Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction

Shishuang Zhao, Hongtai Li, Junjie Hou, Yuhang Liu
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2297-2310, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-zhao26a, title = {Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction}, author = {Zhao, Shishuang and Li, Hongtai and Hou, Junjie and Liu, Yuhang}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2297--2310}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/zhao26a/zhao26a.pdf}, url = {https://proceedings.mlr.press/v315/zhao26a.html}, 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.} }
Endnote
%0 Conference Paper %T Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction %A Shishuang Zhao %A Hongtai Li %A Junjie Hou %A Yuhang Liu %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-zhao26a %I PMLR %P 2297--2310 %U https://proceedings.mlr.press/v315/zhao26a.html %V 315 %X 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.
APA
Zhao, S., Li, H., Hou, J. & Liu, Y.. (2026). Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2297-2310 Available from https://proceedings.mlr.press/v315/zhao26a.html.

Related Material