Anatomy Guided Coronary Artery Segmentation from CCTA Using Spatial Frequency Joint Modeling

2025-12-13

AI Summary

To address segmentation instability in coronary artery CT angiography—caused by fine vessel calibers, complex branching patterns, ambiguous boundaries, and myocardial interference—this paper proposes a 3D wavelet-based encoder-decoder network with joint spatial-frequency modeling. The method innovatively integrates myocardium-anatomy-guided priors, residual attention enhancement, and 3D inverse wavelet transforms to achieve structural-consistent multi-scale feature encoding and decoding. Additionally, overlapping voxel block training and multi-scale feature fusion are introduced to improve representation of small distal branches. Evaluated on the ImageCAS dataset, the model achieves a Dice coefficient of 0.8082, sensitivity of 0.7946, precision of 0.8471, and a 95th-percentile Hausdorff distance (HD95) of 9.77 mm—significantly outperforming state-of-the-art 3D segmentation methods.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate coronary artery segmentation from coronary computed tomography angiography is essential for quantitative coronary analysis and clinical decision support. Nevertheless, reliable segmentation remains challenging because of small vessel calibers, complex branching, blurred boundaries, and myocardial interference. We propose a coronary artery segmentation framework that integrates myocardial anatomical priors, structure aware feature encoding, and three dimensional wavelet inverse wavelet transformations. Myocardial priors and residual attention based feature enhancement are incorporated during encoding to strengthen coronary structure representation. Wavelet inverse wavelet based downsampling and upsampling enable joint spatial frequency modeling and preserve multi scale structural consistency, while a multi scale feature fusion module integrates semantic and geometric information in the decoding stage. The model is trained and evaluated on the public ImageCAS dataset using a 3D overlapping patch based strategy with a 7:1:2 split for training, validation, and testing. Experimental results demonstrate that the proposed method achieves a Dice coefficient of 0.8082, Sensitivity of 0.7946, Precision of 0.8471, and an HD95 of 9.77 mm, outperforming several mainstream segmentation models. Ablation studies further confirm the complementary contributions of individual components. The proposed method enables more stable and consistent coronary artery segmentation under complex geometric conditions, providing reliable segmentation results for subsequent coronary structure analysis tasks.

Problem

• Segments coronary arteries from CCTA images accurately
• Addresses challenges of small vessels and blurred boundaries
• Integrates anatomical priors and spatial-frequency modeling for consistency

Innovation

• Integrates myocardial anatomical priors and residual attention for feature enhancement
• Uses wavelet-based downsampling and upsampling for spatial-frequency joint modeling
• Incorporates multi-scale feature fusion to combine semantic and geometric information