Multi-graph Graph Matching for Coronary Artery Semantic Labeling
This addresses the problem of accurate coronary artery disease assessment for medical professionals, offering a novel tool for vascular analysis, though it appears incremental as it builds on graph-based methods for a specific domain.
The paper tackles the challenge of generating semantic labels for coronary artery segments in invasive coronary angiography (ICA) by modeling vascular trees as graphs and proposing a multi-graph graph matching (MGM) algorithm, achieving an accuracy of 0.9471 for labeling and 0.9155 for stenosis detection on a dataset of 718 ICAs.
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 and varying anatomy of arterial system between different projection view angles and patients. 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 algorithm assesses the similarity between arterials in multiple vascular tree graphs, considering the cycle consistency between each pair of graphs. As a result, the unannotated arterial segments are appropriately labeled by matching them with annotated segments. Through the incorporation of anatomical graph structure, radiomics features, and semantic mapping, the proposed MGM model achieves an impressive accuracy of 0.9471 for coronary artery semantic labeling using our multi-site dataset with 718 ICAs. With the semantic labeled arteries, an overall accuracy of 0.9155 was achieved for stenosis detection. The proposed MGM presents a novel tool for coronary artery analysis using multiple ICA-derived graphs, offering valuable insights into vascular health and pathology.