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

TL;DR

This paper introduces HAGMN-UQ, a novel neural network that uses hyper association graph matching and uncertainty quantification to improve semantic labeling of coronary arteries in angiograms, aiding CAD diagnosis.

Contribution

The paper presents a new graph-matching neural network with uncertainty quantification for coronary artery labeling, addressing morphological similarities that challenge existing deep learning methods.

Findings

Achieved 93.45% accuracy in artery labeling

Enabled real-time inference for clinical use

Improved segmentation accuracy over previous methods

Abstract

Coronary artery disease (CAD) is one of the primary causes leading to death worldwide. Accurate extraction of individual arterial branches on invasive coronary angiograms (ICA) is important for stenosis detection and CAD diagnosis. However, deep learning-based models face challenges in generating semantic segmentation for coronary arteries due to the morphological similarity among different types of coronary arteries. To address this challenge, we propose an innovative approach using the hyper association graph-matching neural network with uncertainty quantification (HAGMN-UQ) for coronary artery semantic labeling on ICAs. The graph-matching procedure maps the arterial branches between two individual graphs, so that the unlabeled arterial segments are classified by the labeled segments, and the coronary artery semantic labeling is achieved. By incorporating the anatomical structural loss and uncertainty, our model achieved an accuracy of 0.9345 for coronary artery semantic labeling with a fast inference speed, leading to an effective and efficient prediction in real-time clinical decision-making scenarios.