger, Joachim and Block, Kai Tobias},
booktitle = {Proceedings of the 16th International Conference on Medical Image Computing and Computer Assisted Intervention},
date = {2013-09-22/2013-09-26},
doi = {10.1007/978-3-642-40760-4{\_}3},
editor = {Mori Kensaku, Sakuma Ichiro, Sato Yoshinobu, Barillot Christian, Navab Nassir},
faupublication = {yes},
pages = {17-24},
title = {{Self}-{Gated} {Radial} {MRI} for {Respiratory} {Motion} {Compensation} on {Hybrid} {PET}/{MR} {Systems}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Grimm13-SRM.pdf},
venue = {Nagoya, Japan},
year = {2013}
}
@inproceedings{faucris.121140624,
author = {Grimm, Robert and Block, Kai Tobias and Hutter, Jana and Forman, Christoph and Hintze, Christian and Kiefer, Berthold and Hornegger, Joachim},
booktitle = {Proceedings of International Society for Magnetic Resonance in Medicine},
date = {2012-05-05/2012-05-11},
faupublication = {yes},
pages = {3814},
peerreviewed = {unknown},
title = {{Self}-gating {Reconstructions} of {Motion} and {Perfusion} for {Free}-breathing {T1}-weighted {DCE}-{MRI} of the {Thorax} {Using} {3D} {Stack}-of-stars {GRE} {Imaging}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Grimm12-SRO.pdf},
venue = {Melbourne},
year = {2012}
}
@inproceedings{faucris.120182304,
abstract = {Magnetically-guided capsule endoscopy (MGCE) is a nascent technology with the goal to allow the steering of a capsule endoscope inside a water filled stomach through an external magnetic field. We developed a classification cascade for MGCE images with groups images in semantic and topological categories. Results can be used in a post-procedure review or as a starting point for algorithms classifying pathologies. The first semantic classification step discards over-/under-exposed images as well as images with a large amount of debris. The second topological classification step groups images with respect to their position in the upper gastrointestinal tract (mouth, esophagus, stomach, duodenum). In the third stage two parallel classifications steps distinguish topologically different regions inside the stomach (cardia, fundus, pylorus, antrum, peristaltic view). For image classification, global image features and local texture features were applied and their performance was evaluated. We show that the third classification step can be improved by a bubble and debris segmentation because it limits feature extraction to discriminative areas only. We also investigated the impact of segmenting intestinal folds on the identification of different semantic camera positions. The results of classifications with a support-vector-machine show the significance of color histogram features for the classification of corrupted images (97%). Features extracted from intestinal fold segmentation lead only to a minor improvement (3%) in discriminating different camera positions. © 2012 SPIE.},
author = {Mewes, Philip and Rennert, P. and Juloski, A. Lj. and Lalande, A. and Angelopoulou, Elli and Kuth, R. and Hornegger, Joachim},
booktitle = {Medical Imaging 2012: Computer-Aided Diagnosis},
doi = {10.1117/12.912280},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Semantic} and topological classification of images in magnetically guided capsule endoscopy},
venue = {San Diego, CA},
volume = {8315},
year = {2012}
}
@inproceedings{faucris.121414964,
address = {Berlin},
author = {Hornegger, Joachim and Nöth, Elmar and Fischer, Volker and Niemann, Heinrich},
booktitle = {Mustererkennung 1996},
date = {1996-09-11/1996-09-13},
doi = {10.1007/978-3-642-80294-2{\_}28},
editor = {Jähne B., Geißler P., Haußecker H., Hering F.},
faupublication = {yes},
pages = {260-267},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Semantic} {Network} {Meet} {Bayesian} {Classifiers}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1996/Hornegger96-SNM.pdf},
venue = {Heidelberg},
year = {1996}
}
@inproceedings{faucris.203850282,
author = {Vesal, Sulaiman and Diaz-Pinto, Andres and Ravikumar, Nishant and Ellmann, Stephan and Davari, Amirabbas and Maier, Andreas},
booktitle = {2017 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC)},
faupublication = {yes},
note = {UnivIS-Import:2018-09-11:Pub.2017.tech.IMMD.IMMD5.semiau{\_}5},
pages = {tbd},
peerreviewed = {Yes},
title = {{Semi}-{Automatic} {Algorithm} for {Breast} {MRI} {Lesion} {Segmentation} {Using} {Marker}-{Controlled} {Watershed} {Transformation}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Vesal17-SAF.pdf},
venue = {Atlanta, Georgia, USA},
year = {2017}
}
@inproceedings{faucris.108068444,
address = {Erlangen},
author = {Han, Jingfeng and Bennewitz, Christian and Hornegger, Joachim and Kuwert, Torsten},
booktitle = {3rd Russian-Bavarian Conference on Biomedical Engineering},
date = {2007-07-02/2007-07-03},
editor = {Hornegger Joachim, Mayr Ernst W., Schookin Sergey, Feußner Hubertus, Navab Nassir, Gulyaev Yuri V., Höller Kurt, Ganzha Victor},
faupublication = {yes},
pages = {93-100},
peerreviewed = {unknown},
publisher = {Union aktuell},
title = {{Semi}-automatical {Validation} of {SPECT}/{CT} {Scanners}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Han07-SVS.pdf},
venue = {Erlangen},
year = {2007}
}
@inproceedings{faucris.111127984,
abstract = {Ablation guided by focal impulse and rotor mapping (FIRM) is a novel treatment option for atrial fibrillation, a frequent heart arrhythmia. This procedure is performed minimally invasively and at least partially under fluoroscopic guidance. It involves a basket catheter comprising 64 electrodes. The 3-D position of these electrodes is important during treatment. We propose a novel model-based method for 3-D reconstruction of this catheter using two X-ray images taken from different views. Our approach requires only little user interaction. An evaluation of the method found that the electrodes of the basket catheter can be reconstructed with a median error of 1.5 mm for phantom data and 3.4 mm for clinical data.},
address = {Berlin},
author = {Zhong, Xia and Hoffmann, Matthias and Strobel, Norbert and Maier, Andreas},
booktitle = {Pattern Recognition},
date = {2015-10-07/2015-10-10},
doi = {10.1007/978-3-319-24947-6{\_}31},
faupublication = {yes},
isbn = {978-3-319-24946-9},
note = {UnivIS-Import:2017-12-18:Pub.2015.tech.IMMD.IMMD5.semiau{\_}8},
pages = {379-389},
peerreviewed = {unknown},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {{Semi}-{Automatic} {Basket} {Catheter} {Reconstruction} from {Two} {X}-{Ray} {Views}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2015/Zhong15-SBC.pdf},
venue = {Aachen},
volume = {9358},
year = {2015}
}
@inproceedings{faucris.123549844,
abstract = {In this article, we describe a semi-automatic calibration algorithm for dereverberation by spectral subtraction. We verify the method by a comparison to a manual calibration derived from measured room impulse responses (RIR). We conduct extensive experiments to understand the effect of all involved parameters and to verify values suggested in the literature. The experiments are performed on a text read by 31 speakers and recorded by a headset and three far-field microphones. Results are measured in terms of automatic speech recognition (ASR) performance using a 1-gram model to emphasize acoustic recognition performance. To accommodate for the acoustic change by dereverberation we apply supervised MAP adaptation to the hidden Markov model output probabilities. The combination of dereverberation and adaptation yields a relative improvement of about 35% in terms of word error rate (WER) compared to the original signal.},
author = {Riedhammer, Korbinian Thomas and Bocklet, Tobias and Orozco-Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {11th ITG Symposium on Speech Communication},
faupublication = {yes},
isbn = {9783800736409},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
title = {{Semi}-automatic calibration for dereverberation by spectral subtraction for continuous speech recognition},
url = {https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84939530520&origin=inward},
year = {2014}
}
@inproceedings{faucris.108079664,
author = {Käppler, Sebastian and Wu, Wen and Chen, Terrence and Koch, Martin and Kiraly, Attila P. and Strobel, Norbert and Hornegger, Joachim},
booktitle = {Proceedings of 2013 10th IEEE International Symposium on Biomedical Imaging: From Nano to Macro},
date = {2013-04-07},
editor = {IEEE},
faupublication = {yes},
pages = {TBD},
title = {{Semi}-{Automatic} {Catheter} {Model} {Generation} using {Biplane} {X}-{Ray} {Images}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Kaeppler13-SCM.pdf},
venue = {San Francisco, CA},
year = {2013}
}
@article{faucris.121154924,
abstract = {We propose novel methods for (a) detection of a catheter in fluoroscopic images and (b) reconstruction of this catheter from two views. The novelty of (a) is a reduced user interaction and a higher accuracy. It requires only a single seed point on the catheter in the fluoroscopic image. Using this starting point, possible parts of the catheter are detected using a graph search. An evaluation of the detection using 66 clinical fluoroscopic images yielded an average error of 0.7 mm +/- 2.0 mm. The novelty of (b) is a better ability to deal with highly curved objects as it selects an optimal set of point correspondences from two point sequences describing the catheters in two fluoroscopic images. The selected correspondences are then used for computation of the 3-D reconstruction. The evaluation on 33 clinical biplane images yielded an average backprojection error of 0.4 mm +/- 0.6 mm.},
author = {Hoffmann, Matthias and Brost, Alexander and Jakob, Carolin and Bourier, Felix and Koch, Martin and Kurzidim, Klaus and Hornegger, Joachim and Strobel, Norbert},
faupublication = {yes},
journal = {Lecture Notes in Computer Science},
pages = {584-591},
peerreviewed = {Yes},
title = {{Semi}-automatic catheter reconstruction from two views},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-84872902383&origin=inward},
volume = {15},
year = {2012}
}
@inproceedings{faucris.118562444,
abstract = {We propose novel methods for (a) detection of a catheter in fluoroscopic images and (b) reconstruction of this catheter from two views. The novelty of (a) is a reduced user interaction and a higher accuracy. It requires only a single seed point on the catheter in the fluoroscopic image. Using this starting point, possible parts of the catheter are detected using a graph search. An evaluation of the detection using 66 clinical fluoroscopic images yielded an average error of 0.7 mm +/- 2.0 mm. The novelty of (b) is a better ability to deal with highly curved objects as it selects an optimal set of point correspondences from two point sequences describing the catheters in two fluoroscopic images. The selected correspondences are then used for computation of the 3-D reconstruction. The evaluation on 33 clinical biplane images yielded an average backprojection error of 0.4 mm +/- 0.6 mm.},
address = {Berlin, Heidelberg},
author = {Hoffmann, Matthias and Brost, Alexander and Jakob, Carolin and Bourier, Felix and Koch, Martin and Kurzidim, Klaus and Hornegger, Joachim and Strobel, Norbert},
booktitle = {MICCAI 2012, Part I},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2012.tech.IMMD.IMMD5.semiau{\_}47},
pages = {584-591},
peerreviewed = {unknown},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
title = {{Semi}-{Automatic} {Catheter} {Reconstruction} from {Two} {Views}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Hoffmann12-SCR.pdf},
venue = {Nice, France},
volume = {7510},
year = {2012}
}
@inproceedings{faucris.216058198,
author = {Chen, Shuqing and Gehrer, Simone and Kaliman, Sara and Ravikumar, Nishant and Becit, Abdurrahman and Aliee, Maryam and Dudziak, Diana and Merkel, Rudolf and Smith, Ana-Suncana and Maier, Andreas},
booktitle = {Bildverarbeitung für die Medizin 2019. Informatik aktuell.},
date = {2019-03-17/2019-03-19},
doi = {10.1007/978-3-658-25326-4{\_}26},
editor = {Handels H., Deserno T., Maier A., Maier-Hein K., Palm C., Tolxdorff T.},
faupublication = {yes},
isbn = {978-3-658-25325-7},
pages = {116-121},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Semi}-{Automatic} {Cell} {Correspondence} {Analysis} {Using} {Iterative} {Point} {Cloud} {Registration}},
venue = {Lübeck},
year = {2019}
}
@article{faucris.121219824,
abstract = {We present a new level-set based method to segment and quantify stenosed internal carotid arteries (ICAs) in 3D contrast-enhanced computed tomography angiography (CTA). Within these data sets it is a difficult task to evaluate the degree of stenoses deterministically even for the experienced physician because the actual vessel lumen is hardly distinguishable from calcified plaque and there is no sharp border between lumen and arterial wall. According to our knowledge no commercially available software package allows the detection of the boundary between lumen and plaque components. Therefore in the clinical environment physicians have to perform the evaluation manually. This approach suffers from both intra- and inter-observer variability. The limitation of the manual approach requires the development of a semi-automatic method that is able to achieve deterministic segmentation results of the internal carotid artery via level-set techniques. With the new method different kinds of plaques were almost completely excluded from the segmented regions. For an objective evaluation we also studied the method's performance with four different phantom data sets for which the ground truth of the degree of stenosis was known a priori. Finally, we applied the method to 10 ICAs and compared the obtained segmentations with manual measurements of three physicians. © 2006 Elsevier B.V. All rights reserved.},
author = {Scherl, Holger and Hornegger, Joachim and Prümmer, Marcus and Lell, Michael},
doi = {10.1016/j.media.2006.09.004},
faupublication = {yes},
journal = {Medical Image Analysis},
pages = {21-34},
peerreviewed = {Yes},
title = {{Semi}-automatic level-set based segmentation and stenosis quantification of the internal carotid artery in {3D} {CTA} data sets},
volume = {11},
year = {2007}
}
@inproceedings{faucris.108154024,
address = {Magdeburg},
author = {Sickel, Konrad and Baloch, Sajjad and Bubnik, Vojtech and Melkisetoglu, Rupen and Azernikov, Sergei and Fang, Tong and Hornegger, Joachim},
booktitle = {Proceedings of the Vision, Modeling, and Visualization Workshop 2009},
date = {2009-11-16/2009-11-18},
editor = {Magnor Marcus A., Rosenhahn Bodo, Theisel Holger},
faupublication = {yes},
pages = {305-312},
peerreviewed = {unknown},
publisher = {Universität Magdeburg Institut fuer Simulation und Graphik},
title = {{Semi}-{Automatic} {Manufacturing} of {Customized} {Hearing} {Aids} {Using} a {Feature} {Driven} {Rule}-based {Framework}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Sickel09-SMO.pdf},
venue = {Braunschweig},
year = {2009}
}
@inproceedings{faucris.250677604,
abstract = {In osteoporosis research, the number and size of lacunae in cortical bone tissue are important characteristics of osteoporosis development. In order to reconstruct lacunae well in X-ray microscopy while protecting bone marrow from high-dose damage in in-vivo experiments, semi-permeable X-ray filters are proposed for dose reduction. Compared with an opaque filter, image quality with a semi-permeable filter is improved remarkably. For image reconstruction, both iterative reconstruction with reweighted total variation (wTV) and FDK reconstruction from penalized weighted least-square (PWLS) processed projections can reconstruct lacunae when the transmission rate of the filter is as small as 5%. However, PWLS is superior in computation efficiency.
Methods : We propose an OCT specific module, “SlicerOCT,” which leverages 3D Slicer’s existing capabilities for orthoplane viewing and volume rendering. OCT and OCTA data are stored in different layers, which allows simultaneous display; layers can be toggled on and off. OCT specific functions, such as volume projection and OCTA thresholding, are available. Orthoplane views can be scrolled through in a manner analogous to a conventional radiology viewer and data can be rendered volumetrically.
Results : Figure 1 shows a SlicerOCT display of OCT and OCTA data from a patient with exudative age-related macular degeneration (AMD). The choroidal neovascularization (CNV) is clearly visible in the OCT angiograms and corresponding structural en face displays (right panels), while CNV location under the retinal pigment epithelium (RPE) and intraretinal cysts are visible in the OCT B-scan display (bottom left). Figure 2 shows a SlicerOCT display of OCT and OCTA data from a patient with geographic atrophy (GA). Areas of RPE alteration are visible on OCTA, while areas of choriocapillaris loss are seen on OCTA. Unlike traditional en face visualization of OCTA data, orthoplane viewing enables interpretation of individual OCTA B-scans, which can help identify artifacts, such as incorrect segmentation, signal attenuation, and decorrelation tails.
Conclusions : SlicerOCT enables simultaneous, orthoplane visualization of OCT and OCTA datasets, which promises to enable more accurate interpretation of OCTA data and is especially crucial for studying diseases whose progression alters both structure and blood flo},
address = {ARVO},
author = {Husvogt, Lennart and Moult, Eric M. and Lee, Byungkun and Waheed, Nadia K. and Hornegger, Joachim and Spaide, Richard F. and Maier, Andreas and Fujimoto, James G.},
booktitle = {Investigative Ophthalmology & Visual Science},
date = {2016-05-01/2016-05-05},
edition = {12},
faupublication = {yes},
keywords = {oct;octa; oct angiography;3d slicer},
note = {UnivIS-Import:2018-09-06:Pub.2016.tech.IMMD.IMMD5.slicer},
pages = {5974},
peerreviewed = {unknown},
publisher = {ARVO},
title = {{SlicerOCT}: {A} 3-{D} visualization platform for orthoplane viewing of {OCT}({A}) datasets},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Husvogt16-SA3.pdf},
venue = {Seattle, WA, USA},
volume = {57},
year = {2016}
}
@inproceedings{faucris.203726251,
abstract = {Large-scale image data such as digital whole-slide histology images pose a challenging task at annotation software solutions. Today, a number of good solutions with varying scopes exist. For cell annotation, however, we find that many do not match the prerequisites for fast annotations. Especially in the field of mitosis detection, it is assumed that detection accuracy could significantly benefit from larger annotation databases that are currently however very troublesome to produce. Further, multiple independent (blind) expert labels are a big asset for such databases, yet there is currently no tool for this kind of annotation available. To ease this tedious process of expert annotation and grading, we introduce SlideRunner, an open source annotation and visualization tool for digital histopathology, developed in close cooperation with two pathologists. SlideRunner is capable of setting annotations like object centers (for e.g. cells) as well as object boundaries (e.g. for tumor outlines). It provides single-click annotations as well as a blind mode for multi-annotations, where the expert is directly shown the microscopy image containing the cells that he has not yet rated.
Cyclic signals are an intrinsic part of daily life, such as human motion and heart activity. The detailed analysis of them is important for clinical applications such as pathological gait analysis and for sports applications such as performance analysis. Labeled training data for algorithms that analyze these cyclic data come at a high annotation cost due to only limited annotations available under laboratory conditions or requiring manual segmentation of the data under less restricted conditions. This paper presents a smart annotation method that reduces this cost of labeling for sensor-based data, which is applicable to data collected outside of strict laboratory conditions. The method uses semi-supervised learning of sections of cyclic data with a known cycle number. A hierarchical hidden Markov model (hHMM) is used, achieving a mean absolute error of 0.041 ± 0.020 s relative to a manually-annotated reference. The resulting model was also used to simultaneously segment and classify continuous, ‘in the wild’ data, demonstrating the applicability of using hHMM, trained on limited data sections, to label a complete dataset. This technique achieved comparable results to its fully-supervised equivalent. Our semi-supervised method has the significant advantage of reduced annotation cost. Furthermore, it reduces the opportunity for human error in the labeling process normally required for training of segmentation algorithms. It also lowers the annotation cost of training a model capable of continuous monitoring of cycle characteristics such as those employed to analyze the progress of movement disorders or analysis of running technique.},
author = {Martindale, Christine and Hönig, Florian Thomas and Strohrmann, Christina and Eskofier, Björn},
doi = {10.3390/s17102328},
faupublication = {yes},
journal = {Sensors},
keywords = {hierarchical hidden Markov models; segmentation; smart annotation; cyclic sensor data; semi-supervised learning; annotation cost; activity recognition; gait classification; inertial sensors; wearable sensors},
peerreviewed = {Yes},
title = {{Smart} {Annotation} of {Cyclic} {Data} {Using} {Hierarchical} {Hidden} {Markov} {Models}},
url = {http://www.mdpi.com/1424-8220/17/10/2328},
volume = {17},
year = {2017}
}
@inproceedings{faucris.203913853,
abstract = {The monitoring of patients within a natural, home environment is important in order to close knowledge gaps in the treatment and care of neurodegenerative diseases, such as quantifying the daily fluctuation of Parkinson’s patients’ symptoms. The combination of machine learning algorithms and wearable sensors for gait analysis is becoming capable of achieving this. However, these algorithms require large, labelled, realistic datasets for training. Most systems used as a ground truth for labelling are restricted to the laboratory environment, as well as being large and expensive. We propose a study design for a realistic activity monitoring dataset, collected with inertial measurement units, pressure insoles and cameras. It is not restricted by a fixed location or capture volume and still enables the labelling of gait phases or, where non-gait movement such as jumping occur: on-the-ground, off-the-ground phases. Additionally, this paper proposes a smart annotation tool which reduces annotation cost by more than 80%. This smart annotation is based on edge detection within the pressure sensor signal. The tool also enables annotators to perform assisted correction of these labels in a post-processing step. This system enables the collection and labelling of large, fairly realistic datasets where 93% of the automatically generated labels are correct and only an additional 10% need to be inserted manually. Our tool and protocol, as a whole, will be useful for efficiently collecting the large datasets needed for training and validation of algorithms capable of cyclic human motion analysis in natural environment},
author = {Martindale, Christine and Roth, Nils and Hannink, Julius and Sprager, Sebastijan and Eskofier, Björn},
booktitle = {2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)},
date = {2018-03-19/2018-03-23},
doi = {10.1109/PERCOMW.2018.8480193},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Smart} {Annotation} {Tool} for {Multi}-sensor gait based daily activity data},
url = {https://www.mad.tf.fau.de/files/2018/09/percom2018{\_}martindale.pdf},
venue = {Athens},
year = {2018}
}
@article{faucris.315845108,
abstract = {Objectives: To evaluate whether artifacts on contrast-enhanced (CE) breast MRI maximum intensity projections (MIPs) might already be forecast before gadolinium-based contrast agent (GBCA) administration during an ongoing examination by analyzing the unenhanced T1-weighted images acquired before the GBCA injection. Materials and methods: This IRB-approved retrospective analysis consisted of n = 2884 breast CE MRI examinations after intravenous administration of GBCA, acquired with n = 4 different MRI devices at different field strengths (1.5 T/3 T) during clinical routine. CE-derived subtraction MIPs were used to conduct a multi-class multi-reader evaluation of the presence and severity of artifacts with three independent readers. An ensemble classifier (EC) of five DenseNet models was used to predict artifacts for the post-contrast subtraction MIPs, giving as the input source only the pre-contrast T1-weighted sequence. Thus, the acquisition directly preceded the GBCA injection. The area under ROC (AuROC) and diagnostics accuracy scores were used to assess the performance of the neural network in an independent holdout test set (n = 285). Results: After majority voting, potentially significant artifacts were detected in 53.6% (n = 1521) of all breast MRI examinations (age 49.6 ± 12.6 years). In the holdout test set (mean age 49.7 ± 11.8 years), at a specificity level of 89%, the EC could forecast around one-third of artifacts (sensitivity 31%) before GBCA administration, with an AuROC = 0.66. Conclusion: This study demonstrates the capability of a neural network to forecast the occurrence of artifacts on CE subtraction data before the GBCA administration. If confirmed in larger studies, this might enable a workflow-blended approach to prevent breast MRI artifacts by implementing in-scan personalized predictive algorithms. Clinical relevance statement: Some artifacts in contrast-enhanced breast MRI maximum intensity projections might be predictable before gadolinium-based contrast agent injection using a neural network. Key Points: • Potentially significant artifacts can be observed in a relevant proportion of breast MRI subtraction sequences after gadolinium-based contrast agent administration (GBCA). • Forecasting the occurrence of such artifacts in subtraction maximum intensity projections before GBCA administration for individual patients was feasible at 89% specificity, which allowed correctly predicting one in three future artifacts. • Further research is necessary to investigate the clinical value of such smart personalized imaging approaches.},
author = {Liebert, Andrzej and Das, Badhan Kumar and Kapsner, Lorenz and Eberle, Jörg and Skwierawska, Dominika and Folle, Lukas and Schreiter, Hannes and Laun, Frederik Bernd and Ohlmeyer, Sabine and Uder, Michael and Wenkel, Evelyn and Bickelhaupt, Sebastian},
doi = {10.1007/s00330-023-10469-7},
faupublication = {yes},
journal = {European Radiology},
keywords = {Artifact; Breast; Forecasting; Magnetic resonance imaging; Neural networks (computer)},
note = {CRIS-Team Scopus Importer:2023-12-22},
peerreviewed = {Yes},
title = {{Smart} forecasting of artifacts in contrast-enhanced breast {MRI} before contrast agent administration},
year = {2023}
}
@incollection{faucris.221674310,
abstract = {The SMARTKOM-Public communications booth is provided with a wide palette of modern communication appliances. SMARTKOM-Public offers a higher degree of privacy, much higher communication bandwidth and optimal quality with regard to input and output results than is available to mobile systems for technical reasons. High rates of data flow and high-resolution screens lead, in contrast to a personal digital assistant (PDA), to increased comfort and better ergonomics. This communication space offers the simultaneous and comfortable use of language, pictorial and data services. A document camera is integrated for the transmission and processing of documents. An interesting further possibility concerns the saving of the user’s data in the communications booth. Upon biometric identification, users are able to access their personal data. The idea of a virtual communications workstation that is capable of traveling with the users and adapting to their needs becomes reality. As the product at hand deals with a communication space for the public, along with supplying services, intuitive usability is of primary importance for acceptance. This is particularly so as even people who do not have access to a home computer with similar services will also make use of SMARTKOM-Public. The human–machine interface is designed to replicate normal human means of communication. This includes the broadest range of free speech dialogue possible and the use of natural gestures. Consideration must be made that conventional uses, and not only those based on multi-modal communication, can be performed from the communication booth. Therefore our project started with a user study. The results are presented in the next section, followed by a description of the implemented functionality and some detailed information on selected realization topics in subsequent section},
address = {Berlin, Heidelberg},
author = {Horndasch, Axel and Rapp, Horst and Röttger, Hans},
booktitle = {SmartKom: Foundations of Multimodal Dialogue Systems},
doi = {10.1007/3-540-36678-4{\_}30},
editor = {Wolfgang Wahlster},
faupublication = {yes},
isbn = {978-3-540-23732-7},
keywords = {Multi-modal dialog systems, SmartKom, public communication, human–machine interface},
pages = {471-492},
peerreviewed = {unknown},
publisher = {Springer},
title = {{SmartKom}-{Public}},
volume = {7},
year = {2006}
}
@inproceedings{faucris.264576812,
abstract = {As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation. The generation of realistic-looking handwritten text is important because it can be used for data augmentation in handwritten text recognition (HTR) systems or human-computer interaction. We propose SmartPatch, a new technique increasing the performance of current state-of-the-art methods by augmenting the training feedback with a tailored solution to mitigate pen-level artifacts. We combine the well-known patch loss with information gathered from the parallel trained handwritten text recognition system and the separate characters of the word. This leads to a more enhanced local discriminator and results in more realistic and higher-quality generated handwritten words.},
author = {Mattick, Alexander and Mayr, Martin and Seuret, Mathias and Maier, Andreas and Christlein, Vincent},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2021-09-05/2021-09-10},
doi = {10.1007/978-3-030-86549-8{\_}18},
editor = {Josep Lladós, Daniel Lopresti, Seiichi Uchida},
faupublication = {yes},
isbn = {9783030865481},
keywords = {Generative adversarial networks; Offline handwriting generation; Patch discriminator},
note = {CRIS-Team Scopus Importer:2021-10-01},
pages = {268-283},
peerreviewed = {Yes},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{SmartPatch}: {Improving} {Handwritten} {Word} {Imitation} with {Patch} {Discriminators}},
url = {https://arxiv.org/abs/2105.10528},
venue = {Lausanne, CHE},
volume = {12821 LNCS},
year = {2021}
}
@inproceedings{faucris.111034924,
abstract = {Touch input on modern smartphones can be tedious, especially if the touchscreen is small. Smartphones with integrated projectors can be used to overcome this limitation by projecting the screen contents onto a surface, allowing the user to interact with the projection by means of simple hand gestures. In this work, we propose a novel approach for projector smartphones that allows the user to remotely interact with the smartphone screen via its projection. We detect user's interaction using the built-in camera, and forward detected hand gestures as touch input events to the operating system. In order to avoid costly computations, we additionally use built-in motion sensors. We verify the proposed method using an implementation for the consumer smartphone Samsung Galaxy Beam equipped with a deflection mirror. © 2014 Springer International Publishing.},
address = {Cham},
author = {Deitsch, Sergiu and Götzelmann, Timo and Gallwitz, Florian},
booktitle = {Human-Computer Interaction. Applications and Services},
date = {2014-06-22/2014-06-27},
doi = {10.1007/978-3-319-07227-2{\_}13},
editor = {Kurosu M.},
faupublication = {no},
isbn = {978-3-319-07226-5},
keywords = {Mobile computing;user interfaces;small screen;fat finger problem;touch input;fingertip detection;projector smartphone;DLP projector},
note = {UnivIS-Import:2017-12-18:Pub.2014.tech.IMMD.IMMD5.smartp},
pages = {124-133},
peerreviewed = {Yes},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
title = {{Smartphone} {Input} {Using} {Its} {Integrated} {Projector} and {Built}-{In} {Camera}},
venue = {Heraklion, Crete, Greece},
volume = {8512},
year = {2014}
}
@inproceedings{faucris.124239544,
abstract = {
Automatic smile recognition plays an important part in several intelligent image processing systems. This paper presents an automatic smile detection system based on lip corners identification. Two different corner detection algorithms are used in this paper to identify lip corners, i.e., the Harris corner detection and the FAST corner detection. The proposed system is tested using our VISiO smiling face database. Our results show that the Harris corner detector yields the best result with 77.5% accuracy while the FAST corner detector gives 72.5% accuracy. However, these results depend on the method of of determining pavg (the average lip corner position during the training phase).
},
author = {Royce, Eduard and Setyawan, Iwan and Timotius, Ivanna},
booktitle = {The 1st International Conference on Information Technology, Computer and Electrical Engineering (ICITACEE 2014)},
doi = {10.1109/ICITACEE.2014.7065746},
faupublication = {no},
keywords = {smile recognition; corner detection; lip corner identification.},
pages = {222 - 225},
peerreviewed = {Yes},
title = {{Smile} {Recognition} {System} based on {Lip} {Corners} {Identification}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7065746},
venue = {Semarang},
year = {2014}
}
@inproceedings{faucris.108033024,
author = {Jordan, Johannes Michael and Helwig, Sabine and Wanka, Rolf},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference},
date = {2008-07-12/2008-07-16},
doi = {10.1145/1389095.1389103},
editor = {ACM Press},
faupublication = {yes},
pages = {49-56},
title = {{Social} {Interaction} in {Particle} {Swarm} {Optimization}, the {Ranked} {FIPS}, and {Adaptive} {Multi}-{Swarms}},
url = {http://www12.informatik.uni-erlangen.de/people/helwig/publications/JHW08.php},
venue = {Atlanta, Georgia},
year = {2008}
}
@misc{faucris.210050568,
author = {Wilke, Peter},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Soft}-{Computing} - {Prinzip}},
year = {1997}
}
@inproceedings{faucris.120173284,
abstract = {Embedded microcontrollers are employed in an increasing number of applications as a target for the implementation of classification systems. This is true for example for the fields of sports, automotive and medical engineering. However, important challenges arise when implementing classification systems on embedded microcontrollers, which is mainly due to limited hardware resources. In this paper, we present a solution to the two main challenges, namely obtaining a classification system with low computational complexity and at the same time high classification accuracy. For the first challenge, we propose complexity measures on the mathematical operation and parameter level, because the abstraction level of the commonly used Landau notation is too high in the context of embedded system implementation. For the second challenge, we present a software toolbox that trains different classification systems, compares their classification rate, and finally analyzes the complexity of the trained system. To give an impression of the importance of such complexity measures when dealing with limited hardware resources, we present the example analysis of the popular Pima Indians Diabetes data set, where considerable complexity differences between classification systems were revealed.},
author = {Ring, Matthias and Jensen, Ulf and Kugler, Patrick and Eskofier, Björn},
booktitle = {Proceedings of the 2012 21st International Conference on Pattern Recognition (ICPR)},
date = {2012-11-11/2012-11-15},
editor = {IEEE},
faupublication = {yes},
pages = {2266-2269},
peerreviewed = {Yes},
title = {{Software}-based {Performance} and {Complexity} {Analysis} for the {Design} of {Embedded} {Classification} {Systems}},
venue = {Tsukuba},
year = {2012}
}
@article{faucris.121209924,
abstract = {In this paper we give a broad overview of modalities used in modern medical imaging and image processing. The whole image processing pipeline including image acquisition, image pre- and post-processing, reconstruction and multi-modal image registration is introduced. We roughly describe the user requirements of medical image processing algorithms and their implication to the system architecture and the software-engineering process as it is established in medical engineering. © 2008 Springer-Verlag.},
author = {Hornegger, Joachim and Reiß, Joachim and Kuwert, Torsten},
faupublication = {yes},
journal = {Computer Science - Research and Development},
pages = {161-171},
peerreviewed = {unknown},
title = {{Software} development in medicine technology using medical image processing as an example},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-58049178852&origin=inward},
volume = {22},
year = {2008}
}
@incollection{faucris.108096384,
address = {San Diego},
author = {Paulus, Dietrich and Hornegger, Joachim and Niemann, Heinrich},
booktitle = {unbekannt},
faupublication = {yes},
pages = {77-103},
peerreviewed = {unknown},
publisher = {Academic Press},
title = {{Software} {Engineering} for {Image} {Processing} and {Analysis}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Paulus99-SEF.pdf},
volume = {3.0},
year = {1999}
}
@article{faucris.121467104,
author = {Hornegger, Joachim and Reiß, Joachim and Kuwert, Torsten},
doi = {10.1007/s00450-008-0041-9},
faupublication = {yes},
journal = {Informatik - Forschung und Entwicklung},
pages = {161 - 171},
peerreviewed = {unknown},
title = {{Softwareentwicklung} in der {Medizintechnik} am {Beispiel} der medizinischen {Bildverarbeitung}},
url = {http://www.springerlink.com/content/71g43kr6jp458814/#ContactOfAuthor1},
year = {2008}
}
@inproceedings{faucris.210093742,
author = {Wilke, Peter},
booktitle = {RISC-Architekturen, Reihe Informatik, vol. 60},
faupublication = {yes},
pages = {pp 63-95},
peerreviewed = {unknown},
title = {{Software} für {RISC}, optimierende {Compiler}},
year = {1988}
}
@inproceedings{faucris.203726519,
author = {Huang, Yixing and Würfl, Tobias and Breininger, Katharina and Liu, Ling and Lauritsch, Günter and Maier, Andreas},
booktitle = {Proceedings of the 21st International Conference on Medical Image Computing & Computer Assisted Intervention},
doi = {10.1007/978-3-030-00928-1{\_}17},
faupublication = {yes},
keywords = {Deep learning; limited angle tomography; robustness; adversarial example},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.somein},
pages = {145-153},
peerreviewed = {Yes},
publisher = {Springer, Cham},
title = {{Some} {Investigations} on {Robustness} of {Deep} {Learning} in {Limited} {Angle} {Tomography}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Huang18-SIO.pdf},
venue = {Granada, Spain},
year = {2018}
}
@inproceedings{faucris.117354204,
abstract = {Sleep plays a fundamental role in the life of every human. The prevalence of sleep disorders has increased significantly, now affecting up to 50%of the general population. Sleep is usually analyzed by extracting a hypnogram containing sleep stages. The gold standard method polysomnography (PSG) requires subjects to stay overnight in a sleep laboratory and to wear a series of obtrusive devices. This work presents an easy to use method to perform somnography at home using unobtrusive motion sensors. © 2013 IEEE.},
author = {Gradl, Stefan and Leutheuser, Heike and Kugler, Patrick and Biermann, Teresa and Kreil, Sebastian and Kornhuber, Johannes and Bergner, Matthias and Eskofier, Björn},
booktitle = {IEEE EMBC 2013},
date = {2013-07-03/2013-07-07},
doi = {10.1109/EMBC.2013.6609717},
editor = {Engineering in Medicine and Biology Society},
faupublication = {yes},
isbn = {9781457702167},
pages = {1182-1185},
peerreviewed = {Yes},
title = {{Somnography} using unobtrusive motion sensors and {Android}-based mobile phones},
venue = {Osaka},
year = {2013}
}
@inproceedings{faucris.107856584,
author = {Bauer, Sebastian and Ettl, Svenja and Wasza, Jakob and Willomitzer, Florian and Huber, Franz and Hornegger, Joachim and Häusler, Gerd},
booktitle = {DGaO Proceedings 2012},
date = {2012-05-29},
editor = {Häusler Gerd, Faber Christian},
faupublication = {yes},
pages = {P22},
peerreviewed = {unknown},
title = {{Sparse} {Active} {Triangulation} {Grids} for {Respiratory} {Motion} {Management}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Bauer12-SAT.pdf},
venue = {Eindhoven NL},
year = {2012}
}
@inproceedings{faucris.203366877,
author = {Wang, Jian and Riess, Christian and Borsdorf, Anja and Heigl, Benno and Hornegger, Joachim},
booktitle = {Proceedings of the 15th International Conference on Computer Analysis of Images and Patterns - Part I},
date = {2013-08-27/2013-08-29},
doi = {10.1007/978-3-642-40261-6{\_}10},
faupublication = {yes},
pages = {86--93},
peerreviewed = {Yes},
title = {{Sparse} {Depth} {Sampling} for {Interventional} 2-{D}/3-{D} {Overlay}: {Theoretical} {Error} {Analysis} and {Enhanced} {Motion} {Estimation}},
venue = {York},
year = {2013}
}
@inproceedings{faucris.107891564,
address = {York, UK},
author = {Wang, Jian and Riess, Christian and Borsdorf, Anja and Heigl, Benno and Hornegger, Joachim},
booktitle = {Computer Analysis of Images and Patterns},
date = {2013-08-27/2013-08-29},
editor = {Wilson Richard, Hancock Edwin, Bors Adrian, Smith William},
faupublication = {yes},
pages = {86-93},
publisher = {Springer Berlin Heidelberg},
title = {{Sparse} {Depth} {Sampling} for {Interventional} 2-{D}/3-{D} {Overlay}: {Theoretical} {Error} {Analysis} and {Enhanced} {Motion} {Estimation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Wang13-SDS.pdf},
venue = {York, UK},
year = {2013}
}
@inproceedings{faucris.121415404,
address = {Heidelberg},
author = {Wasza, Jakob and Bauer, Sebastian and Haase, Sven and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2012},
date = {2012-03-20},
doi = {10.1007/978-3-642-28502-8},
editor = {Deserno Thomas M., Handels Heinz, Meinzer Hans-Peter, Tolxdorff Thomas},
faupublication = {yes},
pages = {316-321},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Sparse} {Principal} {Axes} {Statistical} {Surface} {Deformation} {Models} for {Respiration} {Analysis} and {Classication}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Wasza12-SPA.pdf},
venue = {Berlin},
year = {2012}
}
@inproceedings{faucris.121307604,
author = {Wu, Haibo and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2012},
date = {2012-03-03/2012-03-05},
doi = {10.1007/978-3-642-28502-8{\_}26},
editor = {Springer Berlin Heidelberg},
faupublication = {yes},
pages = {141-146},
peerreviewed = {Yes},
title = {{Sparsity} {Level} {Constrained} {Compressed} {Sensing} for {CT} {Reconstruction}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Wu12-SLC.pdf},
venue = {Berlin},
year = {2012}
}
@article{faucris.107395024,
abstract = {"Natural Orifice Translumenal Endoscopic Surgery" (NOTES) is assumed to offer significant benefits to patients, such as reduced trauma as well as reduced collateral damage. But the potential advantages of this new technology can only be achieved through safe and standardized operation methods. Several barriers, which have been identified during clinical practice in flexible intra-abdominal endoscopy, can only be solved with computer-assisted surgical (CAS) systems. In order to assist the surgeon during the intervention and enhance his visual possibilities, some of these CAS systems require 3-D information of the intervention site, for others 3-D information is even mandatory. Therefore it is evident that the definition and design of new technologies for CAS systems must be strongly considered. A 3-D endoscope, called "Multisensor-Time-of-Flight" (MUSTOF) endoscope, is actually being developed. Within these developments, an optical 3-D time-of-flight (TOF) sensor is attached to the proximal end of a common endoscope. The 3-D depth information obtained by this enhanced endoscope can furthermore be registered with preoperatively acquired 3-D volumetric datasets such as CT or MRI. These enhanced or augmented 3-D data volumes could then be used to find the transgastric or transcolonic entry point to the abdomen. Furthermore, such acquired endoscopic depth data can be used to provide better orientation within the abdomen. Moreover it can also prevent intra-operative collisions and provide an optimized field of view with the possibility for off-axis viewing. Furthermore, providing a stable horizon on video-endoscopic images, especially within non-rigid endoscopic surgery scenarios (particularly within NOTES), remains an open issue. Hence, our recently presented "endorientation" approach for automated image orientation rectification could turn out as an important contribution. It works with a tiny micro-electro-mechanical systems (MEMS) tri-axial inertial sensor that is placed on the distal tip of an endoscope. By measuring the impact of gravity on each of the three orthogonal axes the rotation angle can be estimated with some calculations out of these three acceleration values, which can be used to automatically rectify the endoscopic images using image processing methods. Using such enhanced, progressive endoscopic system extensions proposed in this article, translumenal surgery could in the future be performed in a safer and more feasible manner. © 2010 Informa Healthcare.},
author = {Höller, Kurt Emmerich and Schneider, Armin and Jahn, Jasper and Gutierrez, Javier and Wittenberg, Thomas and Feussner, Hubertus and Hornegger, Joachim},
doi = {10.3109/13645706.2010.510762},
faupublication = {yes},
journal = {Minimally Invasive Therapy & Allied Technologies},
pages = {262-273},
peerreviewed = {Yes},
title = {{Spatial} orientation in translumenal surgery},
volume = {19},
year = {2010}
}
@inproceedings{faucris.121160424,
abstract = {Four dimensional computed tomography (4D-CT) is very important for treatment planning in thorax or abdomen area, e.g. for guiding radiation therapy planning. The respiratory motion makes the reconstruction problem illposed. Recently, compressed sensing theory was introduced. It uses sparsity as a prior to solve the problem and improves image quality considerably. However, the images at each phase are reconstructed individually. The correlations between neighboring phases are not considered in the reconstruction process. In this paper, we propose the spatial-temporal total variation regularization (STTVR) method which not only employs the sparsity in the spatial domain but also in the temporal domain. The algorithm is validated with XCAT thorax phantom. The Euclidean norm of the reconstructed image and ground truth is calculated for evaluation. The results indicate that our method improves the reconstruction quality by more than 50% compared to standard ART. © 2012 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).},
author = {Wu, Haibo and Maier, Andreas and Fahrig, Rebecca and Hornegger, Joachim},
booktitle = {Medical Imaging 2012: Physics of Medical Imaging},
doi = {10.1117/12.911162},
faupublication = {yes},
pages = {-},
peerreviewed = {Yes},
title = {{Spatial}-temporal total variation regularization ({STTVR}) for {4D}-{CT} reconstruction},
venue = {San Diego, CA},
volume = {8313},
year = {2012}
}
@inproceedings{faucris.119120144,
abstract = {In this paper we propose a spatio-temporal digital video hashing scheme. In the proposed scheme, the digital video is treated as a three dimensional signal. Edge Orientation Histogram (EOH) is computed for each frame in the digital video, then a temporal discrete cosine transform (DCT) for the magnitude of each EOH bin is computed. A subset of the resulting DCT coefficients are then pseudo-randomly rearranged to construct the hash. Our experiments show that the proposed system has good discriminating power, is robust against content-preserving attacks but is sensitive to content-altering attacks.},
author = {Setyawan, Iwan and Timotius, Ivanna},
booktitle = {International Conference on Information Technology Systems and Innovation},
doi = {10.1109/ICITSI.2014.7048247},
faupublication = {no},
keywords = {digital video hashing; digital video authentication; edge orientation histogram; discrete cosine transform.},
peerreviewed = {unknown},
title = {{Spatio}--{Temporal} {Digital} {Video} {Hashing} using {Edge} {Orientation} {Histogram} and {Discrete} {Cosine} {Transform}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7048247},
venue = {Bandung},
year = {2014}
}
@inproceedings{faucris.245798477,
abstract = {Most people think that their handwriting is unique and cannot
be imitated by machines, especially not using completely new content.
Current cursive handwriting synthesis is visually limited or needs user
interaction. We show that subdividing the process into smaller subtasks
makes it possible to imitate someone’s handwriting with a high chance to
be visually indistinguishable for humans. Therefore, a given handwritten
sample will be used as the target style. This sample is transferred to
an online sequence. Then, a method for online handwriting synthesis is
used to produce a new realistic-looking text primed with the online input
sequence. This new text is rendered and style-adapted to the input pen.
We show the effectiveness of the pipeline by generating in- and out-of-
vocabulary handwritten samples that are validated in a comprehensive
user study. Additionally, we show that also a typical writer identification
system can partially be fooled by the created fake handwritings.
We demonstrate the efficacy of the proposed method using cine-MR sequences of 145 subjects and comparing the performance with other state-of-the-art quantification methods. The proposed method obtained high prediction accuracy, with an average mean absolute error (MAE) of 129 mm2, 1.23 mm, 1.76 mm, Pearson correlation coefficient (PCC) of 96.4%, 87.2%, and 97.5% for LV and myocardium (Myo) cavity regions, 6 RWTs, 3 LV dimensions, and an error rate of 9.0% for phase classification. The experimental results highlight the robustness of the proposed method, despite varying degrees of cardiac morphology, image appearance, and low contrast in the cardiac MR sequences},
author = {Vesal, Sulaiman and Gu, Mingxuan and Maier, Andreas and Ravikumar, Nishant},
doi = {10.1109/JBHI.2020.3046449},
faupublication = {yes},
journal = {IEEE Journal of Biomedical and Health Informatics},
keywords = {Left Ventricle Quantification, Cardiac MRI, Cardiac Segmentation, Deep Learning, Myocardial Infraction},
peerreviewed = {Yes},
title = {{Spatio}-temporal {Multi}-task {Learning} for {Cardiac} {MRI} {Left} {Ventricle} {Quantification}},
url = {https://ieeexplore.ieee.org/document/9302580},
year = {2020}
}
@article{faucris.206677033,
author = {Arias Vergara, Tomás and Vasquez Correa, Juan and Rafael Orozco-Arroyave, Juan and Nöth, Elmar},
doi = {10.1016/j.specom.2018.05.007},
faupublication = {yes},
journal = {Speech Communication},
pages = {11-25},
peerreviewed = {Yes},
title = {{Speaker} models for monitoring {Parkinson}’s disease progression considering different communication channels and acoustic conditions},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0167639317304454},
volume = {101},
year = {2018}
}
@book{faucris.208421439,
author = {Vasquez Correa, Juan and Castrillon, Reinel and Arias Vergara, Tomás and Orozco Arroyave, Juan Rafael and Nöth, Elmar},
doi = {10.1007/978-3-319-64206-2{\_}31},
faupublication = {yes},
isbn = {9783319642055},
keywords = {Speaker model; UPDRS; Articulation; Parkinson’s disease; Dysarthria; Prosody; Phonation},
pages = {272-280},
peerreviewed = {Yes},
publisher = {Springer Verlag},
title = {{Speaker} model to monitor the neurological state and the dysarthria level of patients with parkinson’s disease},
year = {2017}
}
@inproceedings{faucris.213036419,
address = {NEW YORK},
author = {Garcia-Ospina, Nicanor and Orozco Arroyave, Juan Rafael and Vargas-Bonilla, Jesus-Francisco},
booktitle = {2018 52ND ANNUAL IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST)},
date = {2018-10-22/2018-10-25},
doi = {10.1109/CCST.2018.8585602},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-03-12},
pages = {32-36},
peerreviewed = {unknown},
publisher = {IEEE},
title = {{Speaker} verification system for online education platforms},
venue = {Montreal},
year = {2018}
}
@inproceedings{faucris.313217213,
abstract = {This study investigated the relationship of speech intelligibility and the narrative comprehension among bilingual kindergarten children and how well the speech intelligibility of second language (L2) predicted the L2 narrative comprehension using a machine learning approach. Fifty Chinese-English bilingual children aged 5-6 years old participated in this study by taking a narrative comprehension test. Their L2 narrative comprehension was assessed using the MAIN test. The speech intelligibility was assessed in terms of twenty-four features that encode confidence levels with respect to phoneme and word classifiers trained on native speaker speech data. Our hypothesis posits that it is possible to predict L2 narrative comprehension based on speech intelligibility features. By using seven out of the twenty-four considered features we were able to make predictions of the MAIN test scores with an RMSE of 2.13 and a Pearson correlation coefficient of 0.468 based on a data set of 50 bilingual kindergarten children. We conclude the paper by providing pedagogical implications for second language teaching as well as suggestions for future work.
We present a study on the effect of reverberation on acoustic-linguistic recognition of non-prototypical emotions during child-robot interaction. Investigating the well-defined Interspeech 2009 Emotion Challenge task of recognizing negative emotions in children’s speech, we focus on the impact of artificial and real reverberation conditions on the quality of linguistic features and on emotion recognition accuracy. To maintain acceptable recognition performance of both, spoken content and affective state, we consider matched and multi-condition training and apply our novel multi-stream automatic speech recognition system which outperforms conventional Hidden Markov Modeling. Depending on the acoustic condition, we obtain unweighted emotion recognition accuracies of between 65.4% and 70.3% applying our multi-stream system in combination with the SimpleLogistic algorithm for joint acoustic-linguistic analysis.
},
author = {Wöllmer, Martin and Weninger, Felix and Steidl, Stefan and Batliner, Anton and Schuller, Björn},
booktitle = {Proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH 2011)},
date = {2011-08-27/2011-08-31},
editor = {ISCA},
faupublication = {yes},
keywords = {child-robot interaction; affective computing; acoustic-linguistic emotion recognition; reverberation},
pages = {3113-3116},
peerreviewed = {Yes},
title = {{Speech}-based {Non}-prototypical {Affect} {Recognition} for {Child}-{Robot} {Interaction} in {Reverberated} {Environments}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Woellmer11-SNA.pdf},
venue = {Florenz},
year = {2011}
}
@inproceedings{faucris.108039184,
address = {Muenchen},
author = {Botinhao, Cassia and Nöth, Elmar and Hornegger, Joachim and Maier, Andreas},
booktitle = {Proceedings of the 5th Russian-Bavarian Conference on Biomedical Engineering},
date = {2009-07-01/2009-07-04},
editor = {Russian Bavarian Conference on Bio-Medical Engineering},
faupublication = {yes},
pages = {151-153},
peerreviewed = {Yes},
publisher = {TU Muenchen},
title = {{Speech} {Classification} for {Sigmatism} in {Children}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Botinhao09-SCF.pdf},
venue = {Munich},
year = {2009}
}
@inproceedings{faucris.229601502,
abstract = {Introduction:
The onset of deafness affects speech in different ways. Speech differences of Cochlear Implant (CI) users with pre- and postlingual deafness are examined using acoustic features extracted automatically from speech.
Methods:
Utterances of 22 prelingual (15 up to 71 years old) and 22 postlingual CI users (15 up to 78 years old) were analyzed. All patients read 97 words, which contain every phoneme of the German language in different positions within the words. Speech analysis is performed in the transitions from voiceless to voiced sounds that mark the precise control of speech movement patterns. To extract the transitions, we search for the boundary between voiceless and voiced sounds using the fundamental frequency with a constant segment of 80 ms to the left and right. The feature set includes 13 Mel-Frequency Cepstral Coefficients and their 1st and 2nd derivatives. The mean, standard deviation, skewness and kurtosis are computed from the descriptors, forming a 156-dimensional feature vector. Wilcoxon signed-rank test is used to find differences between the pre- and postlingual groups.
Results:
The Wilcoxon signed-rank test was performed for each descriptor and significant differences between the pre- and postlingual groups (α < 0.05) were found in 8 of the 156 features. Additionally, a support vector regressor was trained to evaluate the age independence of the selected features. According to the results, there was not a strong correlation between the age of the speakers and the selected features (ρ < 0.40).
Conclusions:
Speech patterns differ significantly between pre- and postlingual CI users at the transitions of voiceless to voiced sounds. Other acoustic features are to be examined and considered in the rehabilitation after cochlear implantation.
},
author = {Arias Vergara, Tomás and Orozco Arroyave, Juan Rafael and Vasquez Correa, Juan and Nöth, Elmar and Schuster, Maria and Gollwitzer, Sandra and Högerle, Catalina},
booktitle = {Laryngo-Rhino-Otol 2019},
date = {2019-05-29/2019-06-01},
doi = {10.1055/s-0039-168632},
faupublication = {yes},
keywords = {Speech processing, Automatic acoustic analysis; Cochlear Implants, Voice/voiceless sounds},
pages = {305-305},
peerreviewed = {unknown},
publisher = {Georg Thieme Verlag KG Stuttgart},
title = {{Speech} differences between {CI} users with pre- and postlingual onset of deafness detected by speech processing methods on voiceless to voice transitions},
venue = {Estrel Congress Center Berlin},
year = {2019}
}
@article{faucris.117830724,
abstract = {Tooth loss and its prosthetic rehabilitation significantly affect speech intelligibility. However, little is known about the influence of speech deficiencies on oral health-related quality of life (OHRQoL). The aim of this study was to investigate whether speech intelligibility enhancement through prosthetic rehabilitation significantly influences OHRQoL in patients wearing complete maxillary dentures. Speech intelligibility by means of an automatic speech recognition system (ASR) was prospectively evaluated and compared with subjectively assessed Oral Health Impact Profile (OHIP) scores.Speech was recorded in 28 edentulous patients 1 week prior to the fabrication of new complete maxillary dentures and 6 months thereafter. Speech intelligibility was computed based on the word accuracy (WA) by means of an ASR and compared with a matched control group. One week before and 6 months after rehabilitation, patients assessed themselves for OHRQoL.Speech intelligibility improved significantly after 6 months. Subjects reported a significantly higher OHRQoL after maxillary rehabilitation with complete dentures. No significant correlation was found between the OHIP sum score or its subscales to the WA.Speech intelligibility enhancement achieved through the fabrication of new complete maxillary dentures might not be in the forefront of the patients' perception of their quality of life. For the improvement of OHRQoL in patients wearing complete maxillary dentures, food intake and mastication as well as freedom from pain play a more prominent role.},
author = {Knipfer, Christian and Riemann, Max and Bocklet, Tobias and Nöth, Elmar and Schuster, Maria and Sokol, Biljana and Eitner, Stephan and Nkenke, Emeka and Stelzle, Florian},
faupublication = {yes},
journal = {International Journal of Prosthodontics},
note = {EVALuna2:24365},
pages = {61-9},
peerreviewed = {Yes},
title = {{Speech} intelligibility enhancement after maxillary denture treatment and its impact on quality of life},
volume = {27},
year = {2014}
}
@inproceedings{faucris.115639524,
abstract = {One of the goals of the EMBASSI project is the creation of a speech interface between a user and a TV set or VCR. The interface should allow spontaneous speech recorded by microphones far away from the speaker. This paper describes experiments evaluating the robustness of a speech recognizer against reverberation. For this purpose a speech corpus was recorded with several different distortion types under real-life conditions. On these data the recognition results for reverberated signals using μ-law companded features were compared to an MFCC baseline system. Trained with clear speech, the word accuracy for the μ-law features on highly reverberated signals was 3 percent points better than the baseline result.},
address = {Berlin},
author = {Haderlein, Tino and Stemmer, Georg and Nöth, Elmar and Haderlein, Tino},
booktitle = {Proceedings on the 6th International Conference on Text, Speech, Dialogue - TSD 2003},
date = {2003-09-08/2003-09-12},
editor = {Matouzsek V.; Mautner P.},
faupublication = {yes},
pages = {173-180},
peerreviewed = {unknown},
publisher = {Springer-Verlag},
title = {{Speech} recognition with μ-law companded features on reverberated signals},
url = {https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=9444285489&origin=inward},
venue = {Ceske Budejovice},
volume = {2807},
year = {2003}
}
@inproceedings{faucris.315092998,
abstract = {Recent studies showed the possibility of extracting SoS information from pulse-echo ultrasound raw data (a.k.a. RF data) using deep neural networks that are fully trained on simulated data. These methods take sensor domain data, i.e., RF data, as input and train a network in an end-to-end fashion to learn the implicit mapping between the RF data domain and the SoS domain. However, such networks are prone to overfitting to simulated data which results in poor performance and instability when tested on measured data. We propose a novel method for SoS mapping employing learned representations from two linked autoencoders. We test our approach on simulated and measured data acquired from human breast mimicking phantoms. We show that SoS mapping is possible using the learned representations by linked autoencoders. The proposed method has a Mean Absolute Percentage Error (MAPE) of 2.39 % on the simulated data. On the measured data, the predictions of the proposed method are close to the expected values (MAPE of 1.1 % ). Compared to an end-to-end trained network, the proposed method shows higher stability and reproducibility.},
author = {Khun Jush, Farnaz and Dueppenbecker, Peter M. and Maier, Andreas},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2023-07-29/2023-07-29},
doi = {10.1007/978-3-031-47679-2{\_}8},
editor = {Andreas K. Maier, Julia A. Schnabel, Pallavi Tiwari, Oliver Stegle},
faupublication = {yes},
isbn = {9783031476785},
keywords = {Convolutional Autoencoder; Representation Learning; Speed-of-sound Mapping},
note = {CRIS-Team Scopus Importer:2023-12-15},
pages = {103-114},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Speed}-of-{Sound} {Mapping} for {Pulse}-{Echo} {Ultrasound} {Raw} {Data} {Using} {Linked}-{Autoencoders}},
venue = {Honolulu, HI, USA},
volume = {14315 LNCS},
year = {2024}
}
@article{faucris.120186924,
abstract = {Amplitude decorrelation measurement is sensitive to transverse flow and immune to phase noise in comparison to Doppler and other phase-based approaches. However, the high axial resolution of OCT makes it very sensitive to the pulsatile bulk motion noise in the axial direction. To overcome this limitation, we developed split-spectrum amplitude-decorrelation angiography (SSADA) to improve the signal-to-noise ratio (SNR) of flow detection. The full OCT spectrum was split into several narrower bands. Inter-B-scan decorrelation was computed using the spectral bands separately and then averaged. The SSADA algorithm was tested on in vivo images of the human macula and optic nerve head. It significantly improved both SNR for flow detection and connectivity of microvascular network when compared to other amplitude-decorrelation algorithms. © 2012 Optical Society of America.},
author = {Jia, Yali and Tan, Ou and Tokayer, Jason and Potsaid, Benjamin and Wang, Yimin and Liu, Jonathan J. and Kraus, Martin and Subhash, Hrebesh and Fujimoto, James G. and Hornegger, Joachim and Huang, David},
doi = {10.1364/OE.20.004710},
faupublication = {yes},
journal = {Optics Express},
pages = {4710-4725},
peerreviewed = {Yes},
title = {{Split}-spectrum amplitude-decorrelation angiography with optical coherence tomography},
volume = {20},
year = {2012}
}
@article{faucris.107854824,
author = {Gallwitz, Florian and Niemann, Heinrich and Nöth, Elmar},
doi = {10.1007/s11576-008-0110-5},
faupublication = {yes},
journal = {Wirtschaftsinformatik},
pages = {538-547},
peerreviewed = {Yes},
title = {{Spracherkennung} - {Stand} der {Technik}, {Einsatzmöglichkeiten} und {Perspektiven}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1999/Gallwitz99-SSD.pdf},
volume = {41.0},
year = {1999}
}
@incollection{faucris.120393504,
address = {München},
author = {Görz, Günther and Hornegger, Joachim},
booktitle = {Taschenbuch der Medieninformatik},
faupublication = {yes},
pages = {194-219},
peerreviewed = {unknown},
publisher = {Carl Hanser},
title = {{Sprach}- und {Bilderkennung}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Goerz05-SUB.pdf},
year = {2005}
}
@article{faucris.108142584,
author = {Sambale, Maria and Schuster, Maria and Bocklet, Tobias and Maier, Andreas and Eysholdt, Ulrich and Ströbele, Anika and Stelzle, Florian},
faupublication = {yes},
journal = {Laryngo-Rhino-Otologie},
pages = {-},
peerreviewed = {Yes},
title = {{Sprachverständlichkeit} und {Krankheitsverarbeitung} nach der {Therapie} von {Mundhöhlenkarzinomen}},
url = {https://www.thieme-connect.com/ejournals/abstract/lro/doi/10.1055/s-0030-1267960},
volume = {e-first},
year = {2010}
}
@inproceedings{faucris.120330584,
address = {München},
author = {Frank, Carmen Manuela and Nöth, Elmar},
booktitle = {Fortschritte der Akustik - Proc. DAGA 05},
date = {2005-03-14/2005-03-17},
editor = {DEGA},
faupublication = {yes},
pages = {729-730},
publisher = {DEGA},
title = {{Sprechen}: {Ein} {Hindernis} in der modernen {Mensch}-{Maschine}-{Kommunikation}?},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Frank05-SEH.pdf},
venue = {München},
year = {2005}
}
@inproceedings{faucris.107975164,
address = {-},
author = {Aretoulaki, Maria and Harbeck, Stefan and Gallwitz, Florian and Nöth, Elmar and Niemann, Heinrich and Ivanecky, Josef and Ipsic, Ivo and Pavesic, Nikola and Matoušek, Václav},
booktitle = {Proc. Int. Conf. on Spoken Language Processing},
date = {1998-11-30/1998-12-04},
editor = {ICSLP'98},
faupublication = {yes},
pages = {-},
publisher = {-},
title = {{SQEL}: {A} {Multilingual} and {Multifunctional} {Dialogue} {System}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1998/Aretoulaki98-SAM.pdf},
venue = {Sydney},
year = {1998}
}
@inproceedings{faucris.243513704,
abstract = {Image reconstruction is particularly difficult when the type of image degradations are unknown. This may be the case if the acquisition device is unknown or the images stem from an uncontrolled environment like the internet. Yet, it may be important to reconstruct a specific piece of information from the image, such as digits from signs or vehicle license plates. Existing works incorporate such prior information with a
sequential super-resolution and classification pipeline. However, this approach is prone to error propagation. In this work, we propose a new approach of connecting classification and super-resolution in parallel within a multi-task network. We show that this architecture is able to preserve structures and to remove noisy pixels although the network itself has never been trained on noisy data. We also show that this
design allows to transparently trade classification and super-resolution
quality. On upsampling by factor 4, we outperform sequential approaches in terms of SSIM by 10% and improve classification by 69},
author = {Schirrmacher, Franziska and Lorch, Benedikt and Stimpel, Bernhard and Köhler, Thomas and Riess, Christian},
booktitle = {2020 IEEE International Conference on Image Processing (ICIP)},
date = {2020-10-25/2020-10-28},
doi = {10.1109/ICIP40778.2020.9191253},
faupublication = {yes},
keywords = {Deep learning; Multi-task learning; Super-resolution; Classification},
pages = {533-537},
peerreviewed = {Yes},
title = {{SR²}: {Super}-{Resolution} {With} {Structure}-{Aware} {Reconstruction}},
url = {https://faui1-files.cs.fau.de/public/publications/mmsec/2020-Schirrmacher-SR2.pdf},
venue = {Online},
year = {2020}
}
@inproceedings{faucris.120202104,
abstract = {The intensity-images captured by Time-of-Flight (ToF)-cameras are biased in several ways. The values differ significantly, depending on the integration time set within the camera and on the distance of the scene. Whereas the integration lime leads to an almost linear scaling of the whole image, the attenuation due to the distance is nonlinear, resulting in higher intensities for objects closer to the camera. The background regions that are farther away contain comparably low values, leading to a bad contrast within the image. Another effect is that some kind of specularity may be observed due to uncommon reflecting conditions at some points within the scene. These three effects lead to intensity images which exhibit significantly different values depending on the integration time of the camera and the distance to the scene, thus making parameterization of processing steps like edge-detection, segmentation, registration and threshold computation a tedious task. Additionally, outliers with exceptionally high values lead to insufficient visualization results and problems in processing. In this work we propose scaling techniques which generate images whose intensities are independent of the integration time of the camera and the measured distance. Furthermore, a simple approach for reducing specularity effects is introduced. © 2008 IEEE.},
author = {Stürmer, Michael and Penne, Jochen and Hornegger, Joachim},
booktitle = {2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops},
doi = {10.1109/CVPRW.2008.4563166},
faupublication = {yes},
peerreviewed = {unknown},
title = {{Standardization} of intensity-values acquired by {Time}-of-{Flight}-cameras},
venue = {Anchorage, AK},
volume = {null},
year = {2008}
}
@inproceedings{faucris.113130204,
abstract = {This paper introduces a unified Bayesian approach to 3–D computer vision using segmented image features. The theoretical part summarizes the basic requirements of statistical object recognition systems. Non–standard types of models are introduced using parametric probability density functions, which allow the implementation of Bayesian classifiers for object recognition purposes. The importance of model densities is demonstrated by concrete examples. Normally distributed features are used for automatic learning, localization, and classification. The contribution concludes with the experimental evaluation of the presented theoretical approach. },
address = {Heidelberg},
author = {Hornegger, Joachim and Paulus, Dietrich and Niemann, Heinrich},
booktitle = {Data Highways and Information Flooding, a Challenge for Classification and Data Analysis},
date = {1997-03-12/1997-03-14},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Statistical} classifiers in computer vision},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Hornegger97-SCI.pdf},
venue = {Potsdam},
year = {1997}
}
@incollection{faucris.113137904,
address = {Berlin},
author = {Hornegger, Joachim and Paulus, Dietrich and Niemann, Heinrich},
booktitle = {Classification, Data Analysis, and Data Highways},
doi = {10.1007/978-3-642-72087-1{\_}33},
faupublication = {yes},
pages = {295-303},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Statistical} classifiers in computer vision},
year = {1998}
}
@inproceedings{faucris.121226864,
abstract = {This work describes a statistical approach to deal with learning and recognition problems in the field of computer vision. An abstract theoretical framework is provided, which is suitable for automatic model generation from examples, identification, and localization of objects. Both, the learning and localization stage are formalized as parameter estimation tasks. The statistical learning phase is unsupervised with respect to the matching of model and scene features. The general mathematical description yields algorithms which can even treat parameter estimation problems from projected data. The experiments show that this probabilistic approach is suitable for solving 2D and 3D object recognition problems using grey-level images. The method can also be applied to 3D image processing issues using range images, i.e. 3D input data.},
address = {Piscataway, NJ, United States},
author = {Hornegger, Joachim and Niemann, Heinrich},
booktitle = {Proceedings of the 5th International Conference on Computer Vision},
doi = {10.1109/ICCV.1995.466838},
editor = {Anon},
faupublication = {yes},
pages = {914-919},
peerreviewed = {unknown},
publisher = {IEEE},
title = {{Statistical} learning, localization, and identification of objects},
venue = {Cambridge, MA, USA},
volume = {null},
year = {1995}
}
@inproceedings{faucris.108244224,
address = {-},
author = {Hornegger, Joachim},
booktitle = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
date = {1997-04-21/1997-04-24},
editor = {ICASSP},
faupublication = {yes},
pages = {3173-3176},
publisher = {IEEE Computer Society Press},
title = {{Statistical} {Modeling} of {Relations} for 3-{D} {Object} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Hornegger97-SMO.pdf},
venue = {Munich},
year = {1997}
}
@book{faucris.111632444,
address = {Aachen},
author = {Hornegger, Joachim},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
publisher = {Shaker},
title = {{Statistische} {Modellierung}, {Klassifikation} und {Lokalisation} von {Objekten}},
year = {1996}
}
@incollection{faucris.106270164,
address = {Leipzig},
author = {Hornegger, Joachim},
booktitle = {Die besten Informatik-Dissertationen 1996},
faupublication = {yes},
note = {UnivIS-Import:2015-04-20:Pub.1997.tech.IMMD.IMMD5.statis{\_}6},
pages = {128-149},
peerreviewed = {No},
publisher = {Teubner},
title = {{Statistische} {Modellierung}, {Klassifikation} und {Lokalisation} von {Objekten}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Hornegger97-SMK.pdf},
year = {1997}
}
@inproceedings{faucris.203726796,
author = {Aichert, André and Jérôme, Lesaint and Würfl, Tobias and Clackdoyle, Rolf and Desbat, Laurent and Maier, Andreas},
booktitle = {Proceedings of the Fifth International Conference on Image Formation in X-Ray Computed Tomography (CT-Meeting)},
faupublication = {yes},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.stereo},
pages = {198-201},
peerreviewed = {unknown},
title = {{Stereo} {Rectification} for {X}-ray {Data} {Consistency} {Conditions}},
venue = {Salt Lake City, UT, United States},
year = {2018}
}
@inproceedings{faucris.108870124,
address = {Krumbach},
author = {Haderlein, Tino and Nöth, Elmar and Döllinger, Michael and Schützenberger, Anne},
booktitle = {Aktuelle phoniatrisch-pädaudiologische Aspekte 2017},
doi = {10.3205/17dgpp51},
faupublication = {yes},
isbn = {978-3-9817636-2-1},
keywords = {Sprache},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.stimmq{\_}9},
pages = {136-138},
peerreviewed = {Yes},
publisher = {Frick},
title = {{Stimmqualitätsmessung} mittels prosodischer {Analyse} verschiedener gelesener {Textabschnitte}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Haderlein17-SMP.pdf},
venue = {Bern, Switzerland},
year = {2017}
}
@inproceedings{faucris.111348864,
author = {Huang, Yixing and Lu, Yanye and Taubmann, Oliver and Lauritsch, Günter and Maier, Andreas},
booktitle = {3rd Conference on Image-Guided Interventions & Fokus Neuroradiologie},
date = {2017-11-06/2017-11-07},
faupublication = {yes},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.streak},
pages = {7-8},
peerreviewed = {unknown},
title = {{Streak} {Artifact} {Reduction} in {Limited} {Angle} {Tomography} {Using} {Machine} {Learning}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Huang17-SAR.pdf},
venue = {Magdeburg, Germany},
year = {2017}
}
@article{faucris.117708404,
author = {Barth, Jens and Oberndorfer, Cäcilia and Pasluosta, Cristian Federico and Schülein, Samuel and Gaßner, Heiko and Reinfelder, Samuel and Kugler, Patrick and Schuldhaus, Dominik and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn},
doi = {10.3390/s150306419},
faupublication = {yes},
journal = {Sensors},
keywords = {inertial sensors; stride segmentation; accelerometer; gyroscope; dynamic time warping; free walk; gait analysis; Parkinsons disease; geriatric patients; movement impairments},
note = {UnivIS-Import:2015-04-14:Pub.2015.tech.IMMD.IMMD5.stride},
pages = {6419-6440},
peerreviewed = {Yes},
title = {{Stride} {Segmentation} {During} {Free} {Walk} {Movements} {Using} {Multi}-dimensional {Subsequence} {Dynamic} {Time} {Warping} on {Inertial} {Sensor} {Data}},
volume = {15},
year = {2015}
}
@inproceedings{faucris.120917544,
address = {Berlin Heidelberg},
author = {Hoffmann, Matthias and Bourier, Felix and Strobel, Norbert and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2013},
date = {2013-03-03},
doi = {10.1007/978-3-642-36480-8{\_}43},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {241-246},
publisher = {Springer},
title = {{Structure}-{Enhancing} {Visualization} for {Manual} {Registration} in {Fluoroscopy}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Hoffmann13-SVF.pdf},
venue = {Heidelberg},
year = {2013}
}
@article{faucris.109983324,
abstract = {Fresnel zone plate based soft x-ray transmission microspectroscopy has developed into a routine technique for high-resolution elemental or chemical 2D imaging of thin film specimens. The availability of high resolution Fresnel lenses with short depth of focus offers the possibility of optical slicing (in the third dimension) by focus series with resolutions in the submicron regime. We introduce a 3D reconstruction algorithm that uses a variance-based metric to assign a focus measure as basis for volume rendering. The algorithm is applied to simulated geometries and opaque soft matter specimens thus enabling 3D visualization. These studies with z-resolution of few 100. nm serve as important step towards the vision of a confocal transmission x-ray microscope. © 2014 Elsevier B.},
author = {Späth, Andreas and Schöll, Simon and Riess, Christian and Schmidtel, Daniel and Paradossi, Gaio and Raabe, Jörg and Hornegger, Joachim and Fink, Rainer},
doi = {10.1016/j.ultramic.2014.04.004},
faupublication = {yes},
journal = {Ultramicroscopy},
pages = {19-25},
peerreviewed = {Yes},
title = {{STXM} goes {3D}: {Digital} reconstruction of focal stacks as novel approach towards confocal soft x-ray microscopy},
volume = {144},
year = {2014}
}
@inproceedings{faucris.117319224,
author = {Voigt, Ingmar and et al.},
author_hint = {Stiver Kevin, Calleja Anna, Ionasec Razvan, Voigt Ingmar, Thavendiranathan Paaladinesh, Liu Shizhen, Houle Helene, De Michelis Nathalie, Ryan Thomas, Vannan Mani},
booktitle = {American College of Cardiology Annual Scientific Session & Expo},
editor = {American College of Cardiology},
faupublication = {no},
pages = {nn},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Superior} {Reproducibility} of {Automated} 3-{D} {Surgical} {Anatomy} of {Normal} and {Abnormal} {Mitral} {Valve} when {Compared} to a {Manual} {Approach}},
venue = {New Orleans},
year = {2011}
}
@inproceedings{faucris.118879464,
abstract = {The acquisition of high-resolution retinal fundus images with a large field of view (FOV) is challenging due to technological, physiological and economic reasons. This paper proposes a fully automatic framework to reconstruct retinal images of high spatial resolution and increased FOV from multiple low-resolution images captured with non-mydriatic, mobile and video-capable but low-cost cameras. Within the scope of one examination, we scan different regions on the retina by exploiting eye motion conducted by a patient guidance. Appropriate views for our mosaicing method are selected based on optic disk tracking to trace eye movements. For each view, one super-resolved image is reconstructed by fusion of multiple video frames. Finally, all super-resolved views are registered to a common reference using a novel polynomial registration scheme and combined by means of image mosaicing. We evaluated our framework for a mobile and low-cost video fundus camera. In our experiments, we reconstructed retinal images of up to 30° FOV from 10 complementary views of 15° FOV. An evaluation of the mosaics by human experts as well as a quantitative comparison to conventional color fundus images encourage the clinical usability of our framework.},
author = {Köhler, Thomas and Heinrich, Axel and Maier, Andreas and Hornegger, Joachim and Tornow, Ralf-Peter},
booktitle = {2016 IEEE 13th International Symposium on Biomedical Imaging},
date = {2016-04-13/2016-04-16},
doi = {10.1109/ISBI.2016.7493449},
faupublication = {yes},
isbn = {9781479923502},
keywords = {eye tracking; fundus video imaging; mosaicing; Retinal imaging; super-resolution},
note = {UnivIS-Import:2017-11-07:Pub.2016.tech.IMMD.IMMD5.superr{\_}1},
pages = {1063-1067},
peerreviewed = {unknown},
publisher = {IEEE Computer Society},
title = {{Super}-{Resolved} {Retinal} {Image} {Mosaicing}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Kohler16-SRI.pdf},
venue = {Prague, Czech Republic},
volume = {2016-June},
year = {2016}
}
@inproceedings{faucris.120328824,
address = {München},
author = {Höller, Kurt Emmerich and Penne, Jochen and Schneider, Armin and Jahn, Jasper and Girgis, Hani and Guttierrez, Javier and Wittenberg, Thomas and Feußner, Hubertus and Hornegger, Joachim},
booktitle = {Proceedings of the 5th Russian-Bavarian Conference on Biomedical Engineering},
date = {2009-07-01/2009-07-04},
editor = {Feussner Hubertus, et al.},
faupublication = {yes},
pages = {43-47},
peerreviewed = {unknown},
publisher = {TUM},
title = {{Suppression} of shock based errors with gravity related endoscopic image rectification},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Hoeller09-SOS.pdf},
venue = {München},
year = {2009}
}
@inproceedings{faucris.108071304,
address = {Berlin},
author = {Müller, Kerstin and Schaller, Christian and Penne, Jochen and Hornegger, Joachim},
booktitle = {Bildverarbeitung für die Medizin 2009},
date = {2009-03-22/2009-03-25},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin, Handels Heinz, Tolxdorff Thomas},
faupublication = {yes},
pages = {257-261},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Surface}-based {Respiratory} {Motion} {Classification} and {Verification}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Mueller09-SBR.pdf},
venue = {Heidelberg},
year = {2009}
}
@inproceedings{faucris.203850575,
author = {Bier, Bastian and Unberath, Mathias and Ravikumar, Nishant and Maier, Jennifer and Gooya, Ali and Taylor, Zeike A. and Frangi, Alejandro F. and Gold, Garry and Fahrig, Rebecca and Maier, Andreas},
booktitle = {2017 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC)},
date = {2017-10-21/2017-10-28},
faupublication = {yes},
note = {UnivIS-Import:2018-09-11:Pub.2017.tech.IMMD.IMMD5.surfac},
peerreviewed = {unknown},
title = {{Surface} {Registration} to {Estimate} {Motion} in {CBCT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Bier17-SRT.pdf},
venue = {Atlanta},
year = {2017}
}
@article{faucris.119545184,
author = {Hornegger, Joachim and Paulus, Dietrich},
faupublication = {yes},
journal = {Pattern Recognition and Image Analysis},
pages = {328-332},
peerreviewed = {unknown},
title = {{Surface} segmentation and classification of 3d shapes using dynamic programming},
volume = {3.0},
year = {1993}
}
@inproceedings{faucris.241865262,
abstract = {To solve the task of surgical mask detection from audio recordings in
the scope of Interspeech’s ComParE challenge, we introduce a phonetic
recognizer which is able to differentiate between clear and mask
samples.
A deep recurrent phoneme recognition model is first trained on
spectrograms from a German corpus to learn the spectral properties of
different speech sounds. Under the assumption that each phoneme sounds
differently among clear and mask speech, the model is then used to
compute frame-wise phonetic labels for the challenge data, including
information about the presence of a surgical mask. These labels served
to train a second phoneme recognition model which is finally able to
differentiate between mask and clear phoneme productions. For a single
utterance, we can compute a functional representation and learn a random
forest classifier to detect whether a speech sample was
produced with or without a mask.
Our method performed better than the baseline methods on both validation
and test set. Furthermore, we could show how wearing a mask influences
the speech signal. Certain phoneme groups were clearly affected by the
obstruction in front of the vocal tract, while others remained almost
unaffected.
0.8). The two scenarios with muscle groups yielded the best results along the experiments (AUC>0.85). The best classification results are found with the suprahyoid and masseter muscles, in water and saliva intake. As the main result of the study, we proposed a set of sEMG related biomarkers and classification approaches suitable for automatic dysphagia screening, a step forward in the implementation of non-invasive and objective strategies for swallowing evaluation.},
author = {Roldan-Vasco, Sebastian and Orozco-Duque, Andres and Orozco Arroyave, Juan Rafael},
doi = {10.1016/j.dsp.2022.103815},
faupublication = {yes},
journal = {Digital Signal Processing},
keywords = {Dysphagia; Feature selection; Machine learning; sEMG; Signal processing},
note = {CRIS-Team Scopus Importer:2022-12-02},
peerreviewed = {Yes},
title = {{Swallowing} disorders analysis using surface {EMG} biomarkers and classification models},
volume = {133},
year = {2023}
}
@article{faucris.121437404,
author = {Ahsen, Osman and Tao, Yuankai Kenny and Potsaid, Benjamin and Sheikine, Yuri and Jiang, James and Grulkowski, Ireneusz and Tsai, Tsung-Han and Jayaraman, Vijaysekhar and Kraus, Martin and Connolly, James L. and Hornegger, Joachim and Cable, Alex E. and Fujimoto, James G.},
doi = {10.1364/OE.21.018021},
faupublication = {yes},
journal = {Optics Express},
pages = {18021-18033},
peerreviewed = {Yes},
title = {{Swept} source optical coherence microscopy using a 1310 nm {VCSEL} light source},
volume = {21.0},
year = {2013}
}
@article{faucris.108885304,
author = {Unberath, Mathias and Taubmann, Oliver and Hell, Michaela and Achenbach, Stephan and Maier, Andreas},
doi = {10.1002/mp.12512},
faupublication = {yes},
journal = {Medical Physics},
keywords = {angiography; cone-beam CT; postprocessing; spanning trees},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.symmet},
pages = {5672-5685},
peerreviewed = {Yes},
title = {{Symmetry}, {Outliers}, and {Geodesics} in {Coronary} {Artery} {Centerline} {Reconstruction} from {Rotational} {Angiography}},
volume = {44},
year = {2017}
}
@article{faucris.224001442,
abstract = {Purpose: For a perfectly plane symmetric object, we can find two views—mirrored at the plane of symmetry—that will yield the exact same image of that object. In consequence, having one image of a plane symmetric object and a calibrated camera, we automatically have a second, virtual image of that object if the 3-D location of the symmetry plane is known. Methods: We propose a method for estimating the symmetry plane from a set of projection images as the solution of a consistency maximization based on epipolar consistency. With the known symmetry plane, we can exploit symmetry to estimate in-plane motion by introducing the X-trajectory that can be acquired with a conventional short-scan trajectory by simply tilting the acquisition plane relative to the plane of symmetry. Results: We inspect the symmetry plane estimation on a real scan of an anthropomorphic human head phantom and show the robustness using a synthetic dataset. Further, we demonstrate the advantage of the proposed method for estimating in-plane motion using the acquired projection data. Conclusion: Symmetry breakers in the human body are widely used for the detection of tumors or strokes. We provide a fast estimation of the symmetry plane, robust to outliers, by computing it directly from a set of projections. Further, by coupling the symmetry prior with epipolar consistency, we overcome inherent limitations in the estimation of in-plane motion.},
author = {Preuhs, Alexander and Maier, Andreas and Manhart, Michael and Kowarschik, Markus and Hoppe, Elisabeth and Fotouhi, Javad and Navab, Nassir and Unberath, Mathias},
doi = {10.1007/s11548-019-02027-8},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Cone-beam CT; Consistency conditions; Data completeness; Motion compensation; Symmetry; Tomographic reconstruction},
note = {CRIS-Team Scopus Importer:2019-08-06},
peerreviewed = {Yes},
title = {{Symmetry} prior for epipolar consistency},
year = {2019}
}
@inproceedings{faucris.108899604,
abstract = {In automatic speech understanding, the division of continuously running speech into syntactic chunks is a great problem. Syntactic boundaries are often marked by prosodic means. For the training of statistic models for prosodic boundaries large data-bases are necessary. For the German VERBMOBIL project (automatic speech-to-speech translation), we developed a syntactic-prosodic labeling scheme where two main types of boundaries (major syntactic boundaries and syntactically ambiguous boundaries) and some other special boundaries are labeled for a large VERBMOBIL spontaneous speech corpus. We compare the results of classifiers (multilayer perceptrons and language models) trained on these syntactic-prosodic boundary labels with classifiers trained on perceptual-prosodic and pure syntactic labels. The main advantage of the rough syntactic-prosodic labels presented in this paper is that large amounts of data could be labeled within a short time. Therefore, the classifiers trained with these labels turned out to be superior (recognition rates of up to 96%).},
address = {-},
author = {Batliner, Anton and Kompe, Ralf and KIESSLING, Andreas and Niemann, Heinrich and Nöth, Elmar},
booktitle = {Proc. Int. Conf. on Spoken Language Processing},
date = {1996-10-03/1996-10-06},
editor = {ICSLP},
faupublication = {yes},
month = {Jan},
pages = {1720-1723},
peerreviewed = {unknown},
publisher = {-},
title = {{Syntactic}-prosodic labeling of large spontaneous speech data-bases},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1996/Batliner96-SLO.pdf},
venue = {Philadelphia, PA},
year = {1996}
}
@article{faucris.258185772,
abstract = {Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health. To allow for proper risk assessment, a precise and statistically relevant analysis of particle characteristics (such as size, shape, and composition) is required that would greatly benefit from automated image analysis procedures. While deep learning shows impressive results in object detection tasks, its applicability is limited by the amount of representative, experimentally collected and manually annotated training data. Here, an elegant, flexible, and versatile method to bypass this costly and tedious data acquisition process is presented. It shows that using a rendering software allows to generate realistic, synthetic training data to train a state-of-the art deep neural network. Using this approach, a segmentation accuracy can be derived that is comparable to man-made annotations for toxicologically relevant metal-oxide nanoparticle ensembles which were chosen as examples. The presented study paves the way toward the use of deep learning for automated, high-throughput particle detection in a variety of imaging techniques such as in microscopies and spectroscopies, for a wide range of applications, including the detection of micro- and nanoplastic particles in water and tissue samples.},
author = {Mill, Leonid and Wolff, David and Gerrits, Nele and Philipp, Patrick and Kling, Lasse and Vollnhals, Florian and Ignatenko, Andrew and Jaremenko, Christian and Huang, Yixing and De Castro, Olivier and Audinot, Jean Nicolas and Nelissen, Inge and Wirtz, Tom and Maier, Andreas and Christiansen, Silke},
doi = {10.1002/smtd.202100223},
faupublication = {yes},
journal = {Small Methods},
keywords = {helium ion microscopy; image analysis; machine learning; nanoparticles; segmentation; toxicology},
note = {CRIS-Team Scopus Importer:2021-05-14},
peerreviewed = {Yes},
title = {{Synthetic} {Image} {Rendering} {Solves} {Annotation} {Problem} in {Deep} {Learning} {Nanoparticle} {Segmentation}},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/smtd.202100223},
year = {2021}
}
@article{faucris.223524682,
abstract = {Background
Motor impairment appears as a characteristic symptom of several diseases and injuries. Therefore, tests for analyzing motor dysfunction are widely applied across preclinical models and disease stages. Among those, gait analysis tests are commonly used, but they generate a huge number of gait parameters. Thus, complications in data analysis and reporting raise, which often leads to premature parameter selection.
New methods
In order to avoid arbitrary parameter selection, we present here a systematic initial data analysis by utilizing heat-maps for data reporting. We exemplified this approach within an intervention study, as well as applied it to two longitudinal studies in rodent models related to Parkinson’s disease (PD) and Huntington disease (HD).
Results
The systematic initial data analysis (IDA) is feasible for exploring gait parameters, both in experimental and longitudinal studies. The resulting heat maps provided a visualization of gait parameters within a single chart, highlighting important clusters of differences.
Comparison with existing method
Often, premature parameter selection is practiced, lacking comprehensiveness. Researchers often use multiple separated graphs on distinct gait parameters for reporting. Additionally, negative results are often not reported.
Conclusions
Heat mapping utilized in initial data analysis is advantageous for reporting clustered gait parameter differences in one single chart and improves data mining.
},
author = {Timotius, Ivanna and Canneva, Fabio and Minakaki, Georgia and Moceri, Sandra and Plank, Anne-Christine and Casadei, Nicolas and Riess, Olaf and Winkler, Jürgen and Klucken, Jochen and Eskofier, Björn and von Hörsten, Stephan},
doi = {10.1016/j.jneumeth.2019.108367},
faupublication = {yes},
journal = {Journal of Neuroscience Methods},
keywords = {Gait analysis; CatWalk system; Heat map; Parkinson’s disease; Huntington disease; Rodent models},
peerreviewed = {Yes},
title = {{Systematic} data analysis and data mining in {CatWalk} gait analysis by heat mapping exemplified in rodent models for neurodegenerative diseases},
url = {https://www.sciencedirect.com/science/article/pii/S0165027019302249},
volume = {326},
year = {2019}
}
@incollection{faucris.203741180,
address = {Cham},
author = {Fischer, Peter and Sembritzki, Klaus and Maier, Andreas},
booktitle = {Medical Imaging Systems: An Introductory Guide},
doi = {10.1007/978-3-319-96520-8{\_}2},
faupublication = {yes},
isbn = {978-3-319-96519-2},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.system},
pages = {13-36},
peerreviewed = {unknown},
publisher = {Springer},
series = {Lecture Notes in Computer Science (LNCS)},
title = {{System} {Theory}},
volume = {11111},
year = {2018}
}
@inproceedings{faucris.113211824,
address = {Moscow},
author = {Höller, Kurt Emmerich and Petrunina, Maria and Penne, Jochen and Schneider, Armin and Wilhelm, Dirk and Feußner, Hubertus and Hornegger, Joachim},
booktitle = {Proceedings of the 4th Russian-Bavarian Conference on Biomedical Engineering},
date = {2008-07-08/2008-07-09},
editor = {Bauernschmitt Robert, Chaplygin Yuri, Feußner Hubertus, Gulyaev Yuri, Hornegger Joachim, Mayr Ernst, Navab Nassir, Schookin Sergey, Selishchev Sergey, Umnyashkin Sergei},
faupublication = {yes},
pages = {33-37},
peerreviewed = {unknown},
publisher = {MIET},
title = {{Taking} endoscopy to a higher dimension: {Computer} {Aided} 3-{D} {NOTES}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Hoeller08-TET.pdf},
venue = {Moscow},
year = {2008}
}
@article{faucris.203205862,
author = {Käppler, Sebastian and Seifert, Maria and Horn, Florian and Pelzer, Georg and Rieger, Jens and Michel, Thilo and Maier, Andreas and Anton, Gisela and Riess, Christian},
doi = {10.1002/mp.12200},
faupublication = {yes},
journal = {Medical Physics},
keywords = {grating interferometer; reference image; phase-contrast; x-ray imaging},
pages = {1886-1898},
peerreviewed = {Yes},
title = {{Talbot}-{Lau} {X}-ray phase contrast for tiling-based acquisitions without reference scanning},
volume = {44},
year = {2017}
}
@article{faucris.214898637,
abstract = {Compared to conventional attenuation x-ray radiographic imaging, the x-ray Talbot-Lau technique provides further information about the scattering and the refractive properties of the object in the beam path. Hence, this additional information should improve the diagnostic process concerning medical applications and non-destructive testing. Nevertheless, until now, due to grating fabrication process, Talbot-Lau imaging suffers from small grating sizes (70 mm diameter). This leads to long acquisition times for imaging large objects. Stitching the gratings is one solution. Another one consists of scanning Talbot-Lau setups. In this publication, we present a compact and very fast scanning setup which enables imaging of large samples. With this setup a maximal scanning velocity of 71.7 mm/s is possible. A resolution of 4.1 lines/mm can be achieved. No complex alignment procedures are necessary while the field of view comprises 17.5 x 150 cm2. An improved reconstruction algorithm concerning the scanning approach, which increases robustness with respect to mechanical instabilities, has been developed and is presented. The resolution of the setup in dependence of the scanning velocity is evaluated. The setup imaging qualities are demonstrated using a human knee ex-vivo as an example for a high absorbing human sample.},
author = {Seifert, Maria and Ludwig, Veronika and Käppler, Sebastian and Horn, Florian and Meyer, Pascal and Pelzer, Georg and Rieger, Jens and Sand, Daniel and Michel, Thilo and Mohr, Juergen and Riess, Christian and Anton, Gisela},
doi = {10.1038/s41598-018-38030-3},
faupublication = {yes},
journal = {Scientific Reports},
note = {CRIS-Team WoS Importer:2019-03-29},
peerreviewed = {Yes},
title = {{Talbot}-{Lau} x-ray phase-contrast setup for fast scanning of large samples},
volume = {9},
year = {2019}
}
@inproceedings{faucris.120895984,
abstract = {
Classification performance for emotional user states found in the few realistic, spontaneous databases available is as yet not very high. We present a database with emotional children’s speech in a human-robot scenario. Baseline classification performance for seven classes is 44.5%, for four classes 59.2%. We discuss possible strategies for tuning, e.g., using only prototypes (based on annotation correspondence or classification scores), or taking into account requirements and feasibility in possible applications (weighting of false alarms or speaker-specific overall frequencies).
},
address = {Bonn},
author = {Batliner, Anton and Steidl, Stefan and Hacker, Christian and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Proceedings of the 9th European Conference on Speech Communication and Technology},
date = {2005-09-04/2005-09-08},
editor = {ISCA},
faupublication = {yes},
pages = {489-492},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{Tales} of {Tuning} - {Prototyping} for {Automatic} {Classification} of {Emotional} {User} {States}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Batliner05-TOT.pdf},
venue = {Lisbon},
year = {2005}
}
@article{faucris.108063824,
abstract = {In this article, we focus on keyword detection in children's speech as it is needed in voice command systems. We use the FAU Aibo Emotion Corpus which contains emotionally colored spontaneous children's speech recorded in a child-robot interaction scenario and investigate various recent key-word spotting techniques. As the principle of bidirectional Long Short-Term Memory (BLSTM) is known to be well-suited for context-sensitive phoneme prediction, we incorporate a BLSTM network into a Tandem model for exible coarticulation modeling in children's speech. Our experiments reveal that the Tandem model prevails over a triphone-based Hidden Markov Model approach.},
author = {Wöllmer, Martin and Schuller, Björn and Batliner, Anton and Steidl, Stefan and Seppi, Dino},
doi = {10.1145/1998384.1998386},
faupublication = {yes},
journal = {ACM Transactions on Speech and Language Processing},
keywords = {children's speech; dynamic Bayesian networks; keyword spotting; long short-term memory},
peerreviewed = {Yes},
title = {{Tandem} decoding of children's speech for keyword detection in a child-robot interaction scenario},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Woellmer11-TDO.pdf},
volume = {7},
year = {2011}
}
@article{faucris.121198044,
abstract = {Introduction: The use of self-expandable microstents for treatment of broad-based intracranial aneurysms is widely spread. However, poor fluoroscopic visibility of the stents remains disadvantageous during the coiling procedure. Flat detector angiographic computed tomography (ACT) provides high resolution imaging of microstents even though integration of this imaging modality in the neurointerventional workflow has not been widely reported. Methods: An acrylic glass model was used to simulate the situation of a broad-based sidewall aneurysm. After insertion of a self-expandable microstent, ACT was performed. The resulting 3D dataset of the Microstent was subsequently projected into a conventional 2D fluoroscopic roadmap. This 3D visualization of the stent supported the coil embolization procedure of the in vitro aneurysm. Results: In vitro 2D-3D coregistration with integration of 3D ACT data of a self-expandable microstent in a conventional 2D roadmap is feasible. Conclusions: Unsatisfying stent visibility constrains clinical cases with complex parent vessel anatomy and challenging aneurysm geometry; hence, this technique potentially may be useful in such cases. In our opinion, the clinical feasibility and utility of this new technique should be verified in a clinical aneurysm embolization study series using 2D-3D coregistration. © 2009 Springer-Verlag.},
author = {Richter, Gregor and Pfister, Marcus and Struffert, Tobias and Engelhorn, Tobias and Dölken, Marc and Spiegel, Martin and Hornegger, Joachim and Dörfler, Arnd},
doi = {10.1007/s00234-009-0591-y},
faupublication = {yes},
journal = {Neuroradiology},
pages = {851-854},
peerreviewed = {Yes},
title = {{Technical} feasibility of {2D}-{3D} coregistration for visualization of self-expandable microstents to facilitate coil embolization of broad-based intracranial aneurysms: {An} in vitro study},
volume = {51},
year = {2009}
}
@article{faucris.228162295,
abstract = {Purpose: Recently, several attempts were conducted to transfer deep learning to medical image reconstruction. An increasingly number of publications follow the concept of embedding the computed tomography (CT) reconstruction as a known operator into a neural network. However, most of the approaches presented lack an efficient CT reconstruction framework fully integrated into deep learning environments. As a result, many approaches use workarounds for mathematically unambiguously solvable problems. Methods: PYRO-NN is a generalized framework to embed known operators into the prevalent deep learning framework Tensorflow. The current status includes state-of-the-art parallel-, fan-, and cone-beam projectors, and back-projectors accelerated with CUDA provided as Tensorflow layers. On top, the framework provides a high-level Python API to conduct FBP and iterative reconstruction experiments with data from real CT systems. Results: The framework provides all necessary algorithms and tools to design end-to-end neural network pipelines with integrated CT reconstruction algorithms. The high-level Python API allows a simple use of the layers as known from Tensorflow. All algorithms and tools are referenced to a scientific publication and are compared to existing non-deep learning reconstruction frameworks. To demonstrate the capabilities of the layers, the framework comes with baseline experiments, which are described in the supplementary material. The framework is available as open-source software under the Apache 2.0 licence at https://github.com/csyben/PYRO-NN. Conclusions: PYRO-NN comes with the prevalent deep learning framework Tensorflow and allows to setup end-to-end trainable neural networks in the medical image reconstruction context. We believe that the framework will be a step toward reproducible research and give the medical physics community a toolkit to elevate medical image reconstruction with new deep learning techniques.},
author = {Syben-Leisner, Christopher and Michen, Markus and Stimpel, Bernhard and Seitz, Stephan and Ploner, Stefan and Maier, Andreas},
doi = {10.1002/mp.13753},
faupublication = {yes},
journal = {Medical Physics},
keywords = {inverse problems; known operator learning; machine learning; open source; reconstruction},
note = {CRIS-Team Scopus Importer:2019-10-22},
pages = {5110-5115},
peerreviewed = {Yes},
title = {{Technical} {Note}: {PYRO}-{NN}: {Python} reconstruction operators in neural networks},
url = {https://aapm.onlinelibrary.wiley.com/doi/abs/10.1002/mp.13753},
volume = {46},
year = {2019}
}
@article{faucris.111754764,
abstract = {Purpose: Fast 3D cone beam reconstruction is mandatory for many clinical workflows. For that reason, researchers and industry work hard on hardware-optimized 3D reconstruction. Backprojection is a major component of many reconstruction algorithms that require a projection of each voxel onto the projection data, including data interpolation, before updating the voxel value. This step is the bottleneck of most reconstruction algorithms and the focus of optimization in recent publications. A crucial limitation, however, of these publications is that the presented results are not comparable to each other. This is mainly due to variations in data acquisitions, preprocessing, and chosen geometries and the lack of a common publicly available test dataset. The authors provide such a standardized dataset that allows for substantial comparison of hardware accelerated backprojection methods. Methods: They developed an open platform RabbitCT (www.rabbitCT.com) for worldwide comparison in backprojection performance and ranking on different architectures using a specific high resolution C-arm CT dataset of a rabbit. This includes a sophisticated benchmark interface, a prototype implementation in C++, and image quality measures. Results: At the time of writing, six backprojection implementations are already listed on the website. Optimizations include multithreading using Intel threading building blocks and OpenMP, vectorization using SSE, and computation on the GPU using CUDA 2.0. Conclusions: There is a need for objectively comparing backprojection implementations for reconstruction algorithms. RabbitCT aims to provide a solution to this problem by offering an open platform with fair chances for all participants. The authors are looking forward to a growing community and await feedback regarding future evaluations of novel software- and hardware-based acceleration schemes. © 2009 American Association of Physicists in Medicine.},
author = {Rohkohl, Christopher and Keck, Benjamin and Hofmann, Hannes and Hornegger, Joachim},
doi = {10.1118/1.3180956},
faupublication = {yes},
journal = {Medical Physics},
pages = {3940-3944},
peerreviewed = {Yes},
title = {{Technical} {Note}: {RabbitCT}-an open platform for benchmarking {3D} cone-beam reconstruction algorithms},
volume = {36},
year = {2009}
}
@article{faucris.121398464,
author = {Ritt, Philipp and Hornegger, Joachim and Kuwert, Torsten},
doi = {10.1055/s-0031-1271624},
faupublication = {yes},
journal = {Der Nuklearmediziner},
pages = {09-20},
peerreviewed = {No},
title = {{Technik} und physikalische {Aspekte} der {SPECT} / {CT}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Ritt11-TUP.pdf},
volume = {34.0},
year = {2011}
}
@article{faucris.108170524,
abstract = {
A continuous increase of the anticipated average life is expected in the near future. We have to deal with the consequences of aging, such as loneliness in an environment characterized by technology or the need to help elderly people. Technical solutions are required that solve the occurring problems associated with aging and are accepted and used. This work faces the challenge of improving the early detection of diseases like dementia, using an intelligent dialogue system that improves the chance for integrating applications of telemedicine in an intelligent home environment.
},
author = {Soutschek, Stefan and Spiegl, Werner and Steidl, Stefan and Hornegger, Joachim and Erzigkeit, Hellmut and Kornhuber, Johannes},
faupublication = {yes},
journal = {Künstliche Intelligenz},
pages = {49-54},
peerreviewed = {Yes},
title = {{Technology} {Integration} in the {Daily} {Activities} of the {Elderly}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Soutschek08-TII.pdf},
volume = {2008},
year = {2008}
}
@inproceedings{faucris.221674581,
abstract = {In this contribution we look back on the last years in the history of
telephone-based speech dialog systems. We will start in 1993 when the
world wide first natural language understanding dialog system using a
mixed-initiative approach was made accessible for the public, the
well-known EVAR system from the Chair for Pattern Recognition of the
University of Erlangen-Nuremberg. Then we discuss certain requirements
we consider necessary for the successful application of dialog systems.
Finally we present trends and developments in the area of
telephone-based dialog system},
address = {Berlin, Heidelberg},
author = {Haas, Jürgen and Gallwitz, Florian and Horndasch, Axel and Huber, Richard and Warnke, Volker},
booktitle = {Pattern Recognition},
date = {2005-08-31/2005-09-02},
doi = {10.1007/11550518{\_}16},
editor = {Kropatsch W.G.; Hanbury A.; Sablating R.},
faupublication = {yes},
isbn = {978-3-540-28703-2},
keywords = {Telephone-based speech dialog systems, mixed-initiative dialog systems, natural language understanding, EVAR},
pages = {125-132},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Telephone}-based speech dialog systems},
venue = {Vienna},
volume = {3663},
year = {2005}
}
@inproceedings{faucris.121481404,
address = {-},
author = {Batliner, Anton and Kießling, Andreas and Kompe, Ralf and Niemann, Heinrich and Nöth, Elmar},
booktitle = {Proc. European Conf. on Speech Communication and Technology},
date = {1997-09-22/1997-09-25},
editor = {Eurospeech},
faupublication = {yes},
pages = {763-766},
publisher = {-},
title = {{Tempo} and its {Change} in {Spontaneous} {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1997/Batliner97-TAI.pdf},
venue = {Rhodes},
year = {1997}
}
@article{faucris.240537442,
abstract = {This study proposes a method for the temporal and spatial determination of the onset of local necking determined by means of a Nakajima test set-up for a DC04 deep drawing and a DP800 dual-phase steel, as well as an AA6014 aluminum alloy. Furthermore, the focus lies on the observation of the progress of the necking area and its transformation throughout the remainder of the forming process. The strain behavior is learned by a machine learning approach on the basis of the images when the process is close to material failure. These learned failure characteristics are transferred to new forming sequences, so that critical areas indicating material failure can be identified at an early stage, and consequently enable the determination of the beginning of necking and the analysis of the necking area. This improves understanding of the necking behavior and facilitates the determination of the evaluation area for strain paths. The growth behavior and traceability of the necking area is objectified by the proposed weakly supervised machine learning approach, thereby rendering a heuristic-based determination unnecessary. Furthermore, a simultaneous evaluation on image and pixel scale is provided that enables a distinct selection of the failure quantile of the probabilistic forming limit curve.},
author = {Jaremenko, Christian and Affronti, Emanuela and Merklein, Marion and Maier, Andreas},
doi = {10.3390/ma13112427},
faupublication = {yes},
journal = {Materials},
keywords = {Artificial intelligence; Classification; Deep learning; Forming limit curve; Machine learning; Pattern recognition; Segmentation; Sheet metal forming},
note = {CRIS-Team Scopus Importer:2020-07-17},
peerreviewed = {Yes},
title = {{Temporal} and spatial detection of the onset of local necking and assessment of its growth behavior},
volume = {13},
year = {2020}
}
@article{faucris.203841957,
abstract = {This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show different noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the other hand has a lower resolution and shows high-frequency noise. For the purpose of denoising, we propose a variational framework based on the QuaSI prior and a Huber data fidelity model that can handle 3-D and 3-D+t data. Efficient optimization is facilitated through the use of an alternating direction method of multipliers (ADMM) scheme and the linearization of the quantile filter. Experiments on multiple datasets emphasize the excellent performance of the proposed method.
In this chapter, we focus on the automatic recognition of emotional states using acoustic and linguistic parameters as features, and classifiers as tools to predict the ‘correct’ emotional states. We first sketch history and state-of-the art in this field; then we describe the process of ‘corpus engineering’, i.e. the design and recording of databases, the annotation of emotional states, and further processing such as manual or automatic segmentation. Next we present an overview of acoustic and linguistic features that are extracted automatically or manually. In the section on classifiers, we deal with topics such as the curse of dimensionality and the sparse data problem, classifiers, and evaluation. At the end of each section, we point out important aspects that should be taken into account for the planning or the assessment of studies. The subject area of this chapter is not emotions in some narrow sense but in a wider sense encompassing emotion-related states such as moods, attitudes, or interpersonal stances as well. We do not aim at an in-depth treatise of some specific aspects or algorithms but at an overview of approaches and strategies that have been used or should be used.
},
author = {Batliner, Anton and Schuller, Björn and Seppi, Dino and Steidl, Stefan and Devillers, Laurence and Vidrascu, Laurence and Vogt, Thurid and Aharonson, Vered and Amir, Noam},
booktitle = {Emotion-Oriented Systems – The HUMAINE Handbook},
doi = {10.1007/978-3-642-15184-2},
editor = {Petta Paolo, Pelachaud Catherine, and Cowie Roddy},
faupublication = {yes},
isbn = {978-3642151835},
month = {Jan},
pages = {71-99},
peerreviewed = {No},
publisher = {Springer},
title = {{The} {Automatic} {Recognition} of {Emotions} in {Speech}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Batliner11-TAR.pdf},
year = {2011}
}
@misc{faucris.109848244,
author = {Haderlein, Tino and Nöth, Elmar},
faupublication = {yes},
note = {UnivIS-Import:2016-06-30:Pub.2003.tech.IMMD.IMMD5.theemb},
peerreviewed = {automatic},
title = {{The} {EMBASSI} {Speech} {Corpus}},
year = {2003}
}
@inproceedings{faucris.109249404,
address = {Berlin},
author = {Wilke, Peter and Ostler, Johannes},
booktitle = {Proc. PATAT 2010},
date = {2010-08-10/2010-08-13},
editor = {Burke},
faupublication = {yes},
pages = {1.0},
publisher = {Springer},
title = {{The} {Erlangen} {Advanced} {Time} {Tabling} {System} ({EATTS}) {Unified} {XML} {File} {Format} for the {Specification} of {Time} {Tabling} {Systems}},
venue = {Belfast},
year = {2010}
}
@inproceedings{faucris.109316724,
address = {Berlin},
author = {Wilke, Peter and Ostler, Johannes and Merdenoglu, Kerim and Kremer, Eugen and Killer, Helmut},
booktitle = {Proc. PATAT 2010},
date = {2010-08-10/2010-08-13},
editor = {Burke Edmund},
faupublication = {yes},
pages = {1.0},
peerreviewed = {unknown},
publisher = {Springer},
title = {{The} {Erlangen} {Advanced} {Time} {Tabling} {System} ({EATTS}) version 5},
venue = {Belfast},
year = {2010}
}
@inproceedings{faucris.118076464,
abstract = {We present a new concept as well as the implementation of an FPGA-based reconfigurable platform, the Erlangen Slot Machine (ESM). The main advantages of this platform are: first, the possibility for each module to access its peripheries independent from its location through a programmable crossbar, and distributed SRAMs among slices. This allows an unrestricted relocation of modules on the device. Second, the intermodule structure allows an unlimited communication among running modules. © 2005 IEEE.},
author = {Ahmadinia, Ali and Bobda, Christophe and Fekete, Sandor P. and Haller, Thomas and Linarth, Andre Guilherme and Majer, Mateusz and Teich, Jürgen and Van Der Veen, Jan C.},
booktitle = {Proceedings of the 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'05)},
date = {2005-04-18/2005-04-20},
doi = {10.1109/FCCM.2005.63},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2005.tech.IMMD.inform.theerl},
pages = {319-320},
title = {{The} {Erlangen} {Slot} {Machine}: {A} {Highly} {Flexible} {FPGA}-{Based} {Reconfigurable} {Platform}},
venue = {Marriott at Napa Valley, California},
year = {2005}
}
@incollection{faucris.107901244,
address = {Berlin},
author = {Frank, Carmen Manuela and Adelhardt, Johann and Batliner, Anton and Nöth, Elmar and Shi, Rui Ping and Zeißler, Viktor and Niemann, Heinrich},
booktitle = {SmartKom: Foundations of Multimodal Dialogue Systems},
faupublication = {yes},
pages = {167-180},
peerreviewed = {Yes},
publisher = {Springer},
title = {{The} {Facial} {Expression} {Module}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Frank06-TFE.pdf},
volume = {1.0},
year = {2006}
}
@inproceedings{faucris.122149324,
abstract = {A growing number of universities and other educational institutions provide recordings of lectures and seminars as an additional resource to the students. In contrast to educational films that are scripted, directed and often shot by film professionals, these plain recordings are typically not post-processed in an editorial sense. Thus, the videos often contain longer periods of inactivity or silence, unnecessary repetitions, or corrections of prior mistakes. This paper describes the FAU Video Lecture Browser system, a web-based platform for the interactive assessment of video lectures, that helps to close the gap between a plain recording and a useful e-learning resource by displaying automatically extracted and ranked key phrases on an augmented time line based on stream graphs. In a pilot study, users of the interface were able to complete a topic localization task about 29% faster than users provided with the video only while achieving about the same accuracy. The user interactions can be logged on the server to collect data to evaluate the quality of the phrases and rankings, and to train systems that produce customized phrase rankings.},
author = {Riedhammer, Korbinian Thomas and Gropp, Martin and Nöth, Elmar},
faupublication = {yes},
keywords = {automatic speech recognition;key phrase extraction;key phrase ranking;visualization;user interaction},
month = {Jan},
pages = {392-397},
peerreviewed = {unknown},
title = {{THE} {FAU} {VIDEO} {LECTURE} {BROWSER} {SYSTEM}},
year = {2012}
}
@incollection{faucris.121420244,
address = {Berlin},
author = {Shi, Rui Ping and Adelhardt, Johann and Batliner, Anton and Frank, Carmen Manuela and Nöth, Elmar and Zeißler, Viktor and Niemann, Heinrich},
booktitle = {SmartKom: Foundations of Multimodal Dialogue Systems},
faupublication = {yes},
pages = {209-219},
peerreviewed = {Yes},
publisher = {Springer},
title = {{The} {Gesture} {Interpretation} {Module}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Shi06-TGI.pdf},
volume = {1.0},
year = {2006}
}
@inproceedings{faucris.121403744,
abstract = {
We first depict the challenge to address all non-prototypical varieties of emotional states signalled in speech in an open microphone setting, i.e. using all data recorded. In the remainder of the article, we illustrate promising strategies, using the FAU Aibo Emotion Corpus, by showing different degrees of classification performance for different degrees of prototypicality, and by elaborating on the use of ROC curves, classification confidences, and the use of correlation-based analyses.
},
author = {Steidl, Stefan and Schuller, Björn and Batliner, Anton and Seppi, Dino},
booktitle = {Proceedings of ACII 2009},
date = {2009-09-10/2009-09-12},
editor = {IEEE},
faupublication = {yes},
pages = {690-697},
peerreviewed = {Yes},
title = {{The} {Hinterland} of {Emotions}: {Facing} the {Open}-{Microphone} {Challenge}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Steidl09-THO.pdf},
venue = {Amsterdam},
year = {2009}
}
@inproceedings{faucris.108118384,
abstract = {
Traditionally, it has been assumed that pitch is the most important prosodic feature for the marking of prominence, and of other phenomena such as the marking of boundaries or emotions. This role has been put into question by recent studies. As nowadays larger databases are always being processed automatically, it is not clear up to what extent the possibly lower relevance of pitch can be attributed to extraction errors or to other factors. We present some ideas as for a phenomenological difference between pitch and duration, and compare the performance of automatically extracted F0 values and of manually corrected F0 values for the automatic recognition of prominence and emotion in spontaneous speech (children giving commands to a pet robot). The difference in classification performance between corrected and automatically extracted pitch features turns out to be consistent but not very pronounced.
},
author = {Batliner, Anton and Steidl, Stefan and Schuller, Björn and Seppi, Dino and Vogt, Thurid and Devillers, Laurence and Vidrascu, Laurence and Amir, Noam and Kessous, Loic and Aharonson, Vered},
booktitle = {Proceedings of the 16th International Congress of Phonetic Sciences},
date = {2007-08-06/2007-08-10},
editor = {IPA},
faupublication = {yes},
keywords = {pitch; automatic extraction; manual correction; automatic classification},
pages = {2201-2204},
peerreviewed = {Yes},
title = {{The} {Impact} of {F0} {Extraction} {Errors} on the {Classification} of {Prominence} and {Emotion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Batliner07-TIO.pdf},
venue = {Saarbrücken},
year = {2007}
}
@inproceedings{faucris.207564555,
author = {Christlein, Vincent and Riess, Christian and Angelopoulou, Elli and Evangelopoulos, Georgios and Kakadiaris, Ioannis},
booktitle = {Biometric and Surveillance Technology for Human and Activity Identification},
date = {2013-05-02/2013-05-02},
doi = {10.1117/12.2019014},
editor = {SPIE},
faupublication = {yes},
isbn = {9780819495037},
keywords = {Reectance model; Face recognition; Specularity removal; Specular highlights},
pages = {8712-19},
peerreviewed = {Yes},
title = {{The} {Impact} of {Specular} {Highlights} on {3D}-{2D} {Face} {Recognition}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Christlein13-TIO.pdf},
venue = {Baltimore, MD},
volume = {8712},
year = {2013}
}
@inproceedings{faucris.283166137,
abstract = {This paper empirically investigates the influence of different data splits and splitting strategies on the performance of dysfluency detection systems. For this, we perform experiments using wav2vec 2.0 models with a classification head as well as support vector machines (SVM) in conjunction with the features extracted from the wav2vec 2.0 model to detect dysfluencies. We train and evaluate the systems with different non-speaker-exclusive and speaker-exclusive splits of the Stuttering Events in Podcasts (SEP-28k) dataset to shed some light on the variability of results w.r.t. to the partition method used. Furthermore, we show that the SEP-28k dataset is dominated by only a few speakers, making it difficult to evaluate. To remedy this problem, we created SEP-28k-Extended (SEP-28k-E), containing semi-automatically generated speaker and gender information for the SEP-28k corpus, and suggest different data splits, each useful for evaluating other aspects of methods for dysfluency detection.},
author = {Bayerl, Sebastian P. and Wagner, Dominik and Nöth, Elmar and Bocklet, Tobias and Riedhammer, Korbinian},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2022-09-06/2022-09-09},
doi = {10.1007/978-3-031-16270-1{\_}35},
editor = {Petr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala},
faupublication = {yes},
isbn = {9783031162695},
keywords = {dysfluencies; pathological speech; SEP-28k; stuttering},
note = {CRIS-Team Scopus Importer:2022-10-14},
pages = {423-436},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{The} {Influence} of {Dataset} {Partitioning} on {Dysfluency} {Detection} {Systems}},
venue = {Brno},
volume = {13502 LNAI},
year = {2022}
}
@inproceedings{faucris.122789084,
abstract = {
The last decade has seen a substantial body of literature on the recognition of emotion from speech. However, in comparison to related speech processing tasks such as Automatic Speech and Speaker Recognition, practically no standardised corpora and test-conditions exist to compare performances under exactly the same conditions. Instead a multiplicity of evaluation strategies employed – such as cross-validation or percentage splits without proper instance definition – prevents exact reproducibility. Further, in order to face more realistic scenarios, the community is in desperate need of more spontaneous and less prototypical data. This INTERSPEECH 2009 Emotion Challenge aims at bridging such gaps between excellent research on human emotion recognition from speech and low compatibility of results. The FAU Aibo Emotion Corpus serves as basis with clearly defined test and training partitions incorporating speaker independence and different room acoustics as needed in most real-life settings. This paper introduces the challenge, the corpus, the features, and benchmark results of two popular approaches towards emotion recognition from speech.
},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton},
booktitle = {Proceedings of Interspeech 2009},
date = {2009-09-06/2009-09-10},
editor = {ISCA},
faupublication = {yes},
keywords = {emotion; challenge; feature types; classification},
pages = {312-315},
peerreviewed = {Yes},
title = {{The} {INTERSPEECH} 2009 {Emotion} {Challenge}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Schuller09-TI2.pdf},
venue = {Brighton},
year = {2009}
}
@inproceedings{faucris.107868684,
abstract = {
Most paralinguistic analysis tasks are lacking agreed-upon evaluation procedures and comparability, in contrast to more ‘traditional’ disciplines in speech analysis. The INTERSPEECH 2010 Paralinguistic Challenge shall help overcome the usually low compatibility of results, by addressing three selected sub-challenges. In the Age Sub-Challenge, the age of speakers has to be determined in four groups. In the Gender Sub-Challenge, a three-class classification task has to be solved and finally, the Affect Sub-Challenge asks for speakers’ interest in ordinal representation. This paper introduces the conditions, the Challenge corpora “aGender” and “TUM AVIC” and standard feature sets that may be used. Further, baseline results are given.
},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Burkhardt, Felix and Devillers, Laurence and Müller, Christian and Narayanan, Shrikanth},
booktitle = {Proceedings of Interspeech},
date = {2010-09-26/2010-09-30},
editor = {ISCA},
faupublication = {yes},
keywords = {paralinguistic challenge; age; gender; affect},
pages = {2794-2797},
peerreviewed = {Yes},
title = {{The} {INTERSPEECH} 2010 {Paralinguistic} {Challenge} - {Age}, {Gender}, and {Affect}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Schuller10-TI2.pdf},
venue = {Makuhari},
year = {2010}
}
@inproceedings{faucris.113217104,
abstract = {
While the first open comparative challenges in the field of paralinguistics targeted more ‘conventional’ phenomena such as emotion, age, and gender, there still exists a multiplicity of not yet covered, but highly relevant speaker states and traits. The INTERSPEECH 2011 Speaker State Challenge thus addresses two new sub-challenges to overcome the usually low compatibility of results: In the Intoxication Sub-Challenge, alcoholisation of speakers has to be determined in two classes; in the Sleepiness Sub-Challenge, another two-class classification task has to be solved. This paper introduces the conditions, the Challenge corpora “Alcohol Language Corpus” and “Sleepy Language Corpus”, and a standard feature set that may be used. Further, baseline results are given.
},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Schiel, Florian and Krajewski, Jarek},
booktitle = {Proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH 2011)},
date = {2011-08-27/2011-08-31},
editor = {ISCA},
faupublication = {yes},
keywords = {Speaker State Challenge; intoxication; sleepiness},
pages = {3201-3204},
peerreviewed = {Yes},
title = {{The} {INTERSPEECH} 2011 {Speaker} {State} {Challenge}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Schuller11-TI2.pdf},
venue = {Florenz},
year = {2011}
}
@inproceedings{faucris.121340164,
abstract = {
The INTERSPEECH 2012 Speaker Trait Challenge provides for the first time a unified test-bed for ‘perceived’ speaker traits: Personality in the five OCEAN personality dimensions, likability of speakers, and intelligibility of pathologic speakers. In this paper, we describe these three Sub-Challenges, Challenge conditions, baselines, and a new feature set by the openSMILE toolkit, provided to the participants.
},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Nöth, Elmar and Vinciarelli, Alessandro and Burkhardt, Felix and van Son, Rob and Weninger, Felix and Eyben, Florian and Bocklet, Tobias and Mohammadi, Gelareh and Weiss, Benjamin},
booktitle = {Proceedings of the 13th Annual Conference of the International Speech Communication Association (INTERSPEECH 2012)},
date = {2012-09-09/2012-09-13},
editor = {ISCA},
faupublication = {yes},
keywords = {computational paralinguistics; speaker traits; personality; likability; pathology},
pages = {keine Seitenzählung},
peerreviewed = {Yes},
title = {{The} {INTERSPEECH} 2012 {Speaker} {Trait} {Challenge}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Schuller12-TI2.pdf},
venue = {Portland, OR},
year = {2012}
}
@inproceedings{faucris.121460064,
abstract = {
The INTERSPEECH 2013 Computational Paralinguistics Challenge provides for the first time a unified test-bed for Social Signals such as laughter in speech. It further introduces conflict in group discussions as a new task and deals with autism and its manifestations in speech. Finally, emotion is revisited as task, albeit with a broader range of overall twelve enacted emotional states. In this paper, we describe these four Sub-Challenges, their conditions, baselines, and a new feature set by the openSMILE toolkit, provided to the participants.
},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Vinciarelli, Alessandro and Scherer, Klaus and Ringeval, Fabien and Chetouani, Mohamed and Weninger, Felix and Eyben, Florian and Marchi, Erik and Martillaro, Marcello and Salamin, Hugues and Polychroniou, Anna and Valente, Fabio and Kim, Samuel},
booktitle = {Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013)},
date = {2013-08-25/2013-08-29},
editor = {ISCA},
faupublication = {yes},
keywords = {computational paralinguistics; challenge; social signals; conflict; emotion; autism},
pages = {148-152},
peerreviewed = {Yes},
title = {{The} {INTERSPEECH} 2013 {Computational} {Paralinguistics} {Challenge}: {Social} {Signals}, {Conflict}, {Emotion}, {Autism}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Schuller13-TI2.pdf},
venue = {Lyon, France},
year = {2013}
}
@inproceedings{faucris.121796664,
abstract = {The INTERSPEECH 2014 Computational Paralinguistics Challenge provides for the first time a unified test-bed for the automatic recognition of speakers' cognitive and physical load in speech. In this paper, we describe these two Sub-Challenges, their conditions, baseline results and experimental procedures, as well as the COMPARE baseline features generated with the openSMILE toolkit and provided to the participants in the Challenge.},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Epps, Julien and Eyben, Florian and Ringeval, Fabien and Marchi, Erik and Zhang, Yue},
booktitle = {Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)},
date = {2014-09-14/2014-09-18},
editor = {ISCA},
faupublication = {yes},
keywords = {computational paralinguistics; cognitive load; physical load; challenge},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.theint{\_}7},
pages = {427-431},
peerreviewed = {Yes},
publisher = {International Speech and Communication Association},
title = {{The} {INTERSPEECH} 2014 {Computational} {Paralinguistics} {Challenge}: {Cognitive} & {Physical} {Load}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Schuller14-TI2.pdf},
venue = {Singapore},
year = {2014}
}
@inproceedings{faucris.120332564,
abstract = {The INTERSPEECH 2015 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: The estimation of the degree of nativeness, the neurological state of patients with Parkinson's condition, and the eating conditions of speakers, i. e., whether and which food type they are eating in a seven-class problem. In this paper, we describe these sub-challenges, their conditions, and the baseline feature extraction and classifiers, as provided to the participants.},
author = {Schuller, Björn and Steidl, Stefan and Batliner, Anton and Hantke, Simone and Hönig, Florian Thomas and Orozco Arroyave, Juan Rafael and Nöth, Elmar and Zhang, Yue and Weninger, Felix},
booktitle = {16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015},
faupublication = {yes},
keywords = {Challenge; Computational Paralinguistics; Degree of Nativeness; Eating Condition; Parkinson's Condition},
pages = {478-482},
peerreviewed = {Yes},
publisher = {International Speech and Communication Association},
title = {{The} {INTERSPEECH} 2015 computational paralinguistics challenge: {Nativeness}, {Parkinson}'s & eating condition},
url = {http://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84959078348&origin=inward},
year = {2015}
}
@inproceedings{faucris.219419461,
address = {BAIXAS},
author = {Schuller, Bjorn W. and Steidl, Stefan and Batliner, Anton and Marschik, Peter B. and Baumeister, Harald and Dong, Fengquan and Hantke, Simone and Pokorny, Florian B. and Rathner, Eva-Maria and Bartl-Pokorny, Katrin D. and Einspieler, Christa and Zhang, Dajie and Baird, Alice and Amiriparian, Shahin and Qian, Kun and Ren, Zhao and Schmitt, Maximilian and Tzirakis, Panagiotis and Zafeiriou, Stefanos},
booktitle = {19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6},
date = {2018-08-02/2018-09-06},
doi = {10.21437/interspeech.2018-51},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-06-04},
pages = {122-126},
peerreviewed = {unknown},
publisher = {ISCA-INT SPEECH COMMUNICATION ASSOC},
title = {{The} {INTERSPEECH} 2018 {Computational} {Paralinguistics} {Challenge}: {Atypical} & {Self}-{Assessed} {Affect}, {Crying} & {Heart} {Beats}},
venue = {Hyderabad},
year = {2018}
}
@inproceedings{faucris.229472317,
author = {Schuller, Björn and Batliner, Anton and Bergler, Christian and Porkony, Florian B. and Krajewski, Jarek and Cychosz, Margaret and Vollmann, Ralf and Roelen, Sonja-Dana and Schnieder, Sebastian and Bergelson, Elika and Cristia, Alejandrina and Seidl, Amanda and Warlaumont, Anne S. and Yankowitz, Lisa and Nöth, Elmar and Amiriparian, Shahin and Hantke, Simone and Schmitt, Maximilian},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2019},
date = {2019-09-15/2019-09-19},
doi = {10.21437/Interspeech.2019-1122},
editor = {Gernot Kubin, Thomas Hain, Bjorn Schuller, Dina El Zarka, Petra Hodl},
faupublication = {yes},
keywords = {Computational Paralinguistics; Challenge; Styrian Dialects; Sleepiness; Baby Sounds; Orca Activity},
pages = {2378-2382},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{The} {INTERSPEECH} 2019 {Computational} {Paralinguistics} {Challenge}: {Styrian} {Dialects}, {Continuous} {Sleepiness}, {Baby} {Sounds} & {Orca} {Activity}},
venue = {Graz, AUT},
year = {2019}
}
@inproceedings{faucris.244535312,
author = {Schuller, Björn and Batliner, Anton and Bergler, Christian and Messner, Eva-Maria and Hamilton, Antonia and Amiriparian, Shahin and Baird, Alice and Rizos, Georgios and Schmitt, Maximilian and Stappen, Lukas and Baumeister, Harald and MacIntyre, Alexis Deighton and Hantke, Simone},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2020},
date = {2020-10-25/2020-10-29},
doi = {10.21437/Interspeech.2020-0032},
faupublication = {yes},
keywords = {Computational Paralinguistics, Challenge, Elderly Emotion, Breathing, Speech under Mask},
pages = {2042-2046},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{The} {INTERSPEECH} 2020 {Computational} {Paralinguistics} {Challenge}: {Elderly} {Emotion}, {Breathing} & {Masks}},
venue = {Shanghai, China},
year = {2020}
}
@inproceedings{faucris.259609837,
author = {Schuller, Björn and Batliner, Anton and Bergler, Christian and Mascolo, Cecilia and Han, Jing and Lefter, Iulia and Kaya, Heysem and Amiriparian, Shahin and Baird, Alice and Stappen, Lukas and Ottl, Sandra and Gerczuk, Maurice and Tzirakis, Panagiotis and Brown, Chloe and Chauhan, Jagmohan and Grammenos, Andreas and Hasthanasombat, Apinan and Spathis, Dimitris and Xia, Tong and Cicuta, Pietro and Rothkrantz, Leon J. M. and Zwerts, Joeri A. and Treep, Jelle and Kaandorp, Casper},
booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2021},
date = {2021-08-30/2021-09-03},
doi = {10.21437/Interspeech.2021-19},
faupublication = {yes},
keywords = {Computational Paralinguistics, Challenge, COVID-19, Escalation, Primates},
peerreviewed = {Yes},
publisher = {International Speech Communication Association},
title = {{The} {INTERSPEECH} 2021 {Computational} {Paralinguistics} {Challenge}: {COVID}-19 {Cough}, {COVID}-19 {Speech}, {Escalation} & {Primates}},
venue = {Brno, Czechia},
year = {2021}
}
@inproceedings{faucris.107985064,
author = {Hornegger, Joachim and Niemann, Heinrich},
booktitle = {3-D Scene Acquisition, Modeling and Understanding},
date = {1994-06-09},
editor = {N. Pavesic, H. Niemann, D. Paulus, S. Kovacic},
faupublication = {yes},
pages = {113-126},
peerreviewed = {unknown},
publisher = {IEEE Slovenia Section},
title = {{The} missing information principle in computer vision},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1994/Hornegger94-MIPINCV.pdf},
venue = {Ljubljana},
volume = {2.0},
year = {1994}
}
@article{faucris.120328164,
author = {Hornegger, Joachim and Niemann, Heinrich},
faupublication = {yes},
journal = {International Journal of Computer and Information Technology},
peerreviewed = {unknown},
title = {{The} missing information principle in computer vision},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1994/Hornegger94-MIPC.pdf},
volume = {2},
year = {1994}
}
@incollection{faucris.241874983,
abstract = {Notarial instruments are a category of documents. A notarial instrument can be distinguished from other documents by its notary sign, a prominent symbol in the certificate, which also allows to identify the document’s issuer. Naturally, notarial instruments are underrepresented in regard to other documents. This makes a classification difficult because class imbalance in training data worsens the performance of Convolutional Neural Networks. In this work, we evaluate different countermeasures for this problem. They are applied to a binary classification and a segmentation task on a collection of medieval documents. In classification, notarial instruments are distinguished from other documents, while the notary sign is separated from the certificate in the segmentation task. We evaluate different techniques, such as data augmentation, under- and oversampling, as well as regularizing with focal loss. The combination of random minority oversampling and data augmentation leads to the best performance. In segmentation, we evaluate three loss-functions and their combinations, where only class-weighted dice loss was able to segment the notary sign sufficiently.
This paper describes the corpus of recordings of children’s speech which was collected as part of the EU FP5 PF{\_}STAR project. The corpus contains more than 60 hours of speech, including read and imitated native-language speech in British English, German and Swedish, read and imitated non-native-language English speech from German, Italian and Swedish children, and native-language spontaneous and emotional speech in English and German.
},
address = {Bonn},
author = {Batliner, Anton and Blomberg, Mats and D'Arcy, Shona and Elenius, Daniel and Giuliani, Diego and Gerosa, Matteo and Hacker, Christian and Russell, Martin and Steidl, Stefan and Wong, Michael},
booktitle = {Proceedings of the 9th European Conference on Speech Communication and Technology},
date = {2005-09-04/2005-09-08},
editor = {ISCA},
faupublication = {yes},
pages = {2761-2764},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{The} {PF}-{STAR} {Children}'s {Speech} {Corpus}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Batliner05-TPC.pdf},
venue = {Lisbon},
year = {2005}
}
@inproceedings{faucris.266201746,
author = {Klumpp, Philipp and Bocklet, Tobias and Arias Vergara, Tomás and Vasquez Correa, Juan and Pérez Toro, Paula Andrea and Bayerl, Sebastian and Orozco-Arroyave, Juan Rafael and Nöth, Elmar},
booktitle = {Proc. Interspeech 2021},
date = {2021-08-30/2021-09-03},
doi = {10.21437/Interspeech.2021-1488},
faupublication = {yes},
pages = {441-445},
peerreviewed = {unknown},
title = {{The} {Phonetic} {Footprint} of {Covid}-19},
year = {2021}
}
@article{faucris.267355795,
abstract = {As one of the most prevalent neurodegenerative disorders, Parkinson’s disease (PD) has a significant impact on the fine motor skills of patients. The complex interplay of different articulators during speech production and realization of required muscle tension become increasingly difficult, thus leading to a dysarthric speech. Characteristic patterns such as vowel instability, slurred pronunciation and slow speech can often be observed in the affected individuals and were analyzed in previous studies to determine the presence and progression of PD. In this work, we used a phonetic recognizer trained exclusively on healthy speech data to investigate how PD affected the phonetic footprint of patients. We rediscovered numerous patterns that had been described in previous contributions although our system had never seen any pathological speech previously. Furthermore, we could show that intermediate activations from the neural network could serve as feature vectors encoding information related to the disease state of individuals. We were also able to directly correlate the expert-rated intelligibility of a speaker with the mean confidence of phonetic predictions. Our results support the assumption that pathological data is not necessarily required to train systems that are capable of analyzing PD speech.
In this paper, we present a database with emotional children’s speech in a human-robot scenario: the children were giving instructions to Sony’s pet robot dog AIBO, with AIBO showing both obedient and disobedient behaviour. In such a scenario, a specific type of partner-centered interaction can be observed. We aimed at finding prosodic correlates of children’s emotional speech and were interested to see which speech registers children use when talking to AIBO. For interpretation, we left the weighting and categorization of prosodic features to a statistic classifier. The parameters found to be most important were word duration, average energy, variation in pitch and energy, and harmonics-to-noise ratio. The data moreover suggests that the children used a register that resembled mostly child-directed and pet-directed speech and to some extent computer-directed speech.
},
address = {Dresden},
author = {Batliner, Anton and Steidl, Stefan and Biersack, Sonja},
booktitle = {Proc. Speech Prosody, 3rd International Conference},
date = {2006-05-02/2006-05-05},
editor = {Hoffmann Rüdiger, Mixdorff Hansjörg},
faupublication = {yes},
pages = {1-4},
peerreviewed = {Yes},
publisher = {TUDpress},
title = {{The} {Prosody} of {Pet} {Robot} {Directed} {Speech}: {Evidence} from {Children}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Batliner06-TPO.pdf},
venue = {Dresden},
year = {2006}
}
@misc{faucris.216163746,
abstract = {Data analysis and machine learning have become an
integrative part of the modern scientific methodology, providing
automated techniques to predict further information based on
observations. One of these classification and regression techniques is
the random forest approach. Those decision tree based predictors are
best known for their good computational performance and scalability.
However, in case of severely imbalanced training
data, as often seen in medical studies' data with large control groups,
the training algorithm or the sampling process has to be altered in
order to improve the prediction quality for minority classes.
In this work, a balanced random forest approach for
WEKA is proposed. Furthermore, the prediction quality of the unmodified
random forest implementation and the new balanced random forest version
for WEKA are evaluated against reference implementations in R. Two-class
problems on balanced data sets and imbalanced medical studies' data are
investigated. A superior prediction quality using the proposed method
for imbalanced data is shown compared to the other three techniques},
author = {Amrehn, Mario and Mualla, Firas and Angelopoulou, Elli and Steidl, Stefan and Maier, Andreas},
faupublication = {yes},
peerreviewed = {automatic},
title = {{The} {Random} {Forest} {Classifier} in {WEKA}: {Discussion} and {New} {Developments} for {Imbalanced} {Data}},
url = {https://arxiv.org/pdf/1812.08102.pdf},
year = {2018}
}
@incollection{faucris.108224644,
address = {New York, Berlin},
author = {Batliner, Anton and Huber, Richard and Niemann, Heinrich and Nöth, Elmar and Spilker, Jörg and Fischer, Kerstin},
booktitle = {Verbmobil: Foundations of Speech-to-Speech Translations},
faupublication = {yes},
pages = {122- 130},
peerreviewed = {Yes},
publisher = {Springer},
title = {{The} {Recognition} of {Emotion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2000/Batliner00-TRO.pdf},
year = {2000}
}
@inproceedings{faucris.121434324,
abstract = {
In this paper, we report on classification results for emotional user states (4 classes, German database of children interacting with a pet robot). Six sites computed acoustic and linguistic features independently from each other, following in part different strategies. A total of 4244 features were pooled together and grouped into 12 low level descriptor types and 6 functional types. For each of these groups, classification results using Support Vector Machines and Random Forests are reported for the full set of features, and for 150 features each with the highest individual Information Gain Ratio. The performance for the different groups varies mostly between ≈50% and ≈60%.
},
author = {Schuller, Björn and Batliner, Anton and Seppi, Dino and Steidl, Stefan and Vogt, Thurid and Wagner, Johannes and Devillers, Laurence and Vidrascu, Laurence and Amir, Noam and Kessous, Loic and Aharonson, Vered},
booktitle = {Proceedings Interspeech},
date = {2007-08-27/2007-08-31},
editor = {ISCA},
faupublication = {yes},
keywords = {emotional user states; automatic classification; feature types; functionals},
pages = {2253-2256},
peerreviewed = {Yes},
title = {{The} {Relevance} of {Feature} {Type} for the {Automatic} {Classification} of {Emotional} {User} {States}: {Low} {Level} {Descriptors} and {Functionals}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Schuller07-TRO.pdf},
venue = {Antwerp},
year = {2007}
}
@inproceedings{faucris.107941284,
author = {Riess, Christian and Strehl, Volker and Wanka, Rolf},
booktitle = {Proc. 10th Workshop on Parallel Systems and Algorithms (PASA) of the 25th Int. Conf. on Architecture of Computing Systems (ARCS)},
editor = {GI},
faupublication = {yes},
pages = {505-516},
title = {{The} {Spectral} {Relation} between the {Cube}-{Connected} {Cycles} and the {Shuffle}-{Exchange} {Network}},
venue = {München},
year = {2012}
}
@article{faucris.121031504,
abstract = {Images of ocular fundus are routinely utilized in ophthalmology. Since an examination using fundus camera is relatively fast and cheap procedure, it can be used as a proper diagnostic tool for screening of retinal diseases such as the glaucoma. One of the glaucoma symptoms is progressive atrophy of the retinal nerve fiber layer (RNFL) resulting in variations of the RNFL thickness. Here, we introduce a novel approach to capture these variations using computer-aided analysis of the RNFL textural appearance in standard and easily available color fundus images. The proposed method uses the features based on Gaussian Markov random fields and local binary patterns, together with various regression models for prediction of the RNFL thickness. The approach allows description of the changes in RNFL texture, directly reflecting variations in the RNFL thickness. Evaluation of the method is carried out on 16 normal ("healthy") and 8 glaucomatous eyes. We achieved significant correlation (normals: ?=0.72±0.14; p<<0.05, glaucomatous: ?=0.58±0.10; p<<0.05) between values of the model predicted output and the RNFL thickness measured by optical coherence tomography, which is currently regarded as a standard glaucoma assessment device. The evaluation thus revealed good applicability of the proposed approach to measure possible RNFL thinning.},
author = {Odstrcilik, Jan and Kolar, Radim and Tornow, Ralf-Peter and Jan, Jiri and Budai, Attila and Mayer, Markus Anton and Vodakova, Martina and Lämmer, Robert and Lamos, Martin and Kuna, Zdenek and Gazarek, Jiri and Kubena, Tomas and Cernosek, Pavel and Ronzhina, Marina},
doi = {10.1016/j.compmedimag.2014.05.005},
faupublication = {yes},
journal = {Computerized Medical Imaging and Graphics},
note = {EVALuna2:21169},
pages = {508-16},
peerreviewed = {Yes},
title = {{Thickness} related textural properties of retinal nerve fiber layer in color fundus images},
volume = {38},
year = {2014}
}
@article{faucris.121169004,
abstract = {Purpose: The combination of quickly rotating C-arm gantry with digital flat panel has enabled the acquisition of three-dimensional data (3D) in the interventional suite. However, image quality is still somewhat limited since the hardware has not been optimized for CT imaging. Adaptive anisotropic filtering has the ability to improve image quality by reducing the noise level and therewith the radiation dose without introducing noticeable blurring. By applying the filtering prior to 3D reconstruction, noise-induced streak artifacts are reduced as compared to processing in the image domain. Methods: 3D anisotropic adaptive filtering was used to process an ensemble of 2D x-ray views acquired along a circular trajectory around an object. After arranging the input data into a 3D space (2D projections angle), the orientation of structures was estimated using a set of differently oriented filters. The resulting tensor representation of local orientation was utilized to control the anisotropic filtering. Low-pass filtering is applied only along structures to maintain high spatial frequency components perpendicular to these. The evaluation of the proposed algorithm includes numerical simulations, phantom experiments, and in-vivo data which were acquired using an AXIOM Artis dTA C-arm system (Siemens AG, Healthcare Sector, Forchheim, Germany). Spatial resolution and noise levels were compared with and without adaptive filtering. A human observer study was carried out to evaluate low-contrast detectability. Results: The adaptive anisotropic filtering algorithm was found to significantly improve low-contrast detectability by reducing the noise level by half (reduction of the standard deviation in certain areas from 74 to 30 HU). Virtually no degradation of high contrast spatial resolution was observed in the modulation transfer function (MTF) analysis. Although the algorithm is computationally intensive, hardware acceleration using Nvidia's CUDA Interface provided an 8.9-fold speed-up of the processing (from 1336 to 150 s). Conclusions: Adaptive anisotropic filtering has the potential to substantially improve image quality and/or reduce the radiation dose required for obtaining 3D image data using cone beam CT. © 2011 American Association of Physicists in Medicine.},
author = {Maier, Andreas and Wigström, Lars and Hofmann, Hannes and Hornegger, Joachim and Zhu, Lei and Strobel, Norbert and Fahrig, Rebecca},
doi = {10.1118/1.3633901},
faupublication = {no},
journal = {Medical Physics},
pages = {5896-5909},
peerreviewed = {Yes},
title = {{Three}-dimensional anisotropic adaptive filtering of projection data for noise reduction in cone beam {CT}},
volume = {38},
year = {2011}
}
@article{faucris.120033364,
abstract = {CONCLUSION: SSOCT with motion-correction and vitreous windowing provides wide-field 3-dimensional information of vitreoretinal interface in diabetic eyes. This may be useful in assessing progression of retinopathy, planning diabetic vitreous surgery, and predicting treatment outcomes. (C) 2016 by Elsevier Inc. All rights reserved.},
author = {Adhi, Mehreen and Badaro, Emmerson and Liu, Jonathan J. and Kraus, Martin and Baumal, Caroline R. and Witkin, Andre J. and Hornegger, Joachim and Fujimoto, James G. and Duker, Jay S. and Waheed, Nadia K.},
doi = {10.1016/j.ajo.2015.10.025},
faupublication = {yes},
journal = {American Journal of Ophthalmology},
pages = {140-149},
peerreviewed = {Yes},
title = {{Three}-{Dimensional} {Enhanced} {Imaging} of {Vitreoretinal} {Interface} in {Diabetic} {Retinopathy} {Using} {Swept}-{Source} {Optical} {Coherence} {Tomography}},
volume = {162},
year = {2016}
}
@inproceedings{faucris.267003087,
abstract = {In case of an acute ischemic stroke, rapid diagnosis and removal of the occluding thrombus (blood clot) are crucial for a successful
recovery. We present an automated thrombus detection system for noncontrast computed tomography (NCCT) images to improve the clinical
workflow, where NCCT is typically acquired as a first-line imaging tool
to identify the type of the stroke. The system consists of a candidate
detection model and a subsequent classification model. The detection
model generates a volumetric heatmap from the NCCT and extracts
multiple potential clot candidates, sorted by their likeliness in descending order. The classification model performs reprioritization of these
candidates using graph-based deep learning methods, where the candidates are no longer considered independently, but in a global context. It
was optimized to classify the candidates as clot or no clot. The candidate
detection model, which also serves as a baseline, yields a ROC AUC of
79.8%, which could be improved to 85.2% by the proposed graph-based
classification model.
},
author = {Adams Seewald, Lucas and Facco Rodrigues, Vinicius and Ollenschläger, Malte and Stoffel Antunes, Rodolfo and Andre da Costa, Cristiano and da Rosa Righi, Rodrigo and da Silveira Junior, Luiz Gonzaga and Maier, Andreas and Eskofier, Björn and Fahrig, Rebecca},
doi = {10.1016/j.cviu.2018.09.010},
faupublication = {yes},
journal = {Computer Vision and Image Understanding},
keywords = {Computer vision; Interference; Multi-camera; Depth camera; Evaluation},
peerreviewed = {Yes},
title = {{Toward} analyzing mutual interference on infrared-enabled depth cameras},
year = {2019}
}
@article{faucris.120184724,
abstract = {Vessel diseases are a very common reason for permanent organ damage, disability and death. This fact necessitates further research for extracting meaningful and reliable medical information from the 3D DSA volumes. Murray's law states that at each branch point of a lumen-based system, the sum of the minor branch diameters each raised to the power x, is equal to the main branch diameter raised to the power x. The principle of minimum work and other factors like the vessel type, impose typical values for the junction exponent x. Therefore, deviations from these typical values may signal pathological cases. In this paper, we state the necessary and the sufficient conditions for the existence and the uniqueness of the solution for x. The second contribution is a scale- and orientation- independent set of features for stenosis classification. A support vector machine classifier was trained in the space of these features. Only one branch was misclassified in a cross validation on 23 branches. The two contributions fit into a pipeline for the automatic detection of the cerebral vessel stenoses. © 2012 Institute of Physics and Engineering in Medicine.},
author = {Mualla, Firas and Prümmer, Marcus and Hahn, Dieter and Hornegger, Joachim},
doi = {10.1088/0031-9155/57/9/2555},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
pages = {2555-2573},
peerreviewed = {Yes},
title = {{Toward} automatic detection of vessel stenoses in cerebral {3D} {DSA} volumes},
volume = {57},
year = {2012}
}
@article{faucris.224613637,
author = {Köhler, Thomas and Bätz, Michel and Naderi Boldaji, Farzad and Kaup, André and Maier, Andreas and Rieß, Christian},
doi = {10.1109/TPAMI.2019.2917037},
faupublication = {yes},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
note = {UnivIS-Import:2019-08-15:Pub.2019.tech.IMMD.IMMD5.toward{\_}0},
peerreviewed = {Yes},
title = {{Toward} {Bridging} the {Simulated}-to-{Real} {Gap}: {Benchmarking} {Super}-{Resolution} on {Real} {Data}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Koehler19-TBT.pdf},
volume = {41},
year = {2019}
}
@inproceedings{faucris.203847906,
abstract = {Purpose : Optical coherence tomography angiography (OCTA) is a promising modality for visualizing vascular alterations in a variety of ocular diseases, including age-related macular degeneration (AMD) and diabetic retinopathy (DR). However, most OCTA techniques have limited dynamic range and do not provide information about the relative flow velocities within the imaged vasculature. Visualizing relative flow speed would be especially valuable when assessing diseases in which progression is linked to flow impairment, not just vasculature loss.Methods : OCTA imaging of patients with various stages of AMD and DR was performed with a 1050 nm swept source OCT system at a 400 kHz A-scan rate using a 5 repeated B-scan protocol. Variable interscan time analysis (VISTA) was used to compute the OCTA decorrelation data from pairs of B-scans having 1.5 ms and 3.0 ms separations. The two resulting OCTA data sets were used to compute relative flow speeds, which were then mapped to a color space for display.
Results : The VISTA flow maps for a representative patient with non-proliferative DR (NPDR), and for a patient with geographic atrophy (GA) are shown in Figures 1 and 2, respectively. The VISTA map of the NPDR eye shows slower flows associated with capillary loops in the OCTA image. The VISTA map of the GA eye shows slower flows in the area of atrophy, and on the borders of atrophy.
Conclusions : A method for visualizing VISTA OCTA data is developed and used to differentiate flow speeds in DR and AMD eyes featuring GA. Differentiation of flow speeds is an important first step towards quantitative OCTA and may be useful for assessing vascular diseases at a reversible stag},
author = {Ploner, Stefan and Moult, Eric M. and Waheed, Nadia K. and Husvogt, Lennart and Schottenhamml, Julia and Lee, Byungkun and Hornegger, Joachim and Duker, Jay S. and Rosenfeld, Philip and Fujimoto, James G.},
booktitle = {Investigative Ophthalmology & Visual Science},
date = {2016-05-01/2016-05-05},
edition = {12},
faupublication = {yes},
keywords = {oct;octa; oct angiography;vista;variable interscan time analysis;blood flow},
note = {UnivIS-Import:2018-09-11:Pub.2016.tech.IMMD.IMMD5.toward{\_}7},
peerreviewed = {Yes},
title = {{Toward} quantitative {OCT} angiography: visualizing flow impairment using variable interscan time analysis ({VISTA})},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2016/Ploner16-TQO.pdf},
venue = {Seattle, WA, USA},
volume = {57},
year = {2016}
}
@article{faucris.110064064,
abstract = {Purpose: Currently available optical coherence tomography angiography systems provide information about blood flux but only limited information about blood flow speed. The authors develop a method for mapping the previously proposed variable interscan time analysis (VISTA) algorithm into a color display that encodes relative blood flow speed. Methods: Optical coherence tomography angiography was performed with a 1,050 nm, 400 kHz A-scan rate, swept source optical coherence tomography system using a 5 repeated B-scan protocol. Variable interscan time analysis was used to compute the optical coherence tomography angiography signal from B-scan pairs having 1.5 millisecond and 3.0 milliseconds interscan times. The resulting VISTA data were then mapped to a color space for display. Results: The authors evaluated the VISTA visualization algorithm in normal eyes (n = 2), nonproliferative diabetic retinopathy eyes (n = 6), proliferative diabetic retinopathy eyes (n = 3), geographic atrophy eyes (n = 4), and exudative age-related macular degeneration eyes (n = 2). All eyes showed blood flow speed variations, and all eyes with pathology showed abnormal blood flow speeds compared with controls. Conclusion: The authors developed a novel method for mapping VISTA into a color display, allowing visualization of relative blood flow speeds. The method was found useful, in a small case series, for visualizing blood flow speeds in a variety of ocular diseases and serves as a step toward quantitative optical coherence tomography angiograph},
author = {Ploner, Stefan and Moult, Eric M. and Choi, WooJhon and Waheed, Nadia K. and Lee, Byungkun and Novais, Eduardo A. and Cole, Emily D. and Potsaid, Benjamin and Husvogt, Lennart and Schottenhamml, Julia and Maier, Andreas and Rosenfeld, Philip and Duker, Jay S. and Hornegger, Joachim and Fujimoto, James G.},
doi = {10.1097/IAE.0000000000001328},
faupublication = {yes},
journal = {Retina (Philadelphia, Pa.)},
keywords = {Age-related macular degeneration; Choroidal neovascularization; Nascent geographic atrophy; Ocular blood flow; Optical coherence tomography (OCT); Optical coherence tomography angiography (OCTA); Variable interscan time analysis (VISTA)},
note = {UnivIS-Import:2017-12-18:Pub.2016.tech.IMMD.IMMD5.toward{\_}9},
pages = {S118-S126},
peerreviewed = {Yes},
title = {{Toward} {Quantitative} {Optical} {Coherence} {Tomography} {Angiography}: {Visualizing} {Blood} {Flow} {Speeds} in {Ocular} {Pathology} {Using} {Variable} {Interscan} {Time} {Analysis}},
volume = {32},
year = {2016}
}
@inproceedings{faucris.108099024,
author = {Rohkohl, Christopher and Lauritsch, Günter and Prümmer, Marcus and Boese, Jan and Hornegger, Joachim},
booktitle = {Proceedings of 10th Fully 3D Meeting and 2nd HPIR Workshop},
date = {2009-09-05/2009-09-10},
editor = {Tsui Benjamin M. W.},
faupublication = {yes},
pages = {323-326},
peerreviewed = {unknown},
title = {{Towards} 4-{D} {Cardiac} {Reconstruction} without {ECG} and {Motion} {Periodicity} using {C}-arm {CT}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Rohkohl09-T4C.pdf},
venue = {Beijing},
year = {2009}
}
@inproceedings{faucris.275003983,
author = {Melsheimer, Bastian and Jahn, Annika and Putnings, Markus and Valianos, Stelica and Walther, Marcus},
booktitle = {CRIS2022: 15th International Conference on Current Research Information Systems},
date = {2022-05-12/2022-05-14},
doi = {10.1016/j.procs.2022.10.185},
faupublication = {yes},
keywords = {current research information systems;system interoperability;information exchange;research libraries;Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)},
peerreviewed = {Yes},
title = {{Towards} a {CRIS}-integrated solution for {University} {Press} workflows},
url = {https://dspacecris.eurocris.org/handle/11366/1979},
venue = {Dubrovnik},
year = {2022}
}
@inproceedings{faucris.203274587,
author = {Bopp, Johannes and Ludwig, Veronika and Gallersdörfer, Michael and Seifert, Maria and Pelzer, Georg and Maier, Andreas and Anton, Gisela and Riess, Christian},
booktitle = {Medical Imaging 2018: Physics of Medical Imaging},
doi = {10.1117/12.2292811},
faupublication = {yes},
isbn = {9781510616356},
keywords = {Phase contrast imaging; Talbot-Lau; Dual phase grating; Grating based interferometry},
pages = {1057321},
peerreviewed = {Yes},
publisher = {SPIE},
title = {{Towards} a dual phase grating interferometer on clinical hardware},
url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10573/1057321/Towards-a-dual-phase-grating-interferometer-on-clinical-hardware/10.1117/12.2292811.short},
volume = {10573},
year = {2018}
}
@misc{faucris.208840008,
author = {Riess, Christian and Fuchs, Sven and Angelopoulou, Elli and et al.},
author_hint = {Riess C, Fuchs S, Angelopoulou, E},
faupublication = {yes},
peerreviewed = {automatic},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Towards} a {Feature} {Set} for {Sensor} {Data} {Fusion}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2008/Hornegger08-PRI.pdf#page=113},
year = {2008}
}
@inproceedings{faucris.120139844,
abstract = {We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset. Copyright 2009 ACM.},
author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian Thomas and Nöth, Elmar},
booktitle = {Proceedings of WOCCI 2009},
date = {2009-11-05},
doi = {10.1145/1640377.1640383},
editor = {WOCCI},
faupublication = {yes},
isbn = {9781605586908},
keywords = {Acoustic analysis; Cleft lip and palate; Gaussian mixture models; Support vector regression},
pages = {no pagination},
peerreviewed = {Yes},
title = {{Towards} a language-independent intelligibility assessment of children with cleft lip and palate},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Bocklet09-TAL.pdf},
venue = {Cambridge, MA},
year = {2009}
}
@inproceedings{faucris.113250984,
author = {Köstler, Harald and Popa, Constantin and Prümmer, Marcus and Rüde, Ulrich},
booktitle = {ECCOMAS CFD 06},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2006.tech.IMMD.lsinfs.toward{\_}37},
pages = {1-8},
peerreviewed = {Yes},
title = {{Towards} an {Algebraic} {Multigrid} {Method} for {Tomographic} {Image} {Reconstruction} - {Improving} {Convergence} of {ART}},
url = {https://www10.informatik.uni-erlangen.de/Publications/Papers/2006/Koestler{\_}ECCOMAS-CFD{\_}06},
venue = {Egmond aan Zee, NL},
year = {2006}
}
@inproceedings{faucris.203727364,
author = {Luckner, Christoph and Schebesch, Frank and Mertelmeier, Thomas and Fieselmann, Andreas and Maier, Andreas and Ritschl, Ludwig},
booktitle = {Proc. of SPIE},
doi = {10.1117/12.2318099},
faupublication = {yes},
keywords = {DBT, tomosynthesis, scanning angle, slice thickness, in-plane resolution, analytic model, calcication},
note = {UnivIS-Import:2018-09-06:Pub.2018.tech.IMMD.IMMD5.toward{\_}6},
pages = {107181R},
peerreviewed = {unknown},
title = {{Towards} an analytic model: {Describing} the effect of scan angle and slice thickness on the in-plane spatial resolution of calcications in digital breast tomosynthesis},
venue = {Atlanta, GA, USA},
volume = {10718},
year = {2018}
}
@article{faucris.203842299,
author = {Vasquez Correa, Juan and Orozco-Arroyave, Juan Rafael and Bocklet, Tobias and Nöth, Elmar},
doi = {10.1016/j.jcomdis.2018.08.002},
faupublication = {yes},
journal = {Journal of Communication Disorders},
keywords = {Parkinson's disease, Phonation, Articulation, Prosody, Frenchay Dysarthria Assessment, Longitudinal analysis},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.toward{\_}28},
pages = {21-36},
peerreviewed = {Yes},
title = {{Towards} an automatic evaluation of the dysarthria level of patients with {Parkinson}'s disease},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Vasquez-Correa18-TAA.pdf},
volume = {76},
year = {2018}
}
@inproceedings{faucris.224170044,
address = {CHAM},
author = {Horger, Felix and Würfl, Tobias and Christlein, Vincent and Maier, Andreas},
booktitle = {MACHINE LEARNING FOR MEDICAL IMAGE RECONSTRUCTION, MLMIR 2018},
date = {2018-09-16},
doi = {10.1007/978-3-030-00129-2{\_}15},
faupublication = {yes},
month = {Jan},
note = {CRIS-Team WoS Importer:2019-08-09},
pages = {129-137},
peerreviewed = {unknown},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {{Towards} {Arbitrary} {Noise} {Augmentation}-{Deep} {Learning} for {Sampling} from {Arbitrary} {Probability} {Distributions}},
venue = {Granada},
year = {2018}
}
@inproceedings{faucris.119491064,
author = {Schuldhaus, Dominik and Leutheuser, Heike and Eskofier, Björn},
booktitle = {9th International Conference on Body Area Networks},
date = {2014-09-29/2014-10-01},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.toward{\_}23},
pages = {97-103},
title = {{Towards} {Big} {Data} for {Activity} {Recognition}: {A} {Novel} {Database} {Fusion} {Strategy}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Schuldhaus14-TBD.pdf},
venue = {London},
year = {2014}
}
@inproceedings{faucris.108209244,
author = {Hofmann, Hannes and Keck, Benjamin and Rohkohl, Christopher and Hornegger, Joachim},
booktitle = {Proceedings of 10th Fully 3D Meeting and 2nd HPIR Workshop},
date = {2009-09-05/2009-09-10},
editor = {Tsui Benjamin M. W.},
faupublication = {yes},
pages = {1-4},
peerreviewed = {unknown},
title = {{Towards} {C}-arm {CT} {Reconstruction} on {Larrabee}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Hofmann09-TCC.pdf},
venue = {Beijing},
year = {2009}
}
@inproceedings{faucris.203363425,
author = {Bopp, Johannes and Bartl, Peter and Ritschl, Ludwig and Radicke, Marcus and Maier, Andreas and Anton, Gisela and Riess, Christian},
booktitle = {14th IEEE International Symposium on Biomedical Imaging},
date = {2017-04-18/2017-04-21},
doi = {10.1109/ISBI.2017.7950586},
faupublication = {yes},
pages = {573--577},
peerreviewed = {Yes},
title = {{Towards} cartilage diagnosis in {X}-ray phase-contrast interferometry},
venue = {Melbourne},
year = {2017}
}
@article{faucris.114010204,
abstract = {It is known that a reduction of the field-of-view in 3-D X-ray imaging is proportional to a reduction in radiation dose. The resulting truncation, however, is incompatible with conventional reconstruction algorithms. Recently, a novel method for region of interest reconstruction that uses neither prior knowledge nor extrapolation has been published, named approximated truncation robust algorithm for computed tomography (ATRACT). It is based on a decomposition of the standard ramp filter into a 2-D Laplace filtering and a 2-D Radon-based residual filtering step. In this paper, we present two variants of the original ATRACT. One is based on expressing the residual filter as an efficient 2-D convolution with an analytically derived kernel. The second variant is to apply ATRACT in 1-D to further reduce computational complexity. The proposed algorithms were evaluated by using a reconstruction benchmark, as well as two clinical data sets. The results are encouraging since the proposed algorithms achieve a speed-up factor of up to 245 compared to the 2-D Radon-based ATRACT. Reconstructions of high accuracy are obtained, e.g., even real-data reconstruction in the presence of severe truncation achieve a relative root mean square error of as little as 0.92% with respect to nontruncated data. © 1982-2012 IEEE.},
author = {Xia, Yan and Hofmann, Hannes and Dennerlein, Frank and Müller, Kerstin and Schwemmer, Chris and Bauer, Sebastian and Chintalapani, Gouthami and Chinnadurai, Ponraj and Hornegger, Joachim and Maier, Andreas},
doi = {10.1109/TMI.2013.2291622},
faupublication = {yes},
journal = {IEEE Transactions on Medical Imaging},
keywords = {C-arm CT; dose reduction; image reconstruction; region of interest; truncation; truncation artifact},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.toward{\_}3},
pages = {593-606},
peerreviewed = {Yes},
title = {{Towards} {Clinical} {Application} of a {Laplace} {Operator}-based {Region} of {Interest} {Reconstruction} {Algorithm} in {C}-arm {CT}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Xia14-TCA.pdf},
volume = {33/2014},
year = {2014}
}
@inproceedings{faucris.107940844,
address = {Berlin Heidelberg},
author = {Koch, Martin and Bauer, Sebastian and Hornegger, Joachim and Strobel, Norbert},
booktitle = {Bildverarbeitung für die Medizin 2013},
date = {2013-03-03},
editor = {Hans-Peter Meinzer, Thomas Martin Deserno, Heinz Handels, Thomas Tolxdorff},
faupublication = {yes},
pages = {332-337},
publisher = {Springer},
title = {{Towards} {Deformable} {Shape} {Modeling} of the {Left} {Atrium} {Using} {Non}-{Rigid} {Coherent} {Point} {Drift} {Registration}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Koch13-TDS.pdf},
venue = {Heidelberg, Germany},
year = {2013}
}
@inproceedings{faucris.250221014,
author = {Wang, Zhenghua and Maier, Andreas and Christlein, Vincent},
booktitle = {INFORMATIK 2020},
doi = {10.18420/inf2020{\_}126},
editor = {Reussner RH, Koziolek A, Heinrich R},
faupublication = {yes},
pages = {1345-1354},
peerreviewed = {Yes},
publisher = {Gesellschaft für Informatik, Bonn},
title = {{Towards} {End}-to-{End} {Deep} {Learning}-based {Writer} {Identification}},
url = {https://dl.gi.de/handle/20.500.12116/34716},
year = {2021}
}
@inproceedings{faucris.238079136,
author = {Gallwitz, Florian and Deitsch, Sergiu and Dalsaß, Manuel},
booktitle = {Integration of Sustainable Energy Conference (iSEneC)},
date = {2016-07-11/2016-07-12},
faupublication = {no},
peerreviewed = {Yes},
title = {{Towards} {Fully} {Autonomous} {Aerial} {Inspection} of {Photovoltaic} {Power} {Plants}},
venue = {Nuremberg},
year = {2016}
}
@inproceedings{faucris.208847332,
author = {Bernecker, David and Riess, Christian and Angelopoulou, Elli and Hornegger, Joachim},
booktitle = {Pattern Recognition (Joint 34th DAGM and 36th OAGM Symposium)},
faupublication = {yes},
peerreviewed = {Yes},
title = {{Towards} {Improving} {Solar} {Irradiance} {Forecasts} with {Methods} from {Computer} {Vision}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Bernecker12-TIS.pdf},
venue = {Graz},
year = {2012}
}
@article{faucris.224592722,
abstract = {Robust and fast detection of anatomical structures represents an important component of medical image analysis technologies. Current solutions for anatomy detection are based on machine learning, and are generally driven by suboptimal and exhaustive search strategies. In particular, these techniques do not effectively address cases of incomplete data, i.e., scans acquired with a partial field-of-view. We address these challenges by following a new paradigm, which reformulates the detection task to teaching an intelligent artificial agent how to actively search for an anatomical structure. Using the principles of deep reinforcement learning with multi-scale image analysis, artificial agents are taught optimal navigation paths in the scale-space representation of an image, while accounting for structures that are missing from the field-of-view. The spatial coherence of the observed anatomical landmarks is ensured using elements from statistical shape modeling and robust estimation theory. Experiments show that our solution outperforms marginal space deep learning, a powerful deep learning method, at detecting different anatomical structures without any failure. The dataset contains 5043 3D-CT volumes from over 2000 patients, totaling over 2,500,000 image slices. In particular, our solution achieves 0% false-positive and 0% false-negative rates at detecting whether the landmarks are captured in the field-of-view of the scan (excluding all border cases), with an average detection accuracy of 2.78 mm. In terms of runtime, we reduce the detection-time of the marginal space deep learning method by 20–30 times to under 40 ms, an unmatched performance for high resolution incomplete 3D-CT data.},
author = {Ghesu, Florin-Cristian and Georgescu, Bogdan and Grbic, Sasa and Maier, Andreas and Hornegger, Joachim and Comaniciu, Dorin},
doi = {10.1016/j.media.2018.06.007},
faupublication = {yes},
journal = {Medical Image Analysis},
keywords = {Deep learning; Deep reinforcement learning; Incomplete 3D-data; M-estimator sample consensus; Multi-scale detection; Real-time detection; Robust statistical shape-modeling; Scale-space modeling},
note = {UnivIS-Import:2019-08-15:Pub.2018.tech.IMMD.IMMD5.toward{\_}1},
pages = {203-213},
peerreviewed = {Yes},
title = {{Towards} {Intelligent} {Robust} {Detection} of {Anatomical} {Structures} in {Incomplete} {Volumetric} {Data}},
volume = {1},
year = {2018}
}
@inproceedings{faucris.222906960,
abstract = {Novel X-Ray Microscopy (XRM) systems allow to study the internal structure of a specimen on nanoscale. A possible use of this non-destructive technology is motivated in the medical research area. In-Vivo investigation of medication over a period of time and its effects on perfusion and bony structure might lead to a better understanding of drug mechanisms and diseases like Osteoporosis and could lead to new approaches to their treatment. The first step towards in-vivo XRM imaging is to investigate the suitability of recent XRM systems for this task and subsequently to determine the system parameters. In this context, the impact of mice motion on the image quality is studied in this work. This paper aims to simulate the effects of breathing motion and muscle relaxation of the mice on the reconstructed images, which already effects the projection images. We therefore assume a mouse’s respiration motion pattern, which happens four time during a single projection acquisitions, and the muscle relaxation movement due to anesthesia and simulate its impacts on image quality. Additionally, we show that a frame rate of at least 16 fps is needed to capture in-vivo movements in order to apply state-of-the-art motion correction methods.
The application of traditional machine learning techniques, in the form of regression models based on conventional, “hand-crafted” features, to artifact reduction in limited angle tomography is investigated.
Methods
Mean-variation-median (MVM), Laplacian, Hessian, and shift-variant data loss (SVDL) features are extracted from the images reconstructed from limited angle data. The regression models linear regression (LR), multilayer perceptron (MLP), and reduced-error pruning tree (REPTree) are applied to predict artifact images.
Results
REPTree learns artifacts best and reaches the smallest root-mean-square error (RMSE) of 29 HU for the Shepp–Logan phantom in a parallel-beam study. Further experiments demonstrate that the MVM and Hessian features complement each other, whereas the Laplacian feature is redundant in the presence of MVM. In fan-beam, the SVDL features are also beneficial. A preliminary experiment on clinical data in a fan-beam study demonstrates that REPTree can reduce some artifacts for clinical data. However, it is not sufficient as a lot of incorrect pixel intensities still remain in the estimated reconstruction images.
Conclusion
REPTree has the best performance on learning artifacts in limited angle tomography compared with LR and MLP. The features of MVM, Hessian, and SVDL are beneficial for artifact prediction in limited angle tomography. Preliminary experiments on clinical data suggest that the investigation on more features is necessary for clinical applications of REPTre},
author = {Huang, Yixing and Lu, Yanye and Taubmann, Oliver and Lauritsch, Günter and Maier, Andreas},
doi = {10.1007/s11548-018-1851-2},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Machine learning; limited angle tomography; decision tree},
note = {UnivIS-Import:2018-09-05:Pub.2018.tech.IMMD.IMMD5.tradit{\_}4},
pages = {1-9},
peerreviewed = {Yes},
title = {{Traditional} machine learning for limited angle tomography},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Huang18-TML{\_}IJCARS.pdf},
volume = {8/2018},
year = {2018}
}
@inproceedings{faucris.203727906,
abstract = {In this work, the application of traditional machine learning techniques, in the form of regression models based on conventional, “hand-crafted” features, to streak reduction in limited angle tomography is investigated. Specifically, linear regression (LR), multi-layer perceptron (MLP), and reduced-error pruning tree (REPTree) are investigated. When choosing the mean-variation-median (MVM), Laplacian, and Hessian features, REPTree learns streak artifacts best and reaches the smallest root-mean-square error (RMSE) of 29HU for the Shepp-Logan phantom. Further experiments demonstrate that the MVM and Hessian features complement each other, whereas the Laplacian feature is redundant in the presence of MVM. Preliminary experiments on clinical data suggests that further investigation of clinical applications using REPTree may be worthwhile.
To investigate the occurrence of
pseudoprogression/transient enlargement in meningiomas after
stereotactic radiotherapy (RT) and to evaluate recently proposed volumetric
RANO meningioma criteria
for response assessment in the context of RT. Sixty-nine meningiomas (benign:
90%, atypical: 10%)
received stereotactic RT from January 2005–May 2018. A total of 468 MRI studies
were segmented longitudinally
during a median follow-up of 42.3 months. Best response and local control were evaluated
according to recently proposed volumetric RANO criteria. Transient enlargement
was defined
as volumetric increase ≥20% followed by a
subsequent regression ≥20%. The mean best volumetric
response was −23% change from baseline
(range, −86% to +19%). According to
RANO, the
best volumetric response was SD in 81% (56/69), MR in 13% (9/69) and PR in 6%
(4/69). Transient
enlargement occurred in only 6% (4/69) post RT but would have
represented 60% (3/5) of cases with progressive disease if not accounted for.
Transient enlargement was characterized by a mean maximum
volumetric increase of +181% (range, +24% to +389 %) with all cases occurring
in the first year post-RT
(range, 4.1–10.3 months). Transient enlargement was significantly more frequent
with SRS
or hypofractionation than with conventional fractionation (25% vs. 2%, p
= 0.015).
Five-year volumetric
control was 97.8% if transient enlargement was recognized but 92.9% if not
accounted for.
Transient enlargement/pseudoprogression in the first year following SRS and hypofractionated
RT represents an important differential diagnosis, especially because of
the high volumetric control achieved with stereotactic RT. Meningioma
enlargement during subsequent post-RT follow-up and after
conventional fractionation should raise suspicion for tumor progression.
<},
author = {Maksoud, Ziad and Schmidt, Manuel and Huang, Yixing and Rutzner, Sandra and Mansoorian, Sina and Weissmann, Thomas and Bert, Christoph and Distel, Luitpold and Semrau, Sabine and Lettmaier, Sebastian and Eyüpoglu, Ilker Yasin and Fietkau, Rainer and Putz, Florian},
doi = {10.3390/cancers14061547},
faupublication = {yes},
journal = {Cancers},
keywords = {meningioma; volumetric analysis; segmentation; transient enlargement; pseudoprogression; stereotactic radiotherapy; radiosurgery; response assessment},
pages = {1-13},
peerreviewed = {Yes},
title = {{Transient} {Enlargement} in {Meningiomas} {Treated} with {Stereotactic} {Radiotherapy}},
url = {https://www.mdpi.com/2072-6694/14/6/1547},
volume = {14},
year = {2022}
}
@inproceedings{faucris.307770126,
abstract = {Patient-specific hemodynamics assessment could support diagnosis and treatment of neurovascular diseases. Currently, conventional medical imaging modalities are not able to accurately acquire high-resolution hemodynamic information that would be required to assess complex neurovascular pathologies. Instead, computational fluid dynamics (CFD) simulations can be applied to tomographic reconstructions to obtain clinically relevant information. However, three-dimensional (3D) CFD simulations require enormous computational resources and simulation-related expert knowledge that are usually not available in clinical environments. Recently, deep-learning-based methods have been proposed as CFD surrogates to improve computational efficiency. Nevertheless, the prediction of high-resolution transient CFD simulations for complex vascular geometries poses a challenge to conventional deep learning models. In this work, we present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries. For this, an octree-based spatial discretization is combined with an implicit neural function representation to efficiently handle the prediction of the 3D velocity field for each time step. The presented method is evaluated for the task of cerebral hemodynamics prediction before and during the injection of contrast agent in the internal carotid artery (ICA). Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m s - 1, whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.},
author = {Maul, Noah and Zinn, Katharina and Wagner, Fabian and Thies, Mareike and Rohleder, Maximilian and Pfaff, Laura and Kowarschik, Markus and Birkhold, Annette and Maier, Andreas},
booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
date = {2023-06-18/2023-06-23},
doi = {10.1007/978-3-031-34048-2{\_}15},
editor = {Alejandro Frangi, Marleen de Bruijne, Demian Wassermann, Nassir Navab},
faupublication = {yes},
isbn = {9783031340475},
keywords = {Hemodynamics; Octree; Operator learning},
note = {Created from Fastlane, Scopus look-up},
pages = {183-194},
peerreviewed = {unknown},
publisher = {Springer Science and Business Media Deutschland GmbH},
title = {{Transient} {Hemodynamics} {Prediction} {Using} an {Efficient} {Octree}-{Based} {Deep} {Learning} {Model}},
venue = {San Carlos de Bariloche},
volume = {13939 LNCS},
year = {2023}
}
@article{faucris.110524524,
abstract = {This study is based on the case of BMW, and aims to improve the determination of perceived consumer satisfaction in the automotive industry by transferring existing knowledge from the health care sector. A literature analysis of the health care sector and the automotive industry was conducted to identify the common concepts of determining satisfaction. These were the service encounter, situational factors, and sociodemographics. The practical application was tested by analyzing a contemporary survey from BMW. Based on the findings, managers responsible for customer satisfaction in after-sales services in the automotive industry could improve measurement of customer satisfaction.},
author = {Meinzer, Stefan and Prenninger, Johann and Vesel, Patrick and Kornhuber, Johannes and Volmer, Judith and Hornegger, Joachim and Eskofier, Björn},
doi = {10.1007/s11628-015-0284-z},
faupublication = {yes},
journal = {Service Business},
keywords = {Automotive industry; BMW; Customer satisfaction; Health care; Patient satisfaction},
note = {UnivIS-Import:2015-10-26:Pub.2015.tech.IMMD.IMMD5.transl},
pages = {1-35},
peerreviewed = {Yes},
title = {{Translating} satisfaction determination from health care to the automotive industry},
volume = {06},
year = {2015}
}
@article{faucris.210646812,
abstract = {Gait and postural control dysfunction are prototypical symptoms compromising quality of life for patients with Parkinson’s disease (PD). Hallmarks of cellular pathology are dopaminergic degeneration and accumulation of the cytosolic protein alpha-synuclein, linked to impaired autophagy-lysosome pathway (ALP) clearance. Physical exercise improves gait in PD patients and motor function in rodent lesion models. Moreover, exercise is considered neuroprotective and ALP induction has been reported, e.g. in human skeletal muscle, rodent peripheral and cerebral tissues. A combined analysis of how distinct exercise paradigms affect motor and central biochemical aspects of PD could maximize benefits for patients. Here we examine the effect of 4 weeks treadmill exercise intervention in 7-8 month non-lesioned mice on a) distinct gait categories, b) ALP activity, c) dopaminergic and alpha-synuclein homeostasis. The study includes wild type, alpha-synuclein knockout, and mice exclusively expressing human alpha-synuclein. Parameters of gait regularity and stability, activity, and dynamic postural control during unforced walk, were assessed by an automated system (CatWalk XT). At baseline, alpha-synuclein mouse models exhibited irregular and less active gait, with impaired dynamic postural control, compared to wild type mice. Treadmill exercise particularly improved speed and stride length, while increasing dual diagonal versus three-paw body support in both the alpha-synuclein knockout and transgenic mice. Biochemical analyses showed higher striatal tyrosine hydroxylase immuno-reactivity and reduced higher-order alpha-synuclein species in the cerebral cortex. However, no significant cerebral ALP induction was measured. In summary, treadmill exercise improved gait activity and postural stability, and promoted dopaminergic and alpha-synuclein homeostasis, without robustly inducing cerebral ALP.
For complex segmentation tasks, fully
automatic systems are inherently limited in their achievable accuracy
for extracting relevant objects. Especially in cases where only few data
sets need to be processed for a highly accurate result, semi-automatic
segmentation techniques exhibit a clear benefit for the user. One area
of application is medical image processing during an intervention for a
single patient.
We propose a learning-based cooperative
segmentation approach which includes the computing entity as well as the
user into the task. Our system builds upon a state-of-the-art fully
convolutional artificial neural network (FCN) as well as a simple rule
based active user model for training. During the segmentation process, a
user of the trained system can iteratively add additional hints in form
of pictorial scribbles as seed points into the FCN system to achieve an
interactive and precise segmentation result.
The segmentation
quality of interactive FCNs is evaluated. Iterative FCN approaches can
yield superior results compared to networks without the user input
channel component, due to a consistent improvement in segmentation
quality after each interaction.
},
address = {Goslar, Germany},
author = {Amrehn, Mario and Gaube, Sven and Unberath, Mathias and Schebesch, Frank and Horz, Tim and Strumia, Maddalena and Steidl, Stefan and Kowarschik, Markus and Maier, Andreas},
booktitle = {EG VCBM 2017},
date = {2017-09-07/2017-09-08},
doi = {10.2312/vcbm.20171248},
faupublication = {yes},
isbn = {978-3-03868-036-9},
keywords = {CNN; FCN; Machine Learning; Interactive; User; Semi-automatic; Feedback; Seeds; Segmentation; Medical Imaging},
note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.uineti},
pages = {143-147},
peerreviewed = {Yes},
publisher = {Eurographics Association},
title = {{UI}-{Net}: {Interactive} {Artificial} {Neural} {Networks} for {Iterative} {Image} {Segmentation} {Based} on a {User} {Model}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Amrehn17-UIA.pdf},
venue = {Bremen},
year = {2017}
}
@inproceedings{faucris.282435741,
address = {Rockville},
author = {Ploner, Stefan and Chen, Siyu and Moult, Eric and Husvogt, Lennart and Schottenhamml, Julia and Waheed, Nadia K. and Fujimoto, James G. and Maier, Andreas},
booktitle = {Investigative Ophthalmology & Visual Science},
faupublication = {yes},
note = {CRIS-Team WoS Importer:2022-09-30},
peerreviewed = {unknown},
publisher = {Assoc Research Vision Ophthalmology Inc},
title = {{Ultrahigh} resolution {OCT}, volume merging, and advanced signal reconstruction improve visualization of the {RPE}-{Bruch}'s complex},
url = {https://iovs.arvojournals.org/article.aspx?articleid=2782224},
year = {2022}
}
@article{faucris.113525544,
abstract = {We developed a micromotor based miniature catheter with an outer diameter of 3.2 mm for ultrahigh speed endoscopic swept source optical coherence tomography (OCT) using a vertical cavity surfaceemitting laser (VCSEL) at a 1 MHz axial scan rate. The micromotor can rotate a micro-prism at several hundred frames per second with less than 5 V drive voltage to provide fast and stable scanning, which is not sensitive to the bending of the catheter. The side-viewing probe can be pulled back to acquire a three-dimensional (3D) data set covering a large area on the specimen. The VCSEL provides a high axial scan rate to support dense sampling under high frame rate operation. Using a high speed data acquisition system, in vivo 3D-OCT imaging in the rabbit GI tract and ex vivo imaging of a human colon specimen with 8 μm axial resolution, 8 μm lateral resolution and 1.2 mm depth range in tissue at a frame rate of 400 fps was demonstrated. © 2013 Optical Society of America.},
author = {Tsai, Tsung-Han and Potsaid, Benjamin and Tao, Yuankai Kenny and Jayaraman, Vijaysekhar and Jiang, James and Heim, Peter J. S. and Kraus, Martin and Zhou, Chao and Hornegger, Joachim and Mashimo, Hiroshi and Cable, Alex E. and Fujimoto, James G.},
doi = {10.1364/BOE.4.001119},
faupublication = {yes},
journal = {Biomedical Optics Express},
note = {UnivIS-Import:2015-03-09:Pub.2013.tech.IMMD.IMMD5.ultrah{\_}8},
pages = {1119-1132},
peerreviewed = {Yes},
title = {{Ultrahigh} speed endoscopic optical coherence tomography using micromotor imaging catheter and {VCSEL} technology},
volume = {4},
year = {2013}
}
@inproceedings{faucris.120181204,
abstract = {We developed a micro-motor based miniature catheter with an outer diameter of 3mm for ultrahigh speed endoscopic vbvvvoptical coherence tomography (OCT) using vertical cavity surface-emitting laser (VCSEL) at a 1MHz axial scan rate. The micro-motor can rotate a micro-prism at 1,200-72,000rpm (corresponding to 20- 1,200fps) with less than 5V driving voltage to provide fast and stable scanning, which is not sensitive to the bending of the catheter. The side-viewing probe can be pulled back for a long distance to acquire three-dimensional (3D) dataset covering a large area on the specimen. VCSEL provides high a-line rate to support dense sampling under high frame rate operation. With the use of a C++ based high speed data acquisition (DAQ) system, in vivo three-dimensional OCT imaging in rabbit GI tract with 1.6mm depth range, 11μm axial resolution, 8μm lateral resolution, and frame rate of 400fps is demonstrated. © 2013 Copyright SPIE.},
author = {Tsai, Tsung-Han and Tao, Yuankai Kenny and Potsaid, Benjamin and Jayaraman, Vijaysekhar and Kraus, Martin and Heim, Peter J. S. and Hornegger, Joachim and Mashimo, Hiroshi and Cable, Alex E. and Fujimoto, James G.},
booktitle = {Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XVII},
doi = {10.1117/12.2006952},
faupublication = {yes},
pages = {-},
title = {{Ultrahigh} speed endoscopic optical coherence tomography using micro-motor imaging catheter and {VCSEL} technology},
venue = {San Francisco, CA},
volume = {8571},
year = {2013}
}
@article{faucris.275407431,
abstract = {BackgroundComputed tomography (CT) is widely used as an imaging tool to visualize three-dimensional structures with expressive bone-soft tissue contrast. However, CT resolution can be severely degraded through low-dose acquisitions, highlighting the importance of effective denoising algorithms.
Purpose
Most data-driven denoising techniques are based on deep neural networks and, therefore, contain hundreds of thousands of trainable parameters, making them incomprehensible and prone to prediction failures. Developing understandable and robust denoising algorithms achieving state-of-the-art performance helps to minimize radiation dose while maintaining data integrity.
Methods
This work presents an open-source CT denoising framework based on the idea of bilateral filtering. We propose a bilateral filter that can be incorporated into any deep learning pipeline and optimized in a purely data-driven way by calculating the gradient flow toward its hyperparameters and its input. Denoising in pure image-to-image pipelines and across different domains such as raw detector data and reconstructed volume, using a differentiable backprojection layer, is demonstrated. In contrast to other models, our bilateral filter layer consists of only four trainable parameters and constrains the applied operation to follow the traditional bilateral filter algorithm by design.
Results
Although only using three spatial parameters and one intensity range parameter per filter layer, the proposed denoising pipelines can compete with deep state-of-the-art denoising architectures with several hundred thousand parameters. Competitive denoising performance is achieved on x-ray microscope bone data and the 2016 Low Dose CT Grand Challenge data set. We report structural similarity index measures (SSIM) of 0.7094 and 0.9674 and peak signal-to-noise ratio (PSNR) values of 33.17 and 43.07 on the respective data sets.
Conclusions
Due to the extremely low number of trainable parameters with well-defined effect, prediction reliance and data integrity is guaranteed at any time in the proposed pipelines, in contrast to most other deep learning-based denoising architecture},
author = {Wagner, Fabian and Thies, Mareike and Gu, Mingxuan and Huang, Yixing and Pechmann, Sabrina and Patwari, Mayank and Ploner, Stefan and Aust, Oliver and Uderhardt, Stefan and Schett, Georg and Christiansen, Silke H. and Maier, Andreas},
doi = {10.1002/mp.15718},
faupublication = {yes},
journal = {Medical Physics},
keywords = {known operator learning; low-dose CT; bilateral filter; denoising},
pages = {5107-5120},
peerreviewed = {Yes},
title = {{Ultra} low‐parameter denoising: {Trainable} bilateral filter layers in computed tomography},
volume = {49},
year = {2022}
}
@article{faucris.121136444,
abstract = {Motor impairments are the prerequisite for the diagnosis in Parkinson's disease (PD). The cardinal symptoms (bradykinesia, rigor, tremor, and postural instability) are used for disease staging and assessment of progression. They serve as primary outcome measures for clinical studies aiming at symptomatic and disease modifying interventions. One major caveat of clinical scores such as the Unified Parkinson Disease Rating Scale (UPDRS) or Hoehn&Yahr (H&Y) staging is its rater and time-of-assessment dependency. Thus, we aimed to objectively and automatically classify specific stages and motor signs in PD using a mobile, biosensor based Embedded Gait Analysis using Intelligent Technology (eGaIT). eGaIT consist of accelerometers and gyroscopes attached to shoes that record motion signals during standardized gait and leg function. From sensor signals 694 features were calculated and pattern recognition algorithms were applied to classify PD, H&Y stages, and motor signs correlating to the UPDRS-III motor score in a training cohort of 50 PD patients and 42 age matched controls. Classification results were confirmed in a second independent validation cohort (42 patients, 39 controls). eGaIT was able to successfully distinguish PD patients from controls with an overall classification rate of 81%. Classification accuracy increased with higher levels of motor impairment (91% for more severely affected patients) or more advanced stages of PD (91% for H&Y III patients compared to controls), supporting the PD-specific type of analysis by eGaIT. In addition, eGaIT was able to classify different H&Y stages, or different levels of motor impairment (UPDRS-III). In conclusion, eGaIT as an unbiased, mobile, and automated assessment tool is able to identify PD patients and characterize their motor impairment. It may serve as a complementary mean for the daily clinical workup and support therapeutic decisions throughout the course of the disease. © 2013 Klucken et al.},
author = {Klucken, Jochen and Barth, Jens and Kugler, Patrick and Schlachetzki, Johannes and Henze, Thore and Marxreiter, Franz and Kohl, Zacharias and Steidl, Ralph and Hornegger, Joachim and Eskofier, Björn and Winkler, Jürgen},
doi = {10.1371/journal.pone.0056956},
faupublication = {yes},
journal = {PLoS ONE},
note = {EVALuna2:25318},
peerreviewed = {Yes},
title = {{Unbiased} and {Mobile} {Gait} {Analysis} {Detects} {Motor} {Impairment} in {Parkinson}'s {Disease}},
volume = {8},
year = {2013}
}
@inproceedings{faucris.121224884,
abstract = {The evaluation of tumor growth as regression under therapy is an important clinical issue. Rigid registration of sequentially acquired SD-images has proven its value for this purpose. Existing approaches to rigid image registration use the whole volume for the estimation of the rigid transform. Non-rigid soft tissue deformation, however, will imply a bias to the registration result, because local deformations cannot be modeled by rigid transforms. Anatomical substructures, like bones or teeth, are not affected by these deformations, but follow a rigid transform. This important observation is incorporated in the proposed registration algorithm. The selection of anatomical substructure is done by manual interaction of medical experts adjusting the transfer function of the volume rendering software. The parameters of the transfer function are used to identify the voxels that are considered for registration. A rigid transform is estimated by a quaternion gradient descent algorithm based on the intensity values of the specified tissue classes. Commonly used voxel intensity measures are adjusted to the modified registration algorithm. The contribution describes the mathematical framework of the proposed registration method and its implementation in a commercial software package. The experimental evaluation includes the discussion of different similarity measures, the comparison of the proposed method to established rigid registration techniques and the evaluation of the efficiency of the new method. We conclude with the discussion of potential medical applications of the proposed registration algorithm.},
author = {Hahn, Dieter and Hornegger, Joachim and Bautz, Werner and Kuwert, Torsten and Römer, Wolfgang},
booktitle = {Medical Imaging 2005 - Image Processing},
doi = {10.1117/12.594577},
editor = {Fitzpatrick J.M.Reinhardt J.M.},
faupublication = {yes},
pages = {151-162},
peerreviewed = {unknown},
title = {{Unbiased} rigid registration using transfer functions},
venue = {San Diego, CA},
volume = {5747},
year = {2005}
}
@inproceedings{faucris.228811532,
abstract = {Single Photon Emitted Computed Tomography (SPECT) is characterized by low photon counts and high
degrees of image noise. In this work we investigate deep image postprocessing methods for improving
image quality in SPECT projections and propose a new architecture. Specifically, the residual U-Net proposed by
Heinrich et al. for low-dose Computed Tomography (CT) and the Convolutional Denoising Autoencoder
(CNN DAE) by Gondara et al. were tested for their performance for denoising SPECT projections. Reference
images without noise and scatter were obtained from SPECT Monte Carlo simulations of 24 different XCAT
phantoms of brains, lungs, livers and skeletons using the SIMIND software. These clean images were then
used as training target for the neural networks. Additionally, we propose a U-Net architecture that is more
suited for SPECT image denoising, consisting of 4 layers, each with 2 blocks of convolution, batch
normalization and ReLU. Our results showed that the proposed U-Net outperforms the residual U-Net and
the CNN DAE with a PSNR of 38.25 dB, compared to 27.95 dB and 28.25 dB, respectively. It was shown
that the characteristics of the SPECT data posed a challenge to the neural networks, as there are only few
distinct photon count values at the detector available and these are superimposed with a high degree of
image noise, compared to low-dose CT. Our proposed network was able to decrease the noise within the
phantom and additionally decreased the background noise in the image. The image quality was improved
by 14.15 dB compared to the noisy input image, demonstrating the suitability of our network. We believe that
with increased size and diversity of our dataset we can further boost the performance.
Apart from the ‘normal’ linguistic information entailed in user utterances – segmental (phone/word) information and syntactic/semantic information – there is additional information (supra-segmental and para-linguistic) that can be useful for deciding whether an automatic dialogue system performs well or not. In this paper, we want to deal with such additional information and correlate it with system performance. Moreover, we will examine whether prosodic peculiarities influence word recognition.
},
address = {-},
author = {Batliner, Anton and Hacker, Christian and Steidl, Stefan and Nöth, Elmar and Haas, Jürgen},
booktitle = {Proc. of an ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems},
date = {2003-08-28/2003-08-31},
editor = {ISCA},
faupublication = {yes},
pages = {5-10},
peerreviewed = {Yes},
publisher = {ISCA},
title = {{User} {States}, {User} {Strategies}, and {System} {Performance}: {How} to {Match} the {One} with the {Other}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Batliner03-USU.pdf},
venue = {Chateau d'Oex},
year = {2003}
}
@inproceedings{faucris.108099244,
author = {Fieselmann, Andreas and Ganguly, Arundhuti and Deuerling-Zheng, Yu and Boese, Jan and Fahrig, Rebecca and Hornegger, Joachim},
booktitle = {Medizinische Physik 2010},
date = {2010-09-29/2010-10-02},
editor = {DGMP},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Using} a {C}-arm {CT} for {Interventional} {Perfusion} {Imaging}: {A} {Phantom} {Study} to {Measure} {Linearity} {Between} {Iodine} {Concentration} and {Hounsfield} {Values}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2010/Fieselmann10-UAC.pdf},
venue = {Freiburg i.Br.},
year = {2010}
}
@inproceedings{faucris.112046264,
address = {Berlin},
author = {Haderlein, Tino and Nöth, Elmar and Herbordt, Wolfgang and Kellermann, Walter and Niemann, Heinrich},
booktitle = {Text, Speech and Dialogue; 8th International Conference TSD 2005},
date = {2005-09-12/2005-09-16},
editor = {Václav Matouek, Pavel Mautner, Tomá Pavelka},
faupublication = {yes},
pages = {226-233},
peerreviewed = {Yes},
publisher = {Springer},
title = {{Using} {Artificially} {Reverberated} {Training} {Data} in {Distant}-{Talking} {ASR}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2005/Haderlein05-UAR.pdf},
venue = {Karlovy Vary},
year = {2005}
}
@inproceedings{faucris.121199584,
abstract = {State-of-the-art morphological imaging techniques usually provide high resolution 3D images with a huge number of slices. In clinical practice, however, 2D slice-based examinations are still the method of choice even for these large amounts of data. Providing intuitive interaction methods for specific 3D medical visualization applications is therefore a critical feature for clinical imaging applications. For the domain of catheter navigation and surgery planning, it is crucial to assist the physician with appropriate visualization techniques, such as 3D segmentation maps, fly-through cameras or virtual interaction approaches. There has been an ongoing development and improvement for controllers that help to interact with 3D environments in the domain of computer games. These controllers are based on both motion and infrared sensors and are typically used to detect 3D position and orientation. We have investigated how a state-of-the-art wireless motion sensor controller (Wiimote), developed by Nintendo, can be used for catheter navigation and planning purposes. By default the Wiimote controller only measure rough acceleration over a range of +/- 3g with 10% sensitivity and orientation. Therefore, a pose estimation algorithm was developed for computing accurate position and orientation in 3D space regarding 4 Infrared LEDs. Current results show that for the translation it is possible to obtain a mean error of (0.38cm, 0.41cm, 4.94cm) and for the rotation (0.16, 0.28) respectively. Within this paper we introduce a clinical prototype that allows steering of a virtual fly-through camera attached to the catheter tip by the Wii controller on basis of a segmented vessel tree. © 2009 SPIE.},
author = {Vitanovski, Dime and Hahn, Dieter and Daum, Volker and Hornegger, Joachim},
booktitle = {Medical Imaging 2009: Biomedical Applications in Molecular, Structural, and Functional Imaging},
doi = {10.1117/12.812426},
faupublication = {yes},
pages = {-},
peerreviewed = {unknown},
title = {{Using} a wireless motion controller for {3D} medical image catheter interactions},
venue = {Lake Buena Vista, FL},
volume = {7261},
year = {2009}
}
@phdthesis{faucris.309740384,
abstract = {Speech is a very efficient channel for communication, but it is a challenge to cope with words which are unknown to one of the dialogue partners. Human beings are very good at dealing with words that are not in their vocabulary, for example by exploiting the context the unknown word appears in. In this way, the word can be categorized and, based on this information and the pronunciation, the spelling can be worked out as well.
A key source for task-relevant out-of-vocabulary (OOV) words are named entities like names of cities, persons, companies, products etc. in case they are rarely used or newly invented. In a sentence like “Please give me information about the Argentinian soccer player Jorge Burruchaga!” for example, Mr. Burruchaga’s name is the most important piece of information. Automatic speech recognition (ASR) systems usually map words which were not part of the training material to similar sounding words without considering the word class; often, the consequence of such recognition errors is that the human-machine dialogue cannot be finished successfully.
In this work, it is described how an automatic speech recognition (ASR) system can be enhanced with a functionality that closely resembles the human method so that OOV words can be detected, categorized and recovered in a written form. The suggested approach, hierarchical hybrid word-class-based OOV detection in combination with sub-word units, is integrated into the widely used Kaldi speech recognition toolkit. Experiments on the speech corpora EVAR and SmartWeb show that more than 70% of unknown city names and about 50% of OOV celebrity names can be detected while at the same time improving the word error rate of the system.
In this paper we present our evaluation of the Edge Orientation Histograms (EOH) as feature descriptors in an automatic face-based gender classification application. The feature descriptors extracted from an input image are evaluated using estimated arithmetic means of accuracies to select the feature descriptors that play the most important role in classification success. Our experiments show that features corresponding to the jawline of the subject play the most important role, yielding an average classification accuracy of up to 86%.},
author = {Timotius, Ivanna and Setyawan, Iwan},
booktitle = {International Conference on Information Technology Systems and Innovation},
doi = {10.1109/ICITSI.2014.7048244},
faupublication = {no},
keywords = {gender classification; edge orientation histograms; estimated arithmetic means of accuracies.},
pages = {93 - 98},
peerreviewed = {unknown},
title = {{Using} {Edge} {Orientation} {Histograms} in {Face}--based {Gender} {Classification}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7048244},
venue = {Bandung},
year = {2014}
}
@inproceedings{faucris.117772644,
abstract = {Selecting the appropriate features is essential in building a good classifier. This paper aims to use the approach of estimating the arithmetic means of accuracies (ameans) in selecting the features used in a face-based gender classification. In a face-based gender classification, there are many pixels of the input image that may not aid the classification process, such as those belonging to the background. The experiments show that this approach outperforms the approach based on mean difference especially on the data having relatively high variance by up to 2.14%. Compared to the classifier which does not use any feature selection approach, implementing the feature selection approach based on ameans estimation in a gender classification problem increases the accuracy by up to 7.86%. The experiments also show that the face-based gender classifications rely on the presence of long hair on subjects in the images to make their decision.},
author = {Timotius, Ivanna and Setyawan, Iwan},
booktitle = {The 5th International Conference on Information Technology and Electrical Engineering (ICITEE 2013)},
doi = {10.1109/ICITEED.2013.6676246},
faupublication = {no},
isbn = {978-1-4799-0423-5},
keywords = {Feature Selection; Arithmetic Means of Accuracies; Gender Classification.},
pages = {242 - 247},
peerreviewed = {Yes},
publisher = {IEEE},
title = {{Using} {Estimated} {Arithmetic} {Means} of {Accuracies} to {Select} {Features} for {Face}--based {Gender} {Classification}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6676246},
venue = {Yogyakarta},
year = {2013}
}
@inproceedings{faucris.110274604,
abstract = {When modeling technical processes, the training data regularly come from test plans, to reduce the number of experiments and to save time and costs. On the other hand, this leads to unobserved combinations of the input variables. In this article it is shown, that these unobserved configurations might lead to un-trainable parameters. Afterwards a possible design criterion is introduced, which avoids this drawback. Our approach is tested to model a welding process. The results show, that hybrid Bayesian networks are able to deal with yet unobserved in- and output dat},
address = {Berlin},
author = {Deventer, Rainer and Denzler, Joachim and Niemann, Heinrich and Kreis, Oliver},
booktitle = {Machine Learning and Data Mining in Pattern Recognition},
date = {2003-07-05/2003-07-07},
editor = {Perner P.; Rosenfeld A.},
faupublication = {yes},
keywords = {Bayesian network; Laserbeam welding; Manufacturing process; Modeling},
pages = {307-316},
publisher = {Springer},
title = {{Using} test plans for bayesian modeling},
url = {https://www.scopus.com/record/display.uri?eid=2-s2.0-8344245480∨igin=inward},
venue = {Leipzig},
volume = {2734},
year = {2003}
}
@misc{faucris.116004944,
author = {Haderlein, Tino},
faupublication = {yes},
note = {UnivIS-Import:2016-06-30:Pub.2002.tech.IMMD.IMMD5.usingt},
peerreviewed = {automatic},
title = {{Using} the {ISADORA} {System} for {Analyzing} {Fatigue} {Symptoms} and {Robustness} of {Features} against {Reverberation}},
year = {2002}
}
@article{faucris.109910284,
abstract = {Purpose: Several cell detection approaches which deal with bright-field microscope images utilize defocusing to increase image contrast. The latter is related to the physical light phase through the transport of intensity equation (TIE). Recently, it was shown that it is possible to approximate the solution of the TIE using a low-pass monogenic signal framework. The purpose of this paper is to show that using the local phase of the aforementioned monogenic signal instead of the defocused image improves the cell/background classification accuracy. Materials and methods: The paper statement was tested on an image database composed of three cell lines: adherent CHO, adherent L929, and Sf21 in suspension. Local phase and local energy images were generated using the low-pass monogenic signal framework with axial derivative images as input. Machine learning was then employed to investigate the discriminative power of the local phase. Three classifier models were utilized: random forest (RF), support vector machine (SVM) with a linear kernel, and SVM with a radial basis function (RBF) kernel. Results: The improvement, averaged over cell lines, of classifying 5 x 5 sized patches extracted from the local phase image instead of the defocused image was 7.3 % using the RF, 11.6 % using the linear SVM, and 10.2 % when a RBF kernel was employed instead of the linear one. Furthermore, the feature images can be sorted by increasing discriminative power as follows: at-focus signal, local energy, defocused signal, local phase. The only exception to this order was the superiority of local energy over defocused signal for suspended cells. Conclusions: Local phase computed using the low-pass monogenic signal framework considerably outperforms the defocused image for the purpose of pixel-patch cell/background classification in bright-field microscopy. © 2013 CARS.},
author = {Mualla, Firas and Schöll, Simon and Sommerfeldt, Björn and Maier, Andreas and Steidl, Stefan and Buchholz, Rainer and Hornegger, Joachim},
doi = {10.1007/s11548-013-0969-5},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Bright-field microscopy; Cell detection; Local phase; Machine learning; Monogenic signal; Transport of intensity equation},
note = {UnivIS-Import:2015-03-09:Pub.2014.tech.IMMD.IMMD5.usingt},
pages = {379-386},
peerreviewed = {Yes},
title = {{Using} the {Low}-{Pass} {Monogenic} {Signal} {Framework} for {Cell}/{Background} {Classification} on {Multiple} {Cell} {Lines} in {Bright}-{Field} {Microscope} {Images}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Mualla14-UTL.pdf},
volume = {9},
year = {2014}
}
@inproceedings{faucris.108056784,
address = {Heidelberg},
author = {Mualla, Firas and Schöll, Simon and Sommerfeldt, Björn and Hornegger, Joachim},
booktitle = {Proceedings des Workshops Bildverarbeitung für die Medizin 2013},
date = {2013-03-03},
editor = {Meinzer Hans-Peter, Deserno Thomas Martin},
faupublication = {yes},
pages = {170-174},
publisher = {Springer},
title = {{Using} the {Monogenic} {Signal} for {Cell}-{Background} {Classification} in {Bright}-{Field} {Microscope} {Images}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2013/Mualla13-UTM.pdf},
venue = {Heidelberg},
year = {2013}
}
@inproceedings{faucris.121408584,
address = {Berlin},
author = {Hahn, Dieter and Wolz, Gabriele and Sun, Yiyong and Sauer, Frank and Hornegger, Joachim and Kuwert, Torsten and Xu, Chenyang},
booktitle = {Bildverarbeitung für die Medizin 2006},
date = {2006-03-19/2006-03-21},
doi = {10.1007/3-540-32137-3{\_}45},
editor = {Handels H., Ehrhardt J., Horsch A., Meinzer H.-P., Tolxdorff T.},
faupublication = {yes},
pages = {221-225},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Utilizing} {Salient} {Region} {Features} for {3D} {Multi}-{Modality} {Medical} {Image} {Registration}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2006/Hahn06-USR.pdf},
venue = {Hamburg},
year = {2006}
}
@article{faucris.110943404,
abstract = {Following surgical repair of cleft lip and palate, hearing and speech and language development are important issues for the continued care of affected childhood and adolescent patients. Therefore, PEAKS (Program for Evaluation and Analysis of all Kinds of Speech Disorders) was developed in order to rate speech intelligibility automatically and reduce the time required for diagnostics. PEAKS is based on a speech recognition system and was extended to incorporate a speaker model. This investigation validated PEAKS for isolated cleft palate.From each of the 39 children with isolated cleft palate (3.1-14.5 years), 99 word productions were recorded digitally and analyzed-once "subjectively" by five experts and five nonexperts; once "objectively" using PEAKS.The automatic speech recognition system and the experts arrive at similar results with regard to speech intelligibility. The expert and nonexpert ratings differ significantly from each other. Within the group of nonexperts, a weak interrater reliability demonstrates the uncertainty associated with their ratings.PEAKS delivers reliable and representative results with regard to speech intelligibility among children and adolescents with isolated cleft palate. The automatic measurement of speech quality in children and adolescents with isolated cleft palate is possible.},
author = {Schulz, A. and Bocklet, Tobias and Eysholdt, Ulrich and Bohr, Christopher and Döllinger, Michael and Ziethe, A.},
doi = {10.1007/s00106-013-2825-x},
faupublication = {yes},
journal = {HNO},
note = {EVALuna2:19924},
pages = {525-9},
peerreviewed = {Yes},
title = {{Validation} of an automatic speech analysis in children with isolated cleft palate},
volume = {62},
year = {2014}
}
@inproceedings{faucris.120318484,
abstract = {
Ziel dieser Arbeit ist die Verringerung von Beurteilereinflüssen bei psychometrischen Tests, wie dem Syndrom-Kurztest (SKT), d.h. die Steigerung intersubjektiver Übereinstimmung der Beurteiler, durch die Erfassung validitätssteigernder Variablen mit Hilfe multimodaler Sensoren. Beispiele für solche Sensoren sind Mikrofone, Eyetracker oder Touch-Screens. Die Messung kognitiver Leistungsdefizite nimmt insbesondere bei der Diagnose und Therapiekontrolle altersassoziierter Erkrankungen – zu denen etwa die Demenzen zu zählen sind – einen wichtigen Stellenwert ein. Im Rahmen eines von der Bayerischen Forschungsstiftung (BFS) geförderten Forschungsprojektes (FitForAge) wird untersucht, ob es gelingt, ein interaktives Testsystem zur Erfassung von kognitiven Leistungsstörungen zu konstruieren, das für den Einsatz im telemedizinischen Bereich geeignet ist und vom Patienten weitestgehend selbständig ausgeführt werden kann. Als Grundlage für diese Messungen soll der SKT dienen. Der SKT ist ein international validierter Test zur Erfassung von Gedächtnis- und Aufmerksamkeitsstörungen.
},
address = {Berlin},
author = {Soutschek, Stefan and Spiegl, Werner and Gropp, Martin and Steidl, Stefan and Nöth, Elmar and Erzigkeit, Hellmut and Hornegger, Joachim and Kornhuber, Johannes},
booktitle = {Tagungsband zum 2. deutschen AAL-Kongress (2. Deutscher AAL (Ambient Assisted Living)-Kongress Berlin)},
date = {2009-01-27/2009-01-28},
editor = {BMBF, VDE},
faupublication = {yes},
peerreviewed = {unknown},
publisher = {VDE Verlag GmbH},
title = {{Validierter} {SKT} als {Multimodale} {Telemedizinische} {Applikation}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2009/Soutschek09-VSA.pdf},
venue = {Berlin},
year = {2009}
}
@book{faucris.107393924,
abstract = {We introduce a value-based noise reduction method for Dual-Energy CT applications. It is based on joint intensity statistics estimated from high- and low-energy CT scans of the identical anatomy in order to reduce the noise level in both scans. For a given pair of measurement values, a local gradient ascension algorithm in the probability space is used to provide a noise reduced estimate. As a consequence, two noise reduced images are obtained. It was evaluated with synthetic data in terms of quantitative accuracy and contrast to noise ratio (CNR)-gain. The introduced method allows for reducing patient dose by at least 30% while maintaining the original CNR level. Additionally, the dose reduction potential was shown with a radiological evaluation on real patient data. The method can be combined with state-of-the-art filter-based noise reduction techniques, and makes low-dose Dual-Energy CT possible for the full spectrum of quantitative CT applications. © 2010 Springer-Verlag.},
address = {Berlin},
author = {Balda, Michael and Heismann, Björn and Hornegger, Joachim},
doi = {10.1007/978-3-642-15711-0{\_}68},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2010.tech.IMMD.IMMD5.valueb},
pages = {547-554},
peerreviewed = {Yes},
publisher = {Springer-verlag},
title = {{Value}-based noise reduction for low-dose dual-energy computed tomography},
volume = {null},
year = {2010}
}
@inproceedings{faucris.118760224,
author = {Grimm, Robert and Nickel, Dominik and Hutter, Jana and Forman, Christoph and Kiefer, Berthold and Hornegger, Joachim and Block, Kai Tobias},
booktitle = {Proceedings of the 22nd Annual Meeting of the ISMRM},
faupublication = {yes},
note = {UnivIS-Import:2015-04-16:Pub.2014.tech.IMMD.IMMD5.variab},
pages = {4366},
title = {{Variable} {Temporal} {Resolution} {Reconstruction} for {Golden}-{Angle} {Radial} {Sparse} {Parallel} {DCE}-{MRI}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2014/Grimm14-VTR.pdf},
venue = {Milan, Italy},
year = {2014}
}
@inproceedings{faucris.120331464,
abstract = {
When semicontinuous HMM are used for acoustic modeling in speech recognition usually all states share a single code book. In our investigations we split the feature set into independent subsets and use separate codebooks for each part. This provides a higher modeling flexibility while keeping the parameter space compact. Further experiments integrate new information sources by using additional codebooks which are estimated in a supervised training. For instance codebooks for phone transitions are applied. Codebook exponents weight the different information sources. Relative reductions in word error rate up to 20 % have been achieved.
},
address = {-},
author = {Hacker, Christian and Stemmer, Georg and Steidl, Stefan and Nöth, Elmar and Niemann, Heinrich},
booktitle = {Proceedings of the Speech Processing Workshop, Magdeburg, Germany, September 09},
date = {2003-09-09},
editor = {Wendemuth A.},
faupublication = {yes},
pages = {9-16},
peerreviewed = {Yes},
publisher = {-},
title = {{Various} {Information} {Sources} for {HMM} with {Weighted} {Multiple} {Codebooks}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2003/Hacker03-VIS.pdf},
venue = {Magdeburg},
year = {2003}
}
@inproceedings{faucris.250872449,
abstract = {Introduction
Recent advances in algorithmic processing of medical data are largely based on the use of deep learning algorithms that rely on large amounts of annotated data [1]. To cope with the often complex and time-consuming nature of data acquisition and annotation, data donation and distributed crowd-labeling are an appealing approach [2]. In this paper, we follow this idea and present a single/multi-player mobile game which aids in the annotation process of CT or MR scan data.
Methods
To provide users with an exciting and rewarding annotation experience, our game "Velo-CT" integrates labeling of 3D volume slices into a classical racing game. This is achieved by using data annotation as a key to unlock more advanced racing tracks in the game. To this end, the game has two game modes: 1) Track Racing, and 2) Image Annotation. In “Track Racing”, players compete by steering a vehicle through a racetrack. The main task is to overtake the opponents and try to remain first in position until the end of the race. Checkpoints along the track allow additional guidance if players accidentally leave the racetrack. To provide a more challenging and diverse experience, respawning pick-ups can be found at random locations along the track in the form of floating CT scanners. Such pick-up can either be a speed multiplier (multiplies car speed by 1.2) or a size enhancer (increases the car size by 1.5 to threat opponents and impede their view). The racetracks are modeled based on the segmentation contour of clinical CT data, e.g. showing the respiratory region. For slice segmentation we use a simple K-means classifier. Annotation points earned after beating a track allow the player to unlock new data for the second game mode “Image Annotation”. This is where the medical expertise of the player comes into play. Based on the current progress, the player is presented several medical images which may contain abnormalities. If an abnormality is spotted, the precise location can be marked by a finger tap on the area. The more images a player annotates, the more points can be earned to unlock a new track – and eventually a more intricate anatomy to race on.
Results
Our game was prototyped in Unity3D [3]. As a first anatomy, respiratory tracks based on the “Low Dose CT Grand Challenge” data were constructed. First experiences by players of different gaming background were reported for the single player setting. Users report a fast-paced racing experience with a healthy amount of challenge provided by pick-ups and competitive AI opponents. The organ-aligned layouts result in tracks similar in shape, which should be addressed in the future by adding multiple anatomical regions.
Conclusion
Velo-CT provides an intuitive and extendable integration of the often tedious data annotation process for 3D medical data into a rewarding gaming context. The prototype is available for free download and serves as a basis for further extensions to related game modes.
References
[1] Maier, A., Syben, C., Lasser, T., & Riess, C. (2019). A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik, 29(2), 86-101.
[2] Servadei, L., Schmidt, R., Eidelloth, C., & Maier, A. (2017, October). Medical Monkeys: A Crowdsourcing Approach to Medical Big Data. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" (pp. 87-97). Springer, Cham.
[3] Murray, J. W. (2014). C# game programming cookbook for Unity 3D. AK Peters/CRC Press.
∘ rotations. Rotations around isocentered foreshortening-free vessels passing the isocenter are exact. The precision, however, decreases when the vessel is off-centered or foreshortened. We evaluate worst-case boundaries, providing insight in the maximal inaccuracies to be expected. This can be utilized to design viewpoints guaranteeing desired requirements, e.g., a true rotation around the vessel of at minimum 30 ∘. In addition, a phantom study is performed investigating the impact of input views to 3-D quantitative coronary angiography (QCA). Conclusion: We introduce an algorithm for optimal viewpoint planning from a single angiographic X-ray image. The quality of the second viewpoint—i.e., vessel foreshortening and true rotation around vessel—depends on the first viewpoint selected by the physician; however, our computed viewpoint is guaranteed to reduce the initial foreshortening. Our novel approach uses fluoroscopy images only and, thus, seamlessly integrates with the current clinical workflow for coronary assessment. In addition, it can be implemented in the QCA workflow without increasing user interaction, making vessel-shape reconstruction more stable by standardizing viewpoints.},
address = {Berlin},
author = {Preuhs, Alexander and Berger, Martin and Bauer, Sebastian and Redel, Thomas and Unberath, Mathias and Achenbach, Stephan and Maier, Andreas},
booktitle = {Computer Assisted Radiology and Surgery Proceedings of the 32nd International Congress and Exhibition},
doi = {10.1007/s11548-018-1766-y},
edition = {1},
faupublication = {yes},
keywords = {Active vision; C-arm; Coronary angiography; Foreshortening; Interventional imaging; Patient-specific imaging; QCA},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.viewpo{\_}9},
pages = {201-202},
peerreviewed = {unknown},
publisher = {Springer},
title = {{Viewpoint} {Planning} for {Quantitative} {Coronary} {Angiography}},
url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Preuhs18-VPF.pdf},
venue = {Berlin},
volume = {13},
year = {2018}
}
@article{faucris.203842603,
author = {Preuhs, Alexander and Berger, Martin and Bauer, Sebastian and Redel, Thomas and Unberath, Mathias and Achenbach, Stephan and Maier, Andreas},
doi = {10.1007/s11548-018-1763-1},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {coronary angiography; C-arm; interventional imaging; QCA; active vision; patient specific imaging; foreshortening},
note = {UnivIS-Import:2018-09-11:Pub.2018.tech.IMMD.IMMD5.viewpo{\_}5},
pages = {1159-1167},
peerreviewed = {unknown},
title = {{Viewpoint} {Planning} for {Quantitative} {Coronary} {Angiography} ({IJCARS})},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Preuhs18-VPF1.pdf},
volume = {13},
year = {2018}
}
@inproceedings{faucris.107377644,
author = {Endres, Jürgen and Redel, Thomas and Kowarschik, Markus and Hutter, Jana and Hornegger, Joachim and Dörfler, Arnd},
booktitle = {2012 9th IEEE International Symposium on Biomedical Imaging},
date = {2012-05-02/2012-05-05},
doi = {10.1109/ISBI.2012.6235776},
editor = {IEEE},
faupublication = {yes},
pages = {1200-1203},
peerreviewed = {unknown},
title = {{Virtual} angiography using {CFD} simulations based on patient-specific parameter optimization},
venue = {Barcelona},
year = {2012}
}
@inproceedings{faucris.243140217,
abstract = {Computed Tomography Angiography (CTA) is one of the most commonly used modalities in the diagnosis of cerebrovascular diseases like ischemic strokes. Usually, the anatomy of interest in ischemic stroke cases is the Circle of Willis and its peripherals, the cerebral arteries, as these vessels are the most prominent candidates for occlusions. The diagnosis of occlusions in these vessels remains challenging, not only because of the large amount of surrounding vessels but also due to the large number of anatomical variants. We propose a fully automated image processing and visualization pipeline, which provides a full segmentation and modelling of the cerebral arterial tree for CTA data. The model itself enables the interactive masking of unimportant vessel structures e.g. veins like the Sinus Sagittalis, and the interactive planning of shortest paths meant to be used to prepare further treatments like a mechanical thrombectomy. Additionally, the algorithm automatically labels the cerebral arteries (Middle Cerebral Artery left and right, Anterior Cerebral Artery short, Posterior Cerebral Artery left and right) detects occlusions or interruptions in these vessels. The proposed pipeline does not require a prior non-contrast CT scan and achieves a comparable segmentation appearance as in a Digital Subtraction Angiography (DSA).
2 repeated B-scans, and then computing multiple OCTA signals corresponding to different effective interscan times. The OCTA signals corresponding to different effective interscan times contain independent information about erythrocyte speed. In this study we provide a theoretical overview of VISTA, and investigate the utility of VISTA in studying blood flow alterations in ocular disease. OCTA-VISTA images of eyes with choroidal neovascularization, geographic atrophy, and diabetic retinopathy are presented.
We propose a method to recognize the ‘social attitude’ of users towards an Embodied Conversational Agent from a combination of linguistic and prosodic features. After describing the method and the results of applying it to a corpus of dialogues collected with a Wizard of Oz study, we discuss the advantages and disadvantages of statistical and machine learning methods if compared with other knowledge-based methods
},
address = {Berlin-Heidelberg},
author = {de Rosis, Fiorella and Batliner, Anton and Novielli, Nicole and Steidl, Stefan},
booktitle = {Affective Computing and Intelligent Interaction},
date = {2007-09-12/2007-09-14},
editor = {Ana Paiva, Rui Prada, Rosalind W. Picard},
faupublication = {yes},
pages = {179-190},
peerreviewed = {Yes},
publisher = {Springer},
title = {'{You} are sooo cool, {Valentina}!' {Recognizing} social attitude in speech-based dialogues with an {ECA}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/deRosis07-YAS.pdf},
venue = {Lisbon},
year = {2007}
}
@inproceedings{faucris.107904104,
address = {-},
author = {Huber, Richard and Nöth, Elmar and Batliner, Anton and Buckow, Jan-Constantin and Warnke, Volker and Niemann, Heinrich},
booktitle = {Proceedings of the First Workshop on Text, Speech, Dialogue - TSD'98},
date = {1998-09-23/1998-09-26},
editor = {Petr Sojka, Václav Matou [s] ek, Karel Pala, Ivan Kope [c] ek},
faupublication = {yes},
pages = {223-228},
publisher = {Masaryk University Press},
title = {{You} {BEEP} {Machine} - {Emotion} in {Automatic} {Speech} {Understanding} {Systems}},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/1998/Huber98-YBM.pdf},
venue = {Brno},
year = {1998}
}
@inproceedings{faucris.106721824,
abstract = {Manually browsing through high amount of sports videos, selecting interesting highlight scenes, and applying video effects are time-consuming and one major burden these days. Automatic approaches are preferred, but currently require high-quality TV broadcast material which is usually not available in recreational sports. Thus, the purpose of this paper was to develop a personal low-cost movie producer for highlight videos using wearables. The feasibility of the proposed approach was shown for soccer scenarios. The automatic highlight video generation included three contributions: (i) sensor-based full-instep kick detection and extraction of corresponding video segments, (ii) sensor-based ball speed estimation for provision of highlight-related metadata shown in the final video, and (iii) sensor-driven video effect generation. The proposed system was evaluated on eleven subjects which were equipped with inertial sensors in the cavity of soccer shoes. A mean sensitivity of 95.6 % and a mean absolute error of 7.7 km/h were achieved for the full-instep kick classification and the ball speed estimation, respectively. This personal movie producer based on wearables is a novel idea to provide recreational athletes with attractive automatically generated highlight videos in sports.},
address = {New York, NY, USA},
author = {Schuldhaus, Dominik and Jakob, Carolin and Zwick, Constantin and Koerger, Harald and Eskofier, Björn},
booktitle = {Proceedings of the 2016 ACM International Symposium on Wearable Computers},
date = {2016-09-12/2016-09-16},
doi = {10.1145/2971763.2971772},
faupublication = {yes},
keywords = {Wearables; Inertial Sensors; Soccer; Data Mining; Highlight Videos},
pages = {80-83},
peerreviewed = {Yes},
publisher = {ACM},
title = {{Your} {Personal} {Movie} {Producer}: {Generating} {Highlight} {Videos} in {Soccer} {Using} {Wearables}},
venue = {Heidelberg},
year = {2016}
}
@inproceedings{faucris.113201924,
author = {Batliner, Anton and Hacker, Christian and Steidl, Stefan and Nöth, Elmar and D'Arcy, S. and Russell, Martin and Wong, M.},
booktitle = {Proceedings of the 4th International Conference of Language Resources and Evaluation LREC 2004},
date = {2004-05-26/2004-05-28},
editor = {ELRA},
faupublication = {yes},
pages = {171174},
title = {"{You} stupid tin box" - children interacting with the {AIBO} robot: {A} cross-linguistic emotional speech corpus.},
url = {http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Batliner04-YST.pdf},
venue = {Lisbon},
year = {2004}
}
@misc{faucris.226741230,
author = {Wilke, Peter},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Zusammenhänge} und {Unterschiede} zwischen {Graph}-{Grammatiken} und {Petri}-{Netzen} sowie verwandter {Systeme}
{Arbeitsberichte} des {IMMD} der {Universität} {Erlangen}-{Nürnberg}},
year = {1983}
}
@misc{faucris.210050808,
author = {Wilke, Peter},
faupublication = {yes},
peerreviewed = {automatic},
title = {{Zusammenhänge} und {Unterschiede} zwischen {Graph}-{Grammatiken} und {Petri}-{Netzen} sowie verwandter {Systeme}},
year = {1997}
}
@misc{faucris.210052273,
author = {Wilke, Peter and et al.},
author_hint = {T. Schnaittinger, F. Werner, K. Lampka, N. Grosser,},
faupublication = {yes},
peerreviewed = {automatic},
support_note = {Author relations incomplete. You may find additional data in field 'author{\_}hint'},
title = {{Zwischenbericht} {Entwicklung} eines {Software} {Werkzeuges} für {Risiko}-{Management}},
year = {2001}
}
@article{faucris.215208304,
abstract = {Purpose The quality of X-ray images plays an important role in computer-assisted interventions. Although learning-based denoising techniques have been shown to be successful in improving the image quality, they often rely on pairs of associated low- and high-dose X-ray images that are usually not possible to acquire at different dose levels in a clinical scenario. Moreover, since data variation is an important requirement for learning-based methods, the use of phantom data alone may not be sufficient. A possibility to address this issue is a realistic simulation of low-dose images from their related high-dose counterparts.MethodWe introduce a novel noise simulation method based on an X-ray image formation model. The method makes use of the system parameters associated with low- and high-dose X-ray image acquisitions, such as system gain and electronic noise, to preserve the image noise characteristics of low-dose images.ResultsWe have compared several corresponding regions of the associated real and simulated low-dose imagesobtained from two different imaging systemsvisually as well as statistically, using a two-sample Kolmogorov-Smirnov test at 5% significance. In addition to being visually similar, the hypothesis that the corresponding regionsfrom 80 pairs of real and simulated low-dose regionsbelonging to the same distribution has been accepted in 81.43% of the cases.ConclusionThe results suggest that the simulated low-dose images obtained using the proposed method are almost indistinguishable from real low-dose images. Since extensive calibration procedures required in previous methods can be avoided using the proposed approach, it allows an easy adaptation to different X-ray imaging systems. This in turn leads to an increased diversity of the training data for potential learning-based methods.},
author = {Hariharan, Sai Gokul and Strobel, Norbert and Kaethner, Christian and Kowarschik, Markus and Fahrig, Rebecca and Navab, Nassir},
doi = {10.1007/s11548-019-01912-6},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
note = {CRIS-Team WoS Importer:2019-04-02},
pages = {601-610},
peerreviewed = {unknown},
title = {{An} analytical approach for the simulation of realistic low-dose fluoroscopic images},
volume = {14},
year = {2019}
}
@misc{faucris.239527660,
abstract = {Complex-valued processing brought deep learning-based speech enhancement and
signal extraction to a new level.
Typically, the noise reduction process is based on a time-frequency (TF) mask
which is applied to a noisy spectrogram. Complex masks (CM) usually outperform
real-valued masks due to their ability to modify the phase. Recent work proposed to use a complex linear combination of coefficients
called complex linear coding (CLC) instead of a point-wise multiplication with
a mask.
This allows to incorporate information from previous and optionally future
time steps which results in superior performance over mask-based enhancement
for certain noise conditions.
In fact, the linear combination enables to model quasi-steady properties like
the spectrum within a frequency band.
In this work, we apply CLC to the Deep Noise Suppression (DNS) challenge and
propose CLC as an alternative to traditional mask-based processing, e.g. used
by the baseline.
We evaluated our models using the provided test set and an additional
validation set with real-world stationary and non-stationary noises.
Based on the published test set, we outperform the baseline w.r.t. the scale
independent signal distortion ratio (SI-SDR) by about 3dB.},
author = {Schröter, Hendrik and Rosenkranz, Tobias and Escalante Banuelos, Alberto and Maier, Andreas},
faupublication = {yes},
keywords = {speech enhancement, noise reduction, recurrent neural networks},
peerreviewed = {unknown},
title = {{CLC}: {Complex} {Linear} {Coding} for the {DNS} 2020 {Challenge}},
url = {https://github.com/Rikorose/clc-dns-challenge-2020},
year = {2020}
}
@article{faucris.246694041,
abstract = {Purpose. Denoising X-ray images corrupted by signal-dependent mixed noise is usually approached either by considering noise statistics directly or by using noise variance stabilization (NVS) techniques. An advantage of the latter is that the noise variance can be stabilized to a known constant throughout the image, facilitating the application of denoising algorithms designed for the removal of additive Gaussian noise. A well-performing NVS is the generalized Anscombe transform (GAT). To calculate the GAT, the system gain as well as the variance of electronic noise are required. Unfortunately, these parameters are difficult to predict from the X-ray tube settings in clinical practice, because the system gain observed at the detector depends on the beam hardening caused by the patient. Materials and Methods. We propose a data-driven method for estimating the parameters required to carry out an NVS using the GAT. It utilizes the energy compaction property of the discrete cosine transform to obtain the NVS parameters using a robust regression approach relying on a linear Poisson-Gaussian model. The method has been experimentally validated with respect to beam hardening as well as denoising performance for different dose and scatter levels. Results. Across a range of low-dose X-ray settings, the proposed robust regression approach has estimated both system gain and electronic noise level with an average error of only 4.2%. When used to perform a GAT followed by the denoising of low-dose X-ray images, performance gains of 5% for peak-signal-to-noise ratio and 4% for structural similarity index can be obtained. Conclusion. The parameters needed to calculate the GAT can be estimated efficiently and robustly using a data-driven approach. The improved parameter estimation method facilitates a more accurate GAT-based NVS and, hence, better denoising of low-dose X-ray images when algorithms designed for additive Gaussian noise are applied.},
author = {Hariharan, Sai Gokul and Strobel, Norbert and Kaethner, Christian and Kowarschik, Markus and Fahrig, Rebecca and Navab, Nassir},
doi = {10.1088/1361-6560/abbc82},
faupublication = {yes},
journal = {Physics in Medicine and Biology},
keywords = {Low-dose X-ray imaging; Noise level function estimation; Noise variance stabilization},
note = {CRIS-Team Scopus Importer:2020-12-11},
peerreviewed = {Yes},
title = {{Data}-driven estimation of noise variance stabilization parameters for low-dose {X}-ray images},
volume = {65},
year = {2020}
}
@inproceedings{faucris.270049900,
abstract = {Historical books are often so fragile that they cannot easily be opened in order to read the contents without damaging them. Current research shows, that industrial X-ray computed tomography (CT) can be used to examine closed historical manuscripts. However, the effect of X-rays on ancient paper has rarely been studied, making it difficult to assess the impact of CT measurements on fragile historical manuscripts in terms of additional destruction. To address this problem, various types of paper were exposed to high levels of X-ray radiation in order to examine them for change in optical properties. The investigations showed increasing yellowing due to the increased radiation energy. However, the severity of the yellowing is strongly dependent on the composition of the paper.
Hearing aids (HA) are configured to the wearer’s individual
needs, which might vary greatly from user to user. Currently, it is
common practice, that the initial HA gain settings are based on generic
fitting formulas that link a user’s pure-tone hearing threshold to
amplification characteristics. Subsequently, a time-consuming
fine-tuning process follows, in which a hearing care professional (HCP)
adjusts the HA settings to the user’s individual demands. An advanced,
more personalized gain prescription procedure could support HCPs by
reducing fine-tuning effort and facilitate over-the-counter HAs. We
propose a machine learning based prediction for HA gain to minimize
subsequent fine-tuning effort. The data-driven approach takes audiometic
and personal variables into account, such as age, gender, and the
user’s acoustical environment.
A random forest regression model was trained on real-world HA
fittings from the Connexx database (fitting software provided by
Sivantos GmbH). Three months of data from Connexx version 9.1.0.364 were
used. A data cleaning framework was implemented to extract a
representative data set based on a list of machine learning and
audiological criteria. These criteria include, for instance, using only
‘informative’ HCPs who perform fine-tuning for at least some patients.
Furthermore, ‘informative’ HCPs are those who perform diagnostics beyond
air conduction audiograms, use new technologies and special features.
The resulting training data comprised 20,000 HA fittings and a 10-fold
cross validation was used to train the random forest.
},
author = {Seifer, Ann-Kristin and Schinkel-Bielefeld, Nadja and Schröter, Hendrik and Escalante Banuelos, Alberto and Hoppe, Ulrich and Maier, Andreas},
booktitle = {Virtual Conference on Computational Audiology (VCCA2020)},
date = {2020-06-19/2020-06-19},
faupublication = {yes},
keywords = {Hearing Aids, Machine Learning},
peerreviewed = {unknown},
title = {{Predicting} {Hearing} {Aid} {Fittings} {Based} on {Audiometric} and {Subject}-{Related} {Data}: {A} {Machine} {Learning} {Approach}},
url = {https://computationalaudiology.com/predicting-hearing-aid-fittings-based-on-audiometric-and-subject-related-data-a-machine-learning-approach/},
venue = {Virtual},
year = {2020}
}
@article{faucris.217474255,
abstract = {Purpose: 2D digital subtraction angiography (DSA) has become an important technique for interventional neuroradiology tasks, such as detection and subsequent treatment of aneurysms. In order to provide high-quality DSA images, usually undiluted contrast agent and a high X-ray dose are used. The iodinated contrast agent puts a burden on the patients’ kidneys while the use of high-dose X-rays expose both patients and medical staff to a considerable amount of radiation. Unfortunately, reducing either the X-ray dose or the contrast agent concentration usually results in a sacrifice of image quality. Materials and methods: To denoise a frame, the proposed spatiotemporal denoising method utilizes the low-rank nature of a spatially aligned temporal sequence where variation is introduced by the flow of contrast agent through a vessel tree of interest. That is, a constrained weighted rank-1 approximation of the stack comprising the frame to be denoised and its temporal neighbors is computed where the weights are used to prevent the contribution of non-similar pixels toward the low-rank approximation. The method has been evaluated using a vascular flow phantom emulating cranial arteries into which contrast agent can be manually injected (Vascular Simulations Replicator, Vascular Simulations, Stony Brook NY, USA). For the evaluation, image sequences acquired at different dose levels as well as different contrast agent concentrations have been used. Results: Qualitative and quantitative analyses have shown that with the proposed approach, the dose and the concentration of the contrast agent could both be reduced by about 75%, while maintaining the required image quality. Most importantly, it has been observed that the DSA images obtained using the proposed method have the closest resemblance to typical DSA images, i.e., they preserve the typical image characteristics best. Conclusion: Using the proposed denoising approach, it is possible to improve the image quality of low-dose DSA images. This improvement could enable both a reduction in contrast agent and radiation dose when acquiring DSA images, thereby benefiting patients as well as clinicians. Since the resulting images are free from artifacts and as the inherent characteristics of the images are also preserved, the proposed method seems to be well suited for clinical images as well.},
author = {Hariharan, Sai Gokul and Kaethner, Christian and Strobel, Norbert and Kowarschik, Markus and DiNitto, Julie and Albarqouni, Shadi and Fahrig, Rebecca and Navab, Nassir},
doi = {10.1007/s11548-019-01968-4},
faupublication = {yes},
journal = {International Journal of Computer Assisted Radiology and Surgery},
keywords = {Digital subtraction angiography; Low-dose X-ray sequences; Spatiotemporal denoising; Weighted low-rank approximation},
note = {CRIS-Team Scopus Importer:2019-05-14},
peerreviewed = {Yes},
title = {{Preliminary} results of {DSA} denoising based on a weighted low-rank approach using an advanced neurovascular replication system},
year = {2019}
}
@article{faucris.269362748,
abstract = {The positive outcome of a trauma intervention depends on an intraoperative evaluation of inserted metallic implants. Due to occurring metal artifacts, the quality of this evaluation heavily depends on the performance of so-called Metal Artifact Reduction methods (MAR). The majority of these MAR methods require prior segmentation of the inserted metal objects. Therefore, typically a rather simple thresholding-based segmentation method in the reconstructed 3D volume is applied, despite some major disadvantages. With this publication, the potential of shifting the segmentation task to a learning-based, view-consistent 2D projection-based method on the downstream MAR's outcome is investigated. For segmenting the present metal, a rather simple learning-based 2D projection-wise segmentation network that is trained using real data acquired during cadaver studies, is examined. To overcome the disadvantages that come along with a 2D projection-wise segmentation, a Consistency Filter is proposed. The influence of the shifted segmentation domain is investigated by comparing the results of the standard fsMAR with a modified fsMAR version using the new segmentation masks. With a quantitative and qualitative evaluation on real cadaver data, the investigated approach showed an increased MAR performance and a high insensitivity against metal artifacts. For cases with metal outside the reconstruction's FoV or cases with vanishing metal, a significant reduction in artifacts could be shown. Thus, increases of up to roughly 3 dB w.r.t. the mean PSNR metric over all slices and up to 9 dB for single slices were achieved. The shown results reveal a beneficial influence of the shift to a 2D-based segmentation method on real data for downstream use with a MAR method, like the fsMAR. The nature of the method further suggests the same beneficial behavior for all (also recent data-driven) MAR methods, that for now comprise a 3D-volume-based segmentation step for subsequent inpainting.