Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a special computer model to better grade how much the coronary arteries are narrowed, which is important for heart disease diagnosis. They found that using either CCTA images or 3D SCPR images alone has problems because blood vessels are twisty and images can distort. To fix this, they created a method to carefully combine features from both image types using vessel curves. They also designed a training method that considers how different narrowing levels relate to health risks, making the model’s predictions more clinically relevant. Tests showed their approach works better than other methods.
Coronary Artery StenosisCCTA (Coronary CT Angiography)3D SCPR (3D Straightened Curved Planar Reformation)Deep LearningCurved Feature ReconstructionPoint-by-Point CorrespondenceClinical Risk-Aware LossMulti-level GradingFeature Fusion
Authors
Shishuang Zhao, Hongtai Li, Junjie Hou, Yuhang Liu
Abstract
Developing a multi-level grading model for coronary artery stenosis holds great clinical significance for the diagnosis of coronary artery disease. However, designing an effective multi-level deep learning algorithm faces significant challenges. Specifically, utilizing CCTA or 3D SCPR images alone presents inherent shortcomings: CCTA images are difficult to analyze due to the tortuous paths of blood vessels, while 3D SCPR images are prone to abnormal distortions that hinder accurate grading. Furthermore, different stenosis grades are associated with varying clinical risks, and incorporating this association into the algorithm is non-trivial. To address the former problems, we propose the Curved Feature Reconstruction (CFR) module, which uses vessel curves as prior and employs a point-by-point correspondence strategy to precisely align and fuse features from both 3D SCPR and CCTA images. Meanwhile, a Clinical Risk-Aware (CR) Loss is employed to introduce clinical risk relevance into the network training so that the algorithm can better align with the clinical diagnosis. The experimental results on a in-house dataset reveal that our approach significantly outperforms other methods, and several ablation studies also demonstrate the effectiveness of our proposed designs.