Multi-Domain Brain Vessel Segmentation Through Feature Disentanglement

2025-10-01

AI Summary

Automatic cerebral vascular segmentation faces challenges in cross-modality and multi-center generalization, as existing single-modality models struggle to accurately capture complex vascular tree structures. To address this, we propose a multi-domain adaptive segmentation framework that requires no domain-specific architectural design or data normalization. Our method employs feature disentanglement to separate vascular appearance from spatial geometry, and leverages image-to-image translation for label-preserving cross-domain adaptation—enabling fine-grained arterial/venous segmentation. Integrating deep generative modeling, unsupervised domain adaptation, and disentangled representation learning, it effectively reduces inter-domain distribution shifts while preserving critical morphological information. Experiments demonstrate high robustness and strong generalization across multiple heterogeneous datasets using only a small number of annotated samples. The code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The intricate morphology of brain vessels poses significant challenges for automatic segmentation models, which usually focus on a single imaging modality. However, accurately treating brain-related conditions requires a comprehensive understanding of the cerebrovascular tree, regardless of the specific acquisition procedure. Our framework effectively segments brain arteries and veins in various datasets through image-to-image translation while avoiding domain-specific model design and data harmonization between the source and the target domain. This is accomplished by employing disentanglement techniques to independently manipulate different image properties, allowing them to move from one domain to another in a label-preserving manner. Specifically, we focus on manipulating vessel appearances during adaptation while preserving spatial information, such as shapes and locations, which are crucial for correct segmentation. Our evaluation effectively bridges large and varied domain gaps across medical centers, image modalities, and vessel types. Additionally, we conduct ablation studies on the optimal number of required annotations and other architectural choices. The results highlight our framework's robustness and versatility, demonstrating the potential of domain adaptation methodologies to perform cerebrovascular image segmentation in multiple scenarios accurately. Our code is available at https://github.com/i-vesseg/MultiVesSeg.

Problem

• Segmenting brain vessels across multiple imaging modalities and domains
• Overcoming domain gaps between medical centers and vessel types
• Preserving spatial vessel information during domain adaptation

Innovation

• Feature disentanglement for domain adaptation
• Image-to-image translation preserving spatial information
• Segmentation across multiple domains without harmonization