MHASegNet: A multi-scale hybrid aggregation network of segmenting coronary artery from CCTA images
Journal of X-Ray Science and Technology · 2025
DOI: 10.1177/08953996251346484 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, 2025. Verfasst von Shang Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China. Hauptthemen laut MEDLINE: Coronary Vessels, Computed Tomography Angiography, Coronary Artery Disease, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Liaoning Province Science and Technology Plan Joint Program, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Background
Segmentation of coronary arteries in Coronary Computed Tomography Angiography (CCTA) images is crucial for diagnosing coronary artery disease (CAD), but remains challenging due to small artery size, uneven contrast distribution, and issues like over-segmentation or omission.
Objective
The aim of this study is to improve coronary artery segmentation in CCTA images using both conventional and deep learning techniques.
Methods
We propose MHASegNet, a lightweight network for coronary artery segmentation, combined with a tailored refinement method. MHASegNet employs multi-scale hybrid attention to capture global and local features, and integrates a 3D context anchor attention module to focus on key coronary artery structures while suppressing background noise. An iterative, region-growth-based refinement addresses crown breaks and reduces false alarms. We evaluated the method on an in-house dataset of 90 subjects and two public datasets with 1060 subjects.
Results
MHASegNet, coupled with tailored refinement, outperforms state-of-the-art algorithms, achieving a Dice Similarity Coefficient (DSC) of 0.867 on the in-house dataset, 0.875 on the ASOCA dataset, and 0.827 on the ImageCAS dataset.
Conclusion
The tailored refinement significantly reduces false positives and resolves most discontinuities, even for other networks. MHASegNet and the tailored refinement may aid in diagnosing and quantifying CAD following further validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
- School of Health Management, China Medical University, Shenyang, China.
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
ORCID-Profile: Shang Li, Patrice Monkam, Shouliang Qi
Förderung
- National Natural Science Foundation of China
- Liaoning Province Science and Technology Plan Joint Program
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Li, S., Wu, Y., Jiang, B., Liu, L., Zhang, T., Sun, Y., Hou, J., Monkam, P., Qian, W., & Qi, S. (2025). MHASegNet: A multi-scale hybrid aggregation network of segmenting coronary artery from CCTA images. Journal of X-Ray Science and Technology. https://doi.org/10.1177/08953996251346484
Vancouver
Li S, Wu Y, Jiang B, Liu L, Zhang T, Sun Y, et al. MHASegNet: A multi-scale hybrid aggregation network of segmenting coronary artery from CCTA images. Journal of X-Ray Science and Technology. 2025. doi:10.1177/08953996251346484
BibTeX
@article{Li2025,
author = {Li, Shang and Wu, Yanan and Jiang, Bojun and Liu, Lingkai and Zhang, Tiande and Sun, Yu and Hou, Jie and Monkam, Patrice and Qian, Wei and Qi, Shouliang},
title = {MHASegNet: A multi-scale hybrid aggregation network of segmenting coronary artery from CCTA images},
journal = {Journal of X-Ray Science and Technology},
year = {2025},
doi = {10.1177/08953996251346484}
}
EUVIMED