Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography

2025-04-27

AI Summary

To address the challenges in coronary artery disease (CAD) diagnosis—namely low vessel-to-background contrast, high morphological variability, and difficulty in segmenting small coronary arteries in coronary computed tomography angiography (CCTA)—this paper proposes an end-to-end interpretable framework for fully automatic coronary artery segmentation and stenosis assessment. The method introduces three key innovations: (1) myocardium-guided attention to enhance region-specific feature learning; (2) residual feature encoding with multi-scale adaptive fusion for robust hierarchical representation; and (3) Monte Carlo Dropout to quantify segmentation uncertainty. Stenosis grading is performed via cross-sectional area analysis along anatomically accurate centerlines. Evaluated on a public dataset, the method achieves a Dice score of 85.04% (95% Hausdorff distance = 6.13 mm) for coronary artery segmentation and improves true positive rate for stenosis detection by 5.46% over 3D U-Net. The framework significantly enhances clinical interpretability and robustness.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Coronary artery disease (CAD) remains a leading cause of mortality worldwide, requiring accurate segmentation and stenosis detection using Coronary Computed Tomography angiography (CCTA). Existing methods struggle with challenges such as low contrast, morphological variability and small vessel segmentation. To address these limitations, we propose the Myocardial Region-guided Feature Aggregation Net, a novel U-shaped dual-encoder architecture that integrates anatomical prior knowledge to enhance robustness in coronary artery segmentation. Our framework incorporates three key innovations: (1) a Myocardial Region-guided Module that directs attention to coronary regions via myocardial contour expansion and multi-scale feature fusion, (2) a Residual Feature Extraction Encoding Module that combines parallel spatial channel attention with residual blocks to enhance local-global feature discrimination, and (3) a Multi-scale Feature Fusion Module for adaptive aggregation of hierarchical vascular features. Additionally, Monte Carlo dropout f quantifies prediction uncertainty, supporting clinical interpretability. For stenosis detection, a morphology-based centerline extraction algorithm separates the vascular tree into anatomical branches, enabling cross-sectional area quantification and stenosis grading. The superiority of MGFA-Net was demonstrated by achieving an Dice score of 85.04%, an accuracy of 84.24%, an HD95 of 6.1294 mm, and an improvement of 5.46% in true positive rate for stenosis detection compared to3D U-Net. The integrated segmentation-to-stenosis pipeline provides automated, clinically interpretable CAD assessment, bridging deep learning with anatomical prior knowledge for precision medicine. Our code is publicly available at http://github.com/chenzhao2023/MGFA_CCTA

Problem

• Accurate coronary artery segmentation in low-contrast CCTA images
• Robust stenosis detection amidst morphological variability
• Integration of anatomical knowledge for improved CAD assessment

Innovation

• Myocardial Region-guided Module enhances coronary attention
• Residual Feature Extraction boosts local-global discrimination
• Multi-scale Fusion adaptively aggregates vascular features