Deep learning model for coronary artery segmentation and quantitative stenosis detection in angiographic images
Medical Physics · 2025
DOI: 10.1002/mp.17970 ↗At a glance
Journal article in Medical Physics, 2025. Written by Baixiang Huang and 6 co-authors. Institution: School of Mathematical Sciences, Ocean University of China, Qingdao, China. Major MEDLINE topics: Deep Learning, Coronary Angiography, Image Processing, Computer-Assisted, Coronary Vessels. Cited 8 times so far (Crossref); 45 references. Funded by: Natural Science Foundation of Qingdao Municipality, Fundamental Research Funds for the Central Universities, National Key R&D Plan of China.
Abstract (original language)
Background
Coronary artery disease (CAD) is a leading cause of cardiovascular‐related mortality, and accurate stenosis detection is crucial for effective clinical decision‐making. Coronary angiography remains the gold standard for diagnosing CAD, but manual analysis of angiograms is prone to errors and subjectivity.
Purpose
This study aims to develop a deep learning‐based approach for the automatic segmentation of coronary arteries from angiographic images and the quantitative detection of stenosis, thereby improving the accuracy and efficiency of CAD diagnosis.
Methods
We propose a novel deep learning‐based method for the automatic segmentation of coronary arteries in angiographic images, coupled with a dynamic cohort method for stenosis detection. The segmentation model combines the MedSAM and VM‐UNet architectures to achieve high‐performance results. After segmentation, the vascular centerline is extracted, vessel diameter is computed, and the degree of stenosis is measured with high precision, enabling accurate identification of arterial stenosis.
Results
On the mixed dataset (including the ARCADE, DCA1, and GH datasets), the model achieved an average IoU of 0.6308, with sensitivity and specificity of 0.9772 and 0.9903, respectively. On the ARCADE dataset, the average IoU was 0.6303, with sensitivity of 0.9832 and specificity of 0.9933. Additionally, the stenosis detection algorithm achieved a true positive rate of 0.5867 and a positive predictive value of 0.5911, demonstrating the effectiveness of our model in analyzing coronary angiography images.
Conclusions
SAM‐VMNet offers a promising tool for the automated segmentation and detection of coronary artery stenosis. The model's high accuracy and robustness provide significant clinical value for the early diagnosis and treatment planning of CAD. The code and examples are available at https://github.com/qimingfan10/SAM‐VMNet .
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- School of Mathematical Sciences, Ocean University of China, Qingdao, China.
- School of Haide, Ocean University of China, Qingdao, China.
- School of Ocean and Atmosphere, Ocean University of China, Qingdao, China.
- Department of Cardiology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, China.
Funding
- Natural Science Foundation of Qingdao Municipality
- Fundamental Research Funds for the Central Universities
- National Key R&D Plan of China
Cite
APA
Huang, B., Luo, Y., Wei, G., He, S., Shao, Y., Zeng, X., & Zhang, Q. (2025). Deep learning model for coronary artery segmentation and quantitative stenosis detection in angiographic images. Medical Physics. https://doi.org/10.1002/mp.17970
Vancouver
Huang B, Luo Y, Wei G, He S, Shao Y, Zeng X, et al. Deep learning model for coronary artery segmentation and quantitative stenosis detection in angiographic images. Medical Physics. 2025. doi:10.1002/mp.17970
BibTeX
@article{Huang2025,
author = {Huang, Baixiang and Luo, Yu and Wei, Guangyu and He, Songyan and Shao, Yushuang and Zeng, Xueying and Zhang, Qing},
title = {Deep learning model for coronary artery segmentation and quantitative stenosis detection in angiographic images},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.17970}
}
EUVIMED