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

Coronary artery disease (CAD) is one of the primary causes leading to deathworldwide. Accurate extraction of individual arterial branches on invasivecoronary angiograms (ICA) is important for stenosis detection and CADdiagnosis. However, deep learning-based models face challenges in generatingsemantic segmentation for coronary arteries due to the morphological similarityamong different types of coronary arteries. To address this challenge, wepropose an innovative approach using the hyper association graph-matchingneural network with uncertainty quantification (HAGMN-UQ) for coronary arterysemantic labeling on ICAs. The graph-matching procedure maps the arterialbranches between two individual graphs, so that the unlabeled arterial segmentsare classified by the labeled segments, and the coronary artery semanticlabeling is achieved. By incorporating the anatomical structural loss anduncertainty, our model achieved an accuracy of 0.9345 for coronary arterysemantic labeling with a fast inference speed, leading to an effective andefficient prediction in real-time clinical decision-making scenarios.

Hyper Association Graph Matching with Uncertainty Quantification for Coronary Artery Semantic Labeling