VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation

2025-08-14

AI Summary

In X-ray angiography, the scarcity of annotated data and severe class imbalance between vessels and background hinder conventional mask image modeling (MIM) from learning robust vascular representations. To address this, we propose an anatomy-guided self-supervised pretraining framework: (1) a vessel-region-prioritized masking strategy that explicitly incorporates vascular topological and morphological priors; and (2) a cross-image anatomical consistency loss that enforces semantic coherence of vascular structures across samples. Our method enhances vascular feature representation without requiring additional annotations. Evaluated on three public angiography datasets, it achieves state-of-the-art segmentation performance using only a small number of labeled samples—demonstrating its effectiveness in low-resource settings and its capacity to leverage unlabeled data efficiently.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Unsupervised & Self-Supervised Learning
• Knowledge Representation and Reasoning: Argumentation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Representation, semantic annotation, enhancement, enrichments, access and/or integration of a variety of data on the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate vessel segmentation in X-ray angiograms is crucial for numerous clinical applications. However, the scarcity of annotated data presents a significant challenge, which has driven the adoption of self-supervised learning (SSL) methods such as masked image modeling (MIM) to leverage large-scale unlabeled data for learning transferable representations. Unfortunately, conventional MIM often fails to capture vascular anatomy because of the severe class imbalance between vessel and background pixels, leading to weak vascular representations. To address this, we introduce Vascular anatomy-aware Masked Image Modeling (VasoMIM), a novel MIM framework tailored for X-ray angiograms that explicitly integrates anatomical knowledge into the pre-training process. Specifically, it comprises two complementary components: anatomy-guided masking strategy and anatomical consistency loss. The former preferentially masks vessel-containing patches to focus the model on reconstructing vessel-relevant regions. The latter enforces consistency in vascular semantics between the original and reconstructed images, thereby improving the discriminability of vascular representations. Empirically, VasoMIM achieves state-of-the-art performance across three datasets. These findings highlight its potential to facilitate X-ray angiogram analysis.

Problem

• Addresses vessel segmentation challenges in X-ray angiograms
• Overcomes class imbalance in conventional masked image modeling
• Integrates vascular anatomy knowledge into self-supervised learning

Innovation

• Anatomy-aware masking for vessel focus
• Anatomical consistency loss for semantics
• Self-supervised learning for angiograms