VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
This addresses vessel segmentation for clinical applications, but it is incremental as it adapts existing self-supervised learning methods to a specific domain.
The paper tackled the problem of weak vascular representations in vessel segmentation for X-ray angiograms due to class imbalance, by introducing VasoMIM, a masked image modeling framework that integrates anatomical knowledge, achieving state-of-the-art performance across three datasets.
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.