Vascular anatomy-aware self-supervised pre-training for X-ray angiogram analysis

2026-02-12

AI Summary

This work addresses the limitations in X-ray angiography analysis caused by scarce annotated data and the absence of effective self-supervised pretraining frameworks. It introduces, for the first time, an explicit incorporation of vascular anatomical priors into self-supervised learning through an anatomy-guided masked image modeling strategy and an anatomical consistency loss, thereby enhancing the model’s understanding of vascular semantics and structure. The authors also construct XA-170K, the largest X-ray angiography pretraining dataset to date, and establish the first self-supervised benchmark for this domain. Evaluated across four downstream tasks on six datasets, the proposed method consistently outperforms existing approaches, demonstrating superior transferability and generalization capability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Unsupervised & Self-Supervised Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

X-ray angiography is the gold standard imaging modality for cardiovascular diseases. However, current deep learning approaches for X-ray angiogram analysis are severely constrained by the scarcity of annotated data. While large-scale self-supervised learning (SSL) has emerged as a promising solution, its potential in this domain remains largely unexplored, primarily due to the lack of effective SSL frameworks and large-scale datasets. To bridge this gap, we introduce a vascular anatomy-aware masked image modeling (VasoMIM) framework that explicitly integrates domain-specific anatomical knowledge. Specifically, VasoMIM comprises two key designs: an anatomy-guided masking strategy and an anatomical consistency loss. The former strategically masks vessel-containing patches to compel the model to learn robust vascular semantics, while the latter preserves structural consistency of vessels between original and reconstructed images, enhancing the discriminability of the learned representations. In conjunction with VasoMIM, we curate XA-170K, the largest X-ray angiogram pre-training dataset to date. We validate VasoMIM on four downstream tasks across six datasets, where it demonstrates superior transferability and achieves state-of-the-art performance compared to existing methods. These findings highlight the significant potential of VasoMIM as a foundation model for advancing a wide range of X-ray angiogram analysis tasks. VasoMIM and XA-170K will be available at https://github.com/Dxhuang-CASIA/XA-SSL.

Problem

• X-ray angiography
• self-supervised learning
• annotated data scarcity
• vascular anatomy
• medical image analysis

Innovation

• vascular anatomy-aware
• masked image modeling
• self-supervised learning
• anatomical consistency loss
• X-ray angiography