SSFMamba: Symmetry-driven Spatial-Frequency Feature Fusion for 3D Medical Image Segmentation

2025-08-05

AI Summary

To address insufficient global spatial modeling in 3D medical image segmentation, the neglect of conjugate symmetry in existing frequency-domain methods, and discrepancies between spatial and frequency domain feature distributions, this paper proposes a symmetry-driven dual-domain feature fusion network. Methodologically, we design a symmetry-aware frequency-domain feature extraction module that explicitly enforces the conjugate symmetry constraint on Fourier coefficients; further, we integrate the Mamba architecture with a 3D multi-directional scanning strategy to jointly model long-range dependencies and fuse heterogeneous spatial-frequency features. Our key contribution is the first incorporation of the physical prior of conjugate symmetry into the Mamba framework, enabling an end-to-end dual-branch architecture. Evaluated on BraTS2020 and BraTS2023, our method achieves state-of-the-art performance, improving Dice scores by 1.2–2.4%, while simultaneously enhancing robustness and fine structural preservation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Feature Construction/Reformulation
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

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: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

In light of the spatial domain's limited capacity for modeling global context in 3D medical image segmentation, emerging approaches have begun to incorporate frequency domain representations. However, straightforward feature extraction strategies often overlook the unique properties of frequency domain information, such as conjugate symmetry. They also fail to account for the fundamental differences in data distribution between the spatial and frequency domains, which can ultimately dilute or obscure the complementary strengths that frequency-based representations offer. In this paper, we propose SSFMamba, a Mamba based Symmetry-driven Spatial-Frequency feature fusion network for 3D medical image segmentation. SSFMamba employs a complementary dual-branch architecture that extracts features from both the spatial and frequency domains, and leverages a Mamba block to fuse these heterogeneous features to preserve global context while reinforcing local details. In the frequency domain branch, we harness Mamba's exceptional capability to extract global contextual information in conjunction with the synergistic effect of frequency domain features to further enhance global modeling. Moreover, we design a 3D multi-directional scanning mechanism to strengthen the fusion of local and global cues. Extensive experiments on the BraTS2020 and BraTS2023 datasets demonstrate that our approach consistently outperforms state-of-the-art methods across various evaluation metrics.

Problem

• Enhancing 3D medical image segmentation via spatial-frequency feature fusion
• Addressing conjugate symmetry and data distribution gaps in frequency domain
• Improving global context modeling with Mamba-based dual-branch architecture

Innovation

• Dual-branch architecture for spatial-frequency fusion
• Mamba block enhances global and local feature integration
• 3D multi-directional scanning improves local-global fusion