Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation
Abstract
Based on U-shaped architecture for medical image segmentation faces three fundamental challenges limiting clinical deployment: (1) architectural homogeneity problems where uniform mechanism deployment overlooks distinct encoder-decoder requirements, (2) skip connection feature fusion limitations with insufficient spatial-channel attention integration, (3) computational efficiency versus performance trade-offs. We propose a heterogeneous U-shaped architecture that strategically deploys specialized mechanisms based on component-specific functional requirements. Our approach utilizes Vision Mamba with Non-causal State Space Duality (VSSD) in encoder/bottleneck for efficient global context extraction, Bi-Level Routing Attention (BRA) in decoder for adaptive detail recovery, and introduces Spatial-Channel Synergistic Attention (SCSA) in skip connections to optimize multi-scale feature integration with only 0.1M additional parameters. Extensive experiments across four diverse datasets demonstrate exceptional performance: for example on Synapse dataset, our model achieves 84% Dice Similarity Coefficient and 13.76mm Hausdorff Distance with only 23.43M parameters. Details are available on \href{https://github.com/Yuyan-Bin/Synergistic-Networka}{Github}.