Multi-graph Graph Matching for Coronary Artery Semantic Labeling

arXiv:2402.15894v1 Announce Type: new
Abstract: Coronary artery disease (CAD) stands as the leading cause of death worldwide, and invasive coronary angiography (ICA) remains the gold standard for assessing vascular anatomical information. However, deep learning-based methods encounter challenges in generating semantic labels for arterial segments, primarily due to the morphological similarity between arterial branches. To address this challenge, we model the vascular tree as a graph and propose a multi-graph graph matching (MGM) algorithm for coronary artery semantic labeling. The MGM …

abstract arxiv cad challenges cs.cv death deep learning disease graph information labeling labels semantic standard type