CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ Segmentation

2026-03-20

AI Summary

This work addresses the limitations of existing Mamba-based methods in abdominal multi-organ segmentation, which neglect inter-channel anatomical semantic coordination and lack explicit boundary-aware mechanisms. To overcome these issues, we propose CS-MUNet, which uniquely reconfigures the channel dimension as the sequence dimension within a state space model (SSM) to effectively capture channel-wise semantic synergy. Furthermore, boundary-aware state transitions are achieved by dynamically modulating Mamba’s scanning parameters using a boundary posterior map. Integrating a dual-stream channel-spatial architecture, a Bayesian attention mechanism, and a two-branch weight allocation strategy, CS-MUNet significantly outperforms current state-of-the-art methods on two public datasets, establishing a novel SSM-based paradigm for multi-organ segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning
• Multiagent Systems: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Recently Mamba-based methods have shown promise in abdominal organ segmentation. However, existing approaches neglect cross-channel anatomical semantic collaboration and lack explicit boundary-aware feature fusion mechanisms. To address these limitations, we propose CS-MUNet with two purpose-built modules. The Boundary-Aware State Mamba module employs a Bayesian-attention framework to generate pixel-level boundary posterior maps, injected directly into Mamba's core scan parameters to embed boundary awareness into the SSM state transition mechanism, while dual-branch weight allocation enables complementary modulation between global and local structural representations. The Channel Mamba State Aggregation module redefines the channel dimension as the SSM sequence dimension to explicitly model cross-channel anatomical semantic collaboration in a data-driven manner. Experiments on two public benchmarks demonstrate that CS-MUNet consistently outperforms state-of-the-art methods across multiple metrics, establishing a new SSM modeling paradigm that jointly addresses channel semantic collaboration and boundary-aware feature fusion for abdominal multi-organ segmentation.

Problem

• multi-organ segmentation
• cross-channel semantic collaboration
• boundary-aware feature fusion
• Mamba-based methods
• abdominal organ segmentation

Innovation

• Mamba
• boundary-aware fusion
• channel-spatial modeling
• state space model
• multi-organ segmentation