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

The segmentation of coronary arteries by convolutional neural network ispromising yet requires a large amount of labor-intensive manual annotations.Transferring knowledge from retinal vessels in widely-available public labeledfundus images (FIs) has a potential to reduce the annotation requirement forcoronary artery segmentation in X-ray angiograms (XAs) due to their commontubular structures. However, it is challenged by the cross-anatomy domain shiftdue to the intrinsically different vesselness characteristics in differentanatomical regions under even different imaging protocols. To solve thisproblem, we propose a Semi-Supervised Cross-Anatomy Domain Adaptation (SS-CADA)which requires only limited annotations for coronary arteries in XAs. With thesupervision from a small number of labeled XAs and publicly available labeledFIs, we propose a vesselness-specific batch normalization (VSBN) toindividually normalize feature maps for them considering their differentcross-anatomic vesselness characteristics. In addition, to further facilitatethe annotation efficiency, we employ a self-ensembling mean-teacher (SEMT) toexploit abundant unlabeled XAs by imposing a prediction consistency constraint.Extensive experiments show that our SS-CADA is able to solve the challengingcross-anatomy domain shift, achieving accurate segmentation for coronaryarteries given only a small number of labeled XAs.

SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation