CM-UNet: A Self-Supervised Learning-Based Model for Coronary Artery Segmentation in X-Ray Angiography

TL;DR

This paper introduces CM-UNet, a self-supervised learning model that significantly improves coronary artery segmentation in X-ray angiography with limited annotated data, enhancing clinical diagnosis and reducing annotation efforts.

Contribution

The study demonstrates the effectiveness of self-supervised pre-training combined with transfer learning for coronary artery segmentation, requiring far fewer annotated images than traditional methods.

Findings

Pre-training with self-supervised learning improves segmentation accuracy.

Fine-tuning with only 18 images causes less performance drop.

The approach reduces the need for large annotated datasets.

Abstract

Accurate segmentation of coronary arteries remains a significant challenge in clinical practice, hindering the ability to effectively diagnose and manage coronary artery disease. The lack of large, annotated datasets for model training exacerbates this issue, limiting the development of automated tools that could assist radiologists. To address this, we introduce CM-UNet, which leverages self-supervised pre-training on unannotated datasets and transfer learning on limited annotated data, enabling accurate disease detection while minimizing the need for extensive manual annotations. Fine-tuning CM-UNet with only 18 annotated images instead of 500 resulted in a 15.2% decrease in Dice score, compared to a 46.5% drop in baseline models without pre-training. This demonstrates that self-supervised learning can enhance segmentation performance and reduce dependence on large datasets. This is one of the first studies to highlight the importance of self-supervised learning in improving coronary artery segmentation from X-ray angiography, with potential implications for advancing diagnostic accuracy in clinical practice. By enhancing segmentation accuracy in X-ray angiography images, the proposed approach aims to improve clinical workflows, reduce radiologists' workload, and accelerate disease detection, ultimately contributing to better patient outcomes. The source code is publicly available at https://github.com/CamilleChallier/Contrastive-Masked-UNet.