English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent advances in deep learning-based medical image segmentation studiesachieve nearly human-level performance in fully supervised manner. However,acquiring pixel-level expert annotations is extremely expensive and laboriousin medical imaging fields. Unsupervised domain adaptation (UDA) can alleviatethis problem, which makes it possible to use annotated data in one imagingmodality to train a network that can successfully perform segmentation ontarget imaging modality with no labels. In this work, we propose SDC-UDA, asimple yet effective volumetric UDA framework for slice-direction continuouscross-modality medical image segmentation which combines intra- and inter-sliceself-attentive image translation, uncertainty-constrained pseudo-labelrefinement, and volumetric self-training. Our method is distinguished fromprevious methods on UDA for medical image segmentation in that it can obtaincontinuous segmentation in the slice direction, thereby ensuring higheraccuracy and potential in clinical practice. We validate SDC-UDA with multiplepublicly available cross-modality medical image segmentation datasets andachieve state-of-the-art segmentation performance, not to mention the superiorslice-direction continuity of prediction compared to previous studies.

SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation