Few-shot segmentation of 3D medical images

Abhijit Guha Roy, Shayan Siddiqui, Sebastian Pölsterl, Azade Farshad, Nassir Navab, Christian Wachinger

Publikation: Beitrag in Buch/Bericht/KonferenzbandKapitelBegutachtung

2 Zitate (Scopus)

Abstract

Deep neural networks enable highly accurate image segmentation but require large amounts of manually annotated data for supervised training. Few-shot learning aims to overcome this weakness by learning a new class from a few annotated support samples. This chapter introduces our novel few-shot segmentation framework for volumetric medical images with only a few annotated slices. Compared to other related works in computer vision, the main challenges are the absence of pretrained networks and the volumetric nature of medical scans. We address these challenges by proposing a new architecture for few-shot segmentation that incorporates ‘squeeze & excite’ blocks. Our two-armed architecture consists of a conditioner arm, which processes the annotated support input and generates a task-specific representation. This representation is passed on to the segmenter arm that uses this information to segment the new query image. To facilitate efficient interaction between the conditioner and the segmenter arm, we propose to use ‘channel squeeze & spatial excitation’ blocks – a lightweight computational module – that enables heavy interaction between both the arms with negligible increase in model complexity. This contribution allows us to perform image segmentation without relying on a pretrained model, which generally is unavailable for medical scans. Furthermore, we propose an efficient strategy for volumetric segmentation by optimally pairing a few slices of the support volume to all the slices of the query volume. We perform experiments for organ segmentation on whole-body contrast-enhanced CT scans from the Visceral Dataset. Our proposed model outperforms multiple baselines and existing approaches in segmentation accuracy by a significant margin. The source code is available at https://github.com/abhi4ssj/few-shot-segmentation.

OriginalspracheEnglisch
TitelMeta Learning with Medical Imaging and Health Informatics Applications
Herausgeber (Verlag)Elsevier
Seiten161-183
Seitenumfang23
ISBN (elektronisch)9780323998512
ISBN (Print)9780323998529
DOIs
PublikationsstatusVeröffentlicht - 1 Jan. 2022

Fingerprint

Untersuchen Sie die Forschungsthemen von „Few-shot segmentation of 3D medical images“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren