% 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} @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} } @inproceedings{faucris.276489551, abstract = {Breast density differs from almost entirely fatty to extremely dense tissue composition. In mammography screenings, physicians are often supported by computer-aided detection and diagnosis systems (CAD) whose detection rate is affected by the density of the breast. An automatic pre-assessment of breast density would enable a specific analysis adapted to each density class. Digital mammograms from the INbreast database [1] are decomposed into Haar-Wavelet components and several levels are used for classification. A random forest classifier is applied on the averaged Wavelet components for four class densities which yields an accuracy of 64.53% in CC-view and 51.22% in MLO-view. The 3-class problem with a combined class of medium densities yields an accuracy of 73.89% in CC-view and 67.80% in MLO-view.}, author = {Schebesch, Frank and Unberath, Mathias and Andersen, Ingwer and Maier, Andreas}, booktitle = {Informatik aktuell}, date = {2016-03-13/2016-03-15}, doi = {10.1007/978-3-662-49465-3{\_}9}, editor = {Thomas M. Deserno, Heinz Handels, Thomas Tolxdorff, Hans-Peter Meinzer}, faupublication = {yes}, isbn = {9783662494646}, note = {CRIS-Team Scopus Importer:2022-06-05}, pages = {38-43}, peerreviewed = {unknown}, publisher = {Kluwer Academic Publishers}, title = {{Breast} density assessment using wavelet features on mammograms}, venue = {Berlin, DEU}, year = {2017} } @inproceedings{faucris.111325324, author = {Unberath, Mathias and Hajek, Jonas and Geimer, Tobias and Schebesch, Frank and Amrehn, Mario 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:2017-12-18:Pub.2017.tech.IMMD.IMMD5.deeple{\_}3}, pages = {-}, peerreviewed = {Yes}, publisher = {IEEE}, title = {{Deep} {Learning}-based {Inpainting} for {Virtual} {DSA}}, url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Unberath17-DLI.pdf}, venue = {Hyatt Regency, Atlanta, Georgia}, year = {2017} } @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.121956604, author = {Herbst, Magdalena and Schebesch, Frank and Berger, Martin and Choi, Jang-Hwan and Fahrig, Rebecca and Hornegger, Joachim and Maier, Andreas}, doi = {10.1118/1.4915542}, faupublication = {yes}, journal = {Medical Physics}, keywords = {GRK-1773}, note = {UnivIS-Import:2015-07-08:Pub.2015.tech.IMMD.IMMD5.dynami}, pages = {2718-2729}, peerreviewed = {Yes}, title = {{Dynamic} detector offsets for field of view extension in {C}-arm computed tomography with application to weight-bearing imaging}, volume = {42}, year = {2015} } @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} } @article{faucris.245786724, abstract = {Visual inspection of solar modules is an important monitoring facility in photovoltaic power plants. Since a single measurement of fast CMOS sensors is limited in spatial resolution and often not sufficient to reliably detect small defects, we apply multi-frame super-resolution (MFSR) to a sequence of low resolution measurements. In addition, the rectification and removal of lens distortion simplifies subsequent analysis. Therefore, we propose to fuse this pre-processing with standard MFSR algorithms. This is advantageous, because we omit a separate processing step, the motion estimation becomes more stable and the spacing of high-resolution (HR) pixels on the rectified module image becomes uniform w.r.t. the module plane, regardless of perspective distortion. We present a comprehensive user study showing that MFSR is beneficial for defect recognition by human experts and that the proposed method performs better than the state of the art. Furthermore, we apply automated crack segmentation and show that the proposed method performs 3x better than bicubic upsampling and 2x better than the state of the art for automated inspection.}, author = {Hoffmann, Mathis and Köhler, Thomas and Doll, Bernd and Schebesch, Frank and Talkenberg, Florian and Peters, Ian Marius and Brabec, Christoph and Maier, Andreas and Christlein, Vincent}, doi = {10.1109/JPHOTOV.2021.3072229}, faupublication = {yes}, journal = {IEEE Journal of Photovoltaics}, pages = {1051-1058}, peerreviewed = {Yes}, title = {{Joint} {Super}-{Resolution} and {Rectification} for {Solar} {Cell} {Inspection}}, url = {https://arxiv.org/pdf/2011.05003.pdf}, volume = {11}, year = {2021} } @article{faucris.203364646, author = {Rausch, Johannes and Maier, Andreas and Fahrig, Rebecca and Choi, Jang-Hwan and Hinshaw, Waldo and Schebesch, Frank and Haase, Sven and Wasza, Jakob and Hornegger, Joachim and Riess, Christian}, doi = {10.1155/2016/2502486}, faupublication = {yes}, journal = {International Journal of Biomedical Imaging}, pages = {2502486:1-15}, peerreviewed = {Yes}, title = {{Kinect}-{Based} {Correction} of {Overexposure} {Artifacts} in {Knee} {Imaging} with {C}-{Arm} {CT} {Systems}}, url = {http://downloads.hindawi.com/journals/ijbi/2016/2502486.pdf}, volume = {2016}, year = {2016} } @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.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.111210044, author = {Mentl, Katrin and Mailhé, Boris and Ghesu, Florin-Cristian and Schebesch, Frank and Haderlein, Tino and Maier, Andreas and Nadar, Mariappan}, booktitle = {2017 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING}, faupublication = {yes}, note = {UnivIS-Import:2017-12-18:Pub.2017.tech.IMMD.IMMD5.noiser{\_}1}, pages = {1-6}, peerreviewed = {Yes}, title = {{Noise} {Reduction} {In} {Low}-{Dose} {CT} {Using} a {3D} {Multiscale} {Sparse} {Denoising} {Autoencoder}}, url = {https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Mentl17-NRI.pdf}, venue = {Tokyo, Japan}, year = {2017} } @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.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} } @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.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} } @inproceedings{faucris.111650044, author = {Schebesch, Frank and Maier, Andreas}, booktitle = {3rd Conference on Image-Guided Interventions & Fokus Neuroradiologie}, faupublication = {yes}, note = {UnivIS-Import:2018-02-22:Pub.2017.tech.IMMD.IMMD5.toward{\_}13}, pages = {12-13}, peerreviewed = {unknown}, title = {{Towards} {Optimal} {Channels} for a {Detection} {Channelized} {Hotelling} {Observer}}, venue = {Magdeburg}, year = {2017} } @inproceedings{faucris.108911704, abstract = {
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.