Coronary Artery Classification Using Deep Learning

Mosig D, Marwan M, Achenbach S, Maier A (2025)

Publication Type: Conference contribution

Publication year: 2025

Original Authors: D. Mosig, M. Marwan, S. Achenbach, A. Maier

Pages Range: 1-1

Event location: Yokohama JP

DOI: 10.1109/NSS/MIC/RTSD57106.2025.11287049

Abstract

Automated interpretation of coronary angiography has the potential to improve diagnostic efficiency and reduce intra- and inter-observer variability in the assessment of coronary artery disease. A critical early step in this process is the classification of angiographic sequences into left coronary artery (LCA) and right coronary artery (RCA) views. In this study, we evaluate three deep learning models: ResNet50, Swin Transformer (Swin-B), and Vision Transformer (ViT-B) for single-frame-based LCA/RCA classification. We use a majority-voting scheme to aggregate framelevel predictions into robust video-level classifications. Our dataset comprises 45,901 frames from 2,499 angiographic videos collected from a single-center cohort of 376 patients. ResNet50, trained from scratch on our domain-specific data, consistently outperformed both transformer-based models, which were pretrained on natural images. At video-level, ResNet50 achieved an F1-score of 0.9897, followed by ViT-B (0.9475) and Swin-B (0.9225). The transformer models were more sensitive to class imbalance, resulting in lower specificity. Applying majority voting significantly improved all models' performance by an average of 1.98 %. These results demonstrate that single-frame-based classification, combined with temporal aggregation, can achieve high accuracy while retaining flexibility for downstream tasks.

Authors with CRIS profile

Daniel Mosig Department of Medicine 2 – Cardiology and Angiology Mohamed Marwan Department of Medicine 2 – Cardiology and Angiology Stephan Achenbach Lehrstuhl für Innere Medizin II Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Mosig, D., Marwan, M., Achenbach, S., & Maier, A. (2025). Coronary Artery Classification Using Deep Learning. In Proceedings of the 2025 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD) (pp. 1-1). Yokohama, JP.

MLA:

Mosig, Daniel, et al. "Coronary Artery Classification Using Deep Learning." Proceedings of the 2025 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD), Yokohama 2025. 1-1.

BibTeX: Download