Topological-Aware Regularization for Semi-Supervised Intracranial Aneurysm Vessel Segmentation

Feiyang Xiao, Yichi Zhang, Xigui Li, Yuanye Zhou, Chen Jiang, Xin Guo, Limei Han, Yuxin Li, Fengping Zhu, Yuan Cheng
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:620-636, 2026.

Abstract

Accurate segmentation of intracranial aneurysm and their parent vessels (IA-Vessel) from magnetic resonance angiography is a critical prerequisite for computational fluid dynamics-based rupture risk assessment. While deep learning methods can automate this laborious task, they are hindered by the high cost and scarcity of expert annotations. Most existing semi-supervised methods focus on enforcing regional constraints while largely ignoring topological constraints, which is insensitive to subtle but critical errors like vessel adhesion or surface irregularities, which are often unsuitable for downstream applications. To address this gap, we introduce topological-aware regularization (TAR) by incorporating the learning of local vascular topology to ensure the precise and geometrically correct segmentation of the IA-Vessel complex using only a small amount of labeled data. Experimental results on a multi-center MRA dataset show that our framework efficiently utilizes unlabeled data and outperforms state-of-the-art semi-supervised segmentation methods. Instead of being restricted to a fixed framework, TAR is a plug-and-play strategy that can be seamlessly integrated into various semi-supervised frameworks to further boost their performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-xiao26a, title = {Topological-Aware Regularization for Semi-Supervised Intracranial Aneurysm Vessel Segmentation}, author = {Xiao, Feiyang and Zhang, Yichi and Li, Xigui and Zhou, Yuanye and Jiang, Chen and Guo, Xin and Han, Limei and Li, Yuxin and Zhu, Fengping and Cheng, Yuan}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {620--636}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/xiao26a/xiao26a.pdf}, url = {https://proceedings.mlr.press/v315/xiao26a.html}, abstract = {Accurate segmentation of intracranial aneurysm and their parent vessels (IA-Vessel) from magnetic resonance angiography is a critical prerequisite for computational fluid dynamics-based rupture risk assessment. While deep learning methods can automate this laborious task, they are hindered by the high cost and scarcity of expert annotations. Most existing semi-supervised methods focus on enforcing regional constraints while largely ignoring topological constraints, which is insensitive to subtle but critical errors like vessel adhesion or surface irregularities, which are often unsuitable for downstream applications. To address this gap, we introduce topological-aware regularization (TAR) by incorporating the learning of local vascular topology to ensure the precise and geometrically correct segmentation of the IA-Vessel complex using only a small amount of labeled data. Experimental results on a multi-center MRA dataset show that our framework efficiently utilizes unlabeled data and outperforms state-of-the-art semi-supervised segmentation methods. Instead of being restricted to a fixed framework, TAR is a plug-and-play strategy that can be seamlessly integrated into various semi-supervised frameworks to further boost their performance.} }
Endnote
%0 Conference Paper %T Topological-Aware Regularization for Semi-Supervised Intracranial Aneurysm Vessel Segmentation %A Feiyang Xiao %A Yichi Zhang %A Xigui Li %A Yuanye Zhou %A Chen Jiang %A Xin Guo %A Limei Han %A Yuxin Li %A Fengping Zhu %A Yuan Cheng %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-xiao26a %I PMLR %P 620--636 %U https://proceedings.mlr.press/v315/xiao26a.html %V 315 %X Accurate segmentation of intracranial aneurysm and their parent vessels (IA-Vessel) from magnetic resonance angiography is a critical prerequisite for computational fluid dynamics-based rupture risk assessment. While deep learning methods can automate this laborious task, they are hindered by the high cost and scarcity of expert annotations. Most existing semi-supervised methods focus on enforcing regional constraints while largely ignoring topological constraints, which is insensitive to subtle but critical errors like vessel adhesion or surface irregularities, which are often unsuitable for downstream applications. To address this gap, we introduce topological-aware regularization (TAR) by incorporating the learning of local vascular topology to ensure the precise and geometrically correct segmentation of the IA-Vessel complex using only a small amount of labeled data. Experimental results on a multi-center MRA dataset show that our framework efficiently utilizes unlabeled data and outperforms state-of-the-art semi-supervised segmentation methods. Instead of being restricted to a fixed framework, TAR is a plug-and-play strategy that can be seamlessly integrated into various semi-supervised frameworks to further boost their performance.
APA
Xiao, F., Zhang, Y., Li, X., Zhou, Y., Jiang, C., Guo, X., Han, L., Li, Y., Zhu, F. & Cheng, Y.. (2026). Topological-Aware Regularization for Semi-Supervised Intracranial Aneurysm Vessel Segmentation. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:620-636 Available from https://proceedings.mlr.press/v315/xiao26a.html.

Related Material