VesMamba: Vessel Morphology-Enhanced State Space Model for Cerebrovascular Delineation

Accurate delineation of cerebrovascular structures from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) and Computed Tomography Angiography (CTA) is essential for the clinical diagnosis and treatment of cerebrovascular diseases. However, the intricate topology and fine-scale nature of cerebral vessels pose significant challenges for deep learning methods, which often struggle to capture long-range dependencies and precise morphological details. In this work, we propose VesMamba, a deep learning framework that integrates explicit vascular morphological priors into a state-space model. Unlike generic SSM-based methods that rely on fixed scanning patterns, we introduce a Tri-oriented Vessel-aware Mamba (ToVM) module, which dynamically reorders input 1D sequences using cerebrovascular edge features to better model complex vascular structures. Complementarily, we present the 3D Large-Small Gated Convolution (LSGC) module after the ToVM module to preserve critical spatial information. We conducted extensive experiments on two TOF-MRA and one CTA dataset, comparing our method with eight state-of-the-art approaches. Our results show that VesMamba achieves superior performance on the majority of evaluation metrics relative to all competing methods.