Lung, Nodule and Airway Segmentation Using Partially Annotated Data

Querfurth Av, Kordon F, Denzinger F, Breininger K, Kunze H (2023)

Publication Language: English

Publication Type: Conference contribution, Abstract of a poster

Publication year: 2023

Journal

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Publisher: SPIE

Series: Proceedings of SPIE

City/Town: Bellingham, WA

Book Volume: 12466

Pages Range: 124661Q

Conference Proceedings Title: Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

Event location: San Diego, CA US

ISBN: 9781510660373

DOI: 10.1117/12.2653419

Abstract

To support the development of an automatic path-planning procedure for bronchoscopy, semantic segmentation of pulmonary nodules and airways is required. The segmentation should happen simultaneously and automatically to save time and effort during the intervention. The challenges of the combined segmentation are the different shapes, frequencies, and sizes of airways, lungs, and pulmonary nodules. Therefore, a sampling strategy is explored using especially relevant crops of the volumes during training and weighting the classes differently, counteracting class imbalance. For the segmentation, a 3D U-Net is used. The proposed algorithm is compared to nnU-Net. First, it is trained as a one-class problem on all classes individually and in a second approach as a multi-label problem. The developed multi-label segmentation network (MLS) is trained with full supervision. The results of the experiments have shown that without further adaption, a combined segmentation of nodules, airways, and lungs is complex. The multi-label nnU-Net failed to find nodules. Considering the different properties of the three classes, MLS accomplishes segmenting all classes simultaneously.

Authors with CRIS profile

Florian Kordon Lehrstuhl für Informatik 5 (Mustererkennung) Felix Denzinger Lehrstuhl für Informatik 5 (Mustererkennung) Katharina Breininger Department Artificial Intelligence in Biomedical Engineering (AIBE) Holger Kunze Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Querfurth, A.v., Kordon, F., Denzinger, F., Breininger, K., & Kunze, H. (2023, April). Lung, Nodule and Airway Segmentation Using Partially Annotated Data. Poster presentation at Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, CA, US.

MLA:

Querfurth, Anne von, et al. "Lung, Nodule and Airway Segmentation Using Partially Annotated Data." Presented at Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, CA Ed. Cristian A. Linte, Jeffrey H. Siewerdsen, Bellingham, WA: SPIE, 2023.

BibTeX: Download