VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4985-4993
DOI: 10.1609/aaai.v40i6.42503 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von De-Xing Huang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Huang, D., Zhou, X., Gui, M., Xie, X., Liu, S., Wang, S., Xiang, T., Ma, R., Xiao, N., & Hou, Z. (2026). VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4985-4993. https://doi.org/10.1609/aaai.v40i6.42503
Vancouver
Huang D, Zhou X, Gui M, Xie X, Liu S, Wang S, et al. VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4985-4993. doi:10.1609/aaai.v40i6.42503
BibTeX
@article{Huang2026,
author = {Huang, De-Xing and Zhou, Xiao-Hu and Gui, Mei-Jiang and Xie, Xiao-Liang and Liu, Shi-Qi and Wang, Shuang-Yi and Xiang, Tian-Yu and Ma, Rui-Ze and Xiao, Nu-Fang and Hou, Zeng-Guang},
title = {VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4985--4993},
doi = {10.1609/aaai.v40i6.42503}
}
EUVIMED