Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation
PeerJ Computer Science · 15.07.2026 · 12 · e3941
DOI: 10.7717/peerj-cs.3941 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 15.07.2026. Verfasst von Bo Li und 3 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Science and Technology Program of Sichuan Province, China.
Abstract (Originalsprache)
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, and (3) computational efficiency vs . 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 0.01M additional parameters. Extensive experiments across four diverse datasets demonstrate exceptional performance: for example on Synapse dataset, our model achieves 84% Dice Similarity Coefficient and 13.76 mm Hausdorff Distance with only 23.43M parameters. Details are available on https://github.com/Yuyan-Bin/Synergistic-Network .
Förderung
- The Science and Technology Program of Sichuan Province, China
Zitieren
APA
Li, B., Bin, Y., Li, H., & Zhou, W. (2026). Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation. PeerJ Computer Science, 12, e3941. https://doi.org/10.7717/peerj-cs.3941
Vancouver
Li B, Bin Y, Li H, Zhou W. Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation. PeerJ Computer Science. 2026;12:e3941. doi:10.7717/peerj-cs.3941
BibTeX
@article{Li2026,
author = {Li, Bo and Bin, Yuyan and Li, Haijun and Zhou, Wei},
title = {Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3941},
doi = {10.7717/peerj-cs.3941}
}
EUVIMED