SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI Volumes

2025-08-17

AI Summary

Liver lesion segmentation in MRI volumes of cirrhotic patients faces challenges including complex anatomical structures, ill-defined lesion boundaries, and insufficient 3D contextual modeling, leading to limited interpretability and accuracy in existing methods. To address these issues, we propose SRMA-Mamba, a novel network featuring: (1) a spatial-anatomy-aware Mamba module for efficient long-range 3D spatial dependency modeling; (2) tri-planar global feature fusion coupled with hierarchical encoding feedback to enhance multi-scale anatomical consistency; and (3) a spatial reverse attention module for progressive boundary refinement. Evaluated on a public dataset, SRMA-Mamba achieves state-of-the-art performance, improving Dice score by 3.2% over prior methods. Crucially, its segmentation outputs exhibit explicit anatomical interpretability, enabling reliable 3D quantitative support for clinical auxiliary diagnosis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Learning with Manifolds
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Liver Cirrhosis plays a critical role in the prognosis of chronic liver disease. Early detection and timely intervention are critical in significantly reducing mortality rates. However, the intricate anatomical architecture and diverse pathological changes of liver tissue complicate the accurate detection and characterization of lesions in clinical settings. Existing methods underutilize the spatial anatomical details in volumetric MRI data, thereby hindering their clinical effectiveness and explainability. To address this challenge, we introduce a novel Mamba-based network, SRMA-Mamba, designed to model the spatial relationships within the complex anatomical structures of MRI volumes. By integrating the Spatial Anatomy-Based Mamba module (SABMamba), SRMA-Mamba performs selective Mamba scans within liver cirrhotic tissues and combines anatomical information from the sagittal, coronal, and axial planes to construct a global spatial context representation, enabling efficient volumetric segmentation of pathological liver structures. Furthermore, we introduce the Spatial Reverse Attention module (SRMA), designed to progressively refine cirrhotic details in the segmentation map, utilizing both the coarse segmentation map and hierarchical encoding features. Extensive experiments demonstrate that SRMA-Mamba surpasses state-of-the-art methods, delivering exceptional performance in 3D pathological liver segmentation. Our code is available for public: {color{blue}{https://github.com/JunZengz/SRMA-Mamba}}.

Problem

• Accurate segmentation of pathological liver in MRI volumes
• Underutilization of spatial details in existing MRI methods
• Complex anatomical structures complicating lesion detection

Innovation

• Spatial Anatomy-Based Mamba module for MRI scans
• Combines sagittal, coronal, axial plane data
• Spatial Reverse Attention refines segmentation details