{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T09:03:36Z","timestamp":1784106216543,"version":"3.55.0"},"reference-count":58,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Science and Technology Program of Sichuan Province, China","award":["2023YFG0264"],"award-info":[{"award-number":["2023YFG0264"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    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\n                    <jats:italic>vs<\/jats:italic>\n                    . 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\u00a0mm Hausdorff Distance with only 23.43M parameters. Details are available on\n                    <jats:uri xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/Yuyan-Bin\/Synergistic-Network\">https:\/\/github.com\/Yuyan-Bin\/Synergistic-Network<\/jats:uri>\n                    .\n                  <\/jats:p>","DOI":"10.7717\/peerj-cs.3941","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:07:51Z","timestamp":1784102871000},"page":"e3941","source":"Crossref","is-referenced-by-count":0,"title":["Bidirectional Mamba and routing-attention synergistic network for efficient medical image segmentation"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3345-8339","authenticated-orcid":true,"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyan","family":"Bin","sequence":"additional","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Cancer Center, The Second People\u2019s Hospital of Neijiang, Neijiang, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"issue":"1258","key":"10.7717\/peerj-cs.3941\/ref-1","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","article-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians","volume":"43","author":"Bernal","year":"2015","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"10.7717\/peerj-cs.3941\/ref-2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.06623","article-title":"Polyp-SAM++: can a text guided SAM perform better for polyp segmentation?","author":"Biswas","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-3","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/978-981-96-2064-7_18","article-title":"Pubic symphysis-fetal head segmentation network using BiFormer attention mechanism and multipath dilated convolution","volume-title":"MultiMedia Modeling","author":"Cai","year":"2025"},{"key":"10.7717\/peerj-cs.3941\/ref-4","first-page":"205","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"issue":"1","key":"10.7717\/peerj-cs.3941\/ref-5","doi-asserted-by":"publisher","first-page":"44503","DOI":"10.1038\/s41598-025-28088-1","article-title":"Lightweight UNet with multi-module synergy and dual-domain attention for precise skin lesion segmentation","volume":"15","author":"Chen","year":"2025","journal-title":"Scientific Reports"},{"issue":"2","key":"10.7717\/peerj-cs.3941\/ref-6","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3941\/ref-7","first-page":"12021","article-title":"Run, don\u2019t walk: chasing higher flops for faster neural networks","author":"Chen","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-8","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1109\/ISBI.2018.8363547","article-title":"Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)","author":"Codella","year":"2018"},{"issue":"2","key":"10.7717\/peerj-cs.3941\/ref-9","doi-asserted-by":"publisher","first-page":"e1515","DOI":"10.7717\/peerj-cs.1515","article-title":"Optimization of U-shaped pure transformer medical image segmentation network","volume":"9","author":"Dan","year":"2023","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3941\/ref-10","first-page":"12124","article-title":"Cswin transformer: a general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.7717\/peerj-cs.3941\/ref-11","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.7717\/peerj-cs.3941\/ref-12","volume-title":"Modeling sequences with structured state spaces","author":"Gu","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-13","first-page":"12175","article-title":"CMT: convolutional neural networks meet vision transformers","author":"Guo","year":"2022"},{"key":"10.7717\/peerj-cs.3941\/ref-14","first-page":"6202","article-title":"HiFormer: hierarchical multi-scale representations using transformers for medical image segmentation","author":"Heidari","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-15","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"27","key":"10.7717\/peerj-cs.3941\/ref-16","doi-asserted-by":"publisher","first-page":"108784","DOI":"10.1016\/j.compbiomed.2024.108784","article-title":"Channel prior convolutional attention for medical image segmentation","volume":"178","author":"Huang","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"5","key":"10.7717\/peerj-cs.3941\/ref-17","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1109\/TMI.2022.3230943","article-title":"MISSFormer: an effective transformer for 2D medical image segmentation","volume":"42","author":"Huang","year":"2023","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3941\/ref-18","first-page":"1055","article-title":"UNet 3+: a full-scale connected UNet for medical image segmentation","author":"Huang","year":"2020"},{"key":"10.7717\/peerj-cs.3941\/ref-19","doi-asserted-by":"publisher","first-page":"8906","DOI":"10.1109\/tmm.2023.3243616","article-title":"DilateFormer: multi-scale dilated transformer for visual recognition","volume":"25","author":"Jiao","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.7717\/peerj-cs.3941\/ref-20","doi-asserted-by":"publisher","first-page":"139171\u2013139186","DOI":"10.1109\/ACCESS.2023.3340719","article-title":"ps-CALR: periodic-shift cosine annealing learning rate for deep neural networks","volume":"11","author":"Johnson","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3941\/ref-21","article-title":"ADAM: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.7717\/peerj-cs.3941\/ref-22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRPMS.2026.3666783","article-title":"BRAU-Net++: U-shaped hybrid CNN-transformer network for medical image segmentation","author":"Lan","year":"2026","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"key":"10.7717\/peerj-cs.3941\/ref-23","doi-asserted-by":"publisher","DOI":"10.7303\/syn3193805","article-title":"Synapse multi-organ abdominal CT segmentation dataset","author":"Landman","year":"2015"},{"key":"10.7717\/peerj-cs.3941\/ref-24","first-page":"759","article-title":"Polyp-SAM: transfer SAM for polyp segmentation","volume":"12927","author":"Li","year":"2024"},{"key":"10.7717\/peerj-cs.3941\/ref-25","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.7717\/peerj-cs.3941\/ref-26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273","article-title":"VMamba: visual state space model","volume-title":"Advances in Neural Information Processing Systems 37","author":"Liu","year":"2024"},{"key":"10.7717\/peerj-cs.3941\/ref-27","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017"},{"key":"10.7717\/peerj-cs.3941\/ref-28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.7717\/peerj-cs.3941\/ref-29","first-page":"565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"10.7717\/peerj-cs.3941\/ref-30","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1109\/AIIoT65859.2025.11105308","article-title":"Focal-UNet: UNet-like focal modulation for medical image segmentation","author":"Naderi","year":"2025"},{"key":"10.7717\/peerj-cs.3941\/ref-31","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"10.7717\/peerj-cs.3941\/ref-32","first-page":"1","article-title":"Efficient multi-scale attention module with cross-spatial learning","author":"Ouyang","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-33","first-page":"Article 721, 12","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.7717\/peerj-cs.3941\/ref-34","first-page":"6222","article-title":"Medical image segmentation via cascaded attention decoding","author":"Rahman","year":"2023"},{"key":"10.7717\/peerj-cs.3941\/ref-35","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.3941\/ref-36","doi-asserted-by":"publisher","first-page":"108205","DOI":"10.1145\/3767748","article-title":"VM-UNet: vision mamba UNet for medical image segmentation","volume":"10","author":"Ruan","year":"2025","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"10.7717\/peerj-cs.3941\/ref-37","first-page":"10819","article-title":"VSSD: vision mamba with non-causal state space duality","author":"Shi","year":"2025"},{"issue":"11","key":"10.7717\/peerj-cs.3941\/ref-38","doi-asserted-by":"publisher","first-page":"8427","DOI":"10.1007\/s11760-024-03484-8","article-title":"RM-UNet: UNet-like mamba with rotational SSM module for medical image segmentation","volume":"18","author":"Tang","year":"2024","journal-title":"Signal, Image and Video Processing"},{"key":"10.7717\/peerj-cs.3941\/ref-39","article-title":"Quadtree attention for vision transformers","author":"Tang","year":"2022"},{"key":"10.7717\/peerj-cs.3941\/ref-40","first-page":"36","article-title":"Medical transformer: gated axial-attention for medical image segmentation","author":"Valanarasu","year":"2021"},{"key":"10.7717\/peerj-cs.3941\/ref-41","volume-title":"Python tutorial","volume":"620","author":"Van Rossum","year":"1995"},{"key":"10.7717\/peerj-cs.3941\/ref-42","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)","author":"Vaswani","year":"2017"},{"key":"10.7717\/peerj-cs.3941\/ref-43","first-page":"1","article-title":"Mamba-SEUNet: mamba UNet for monaural speech enhancement","author":"Wang","year":"2025a"},{"key":"10.7717\/peerj-cs.3941\/ref-44","first-page":"1","article-title":"Clinically robust polyp segmentation: enhanced generalization and perturbation resistance","author":"Wang","year":"2025b"},{"key":"10.7717\/peerj-cs.3941\/ref-45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.05079","article-title":"Mamba-UNet: UNet-like pure visual mamba for medical image segmentation","author":"Wang","year":"2024"},{"key":"10.7717\/peerj-cs.3941\/ref-46","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"issue":"1","key":"10.7717\/peerj-cs.3941\/ref-47","doi-asserted-by":"publisher","first-page":"103654","DOI":"10.1016\/j.media.2025.103654","article-title":"Diff-UNet: a diffusion embedded network for robust 3D medical image segmentation","volume":"105","author":"Xing","year":"2025","journal-title":"Medical Image Analysis"},{"issue":"1","key":"10.7717\/peerj-cs.3941\/ref-48","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TMI.2025.3589797","article-title":"SegMamba-V2: long-range sequential modeling mamba for general 3-D medical image segmentation","volume":"45","author":"Xing","year":"2026","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3941\/ref-49","first-page":"578","article-title":"SegMamba: long-range sequential modeling mamba for 3D medical image segmentation","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2024","author":"Xing","year":"2024a"},{"key":"10.7717\/peerj-cs.3941\/ref-50","first-page":"140","article-title":"NestedFormer: nested modality-aware transformer for brain tumor segmentation","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2022","author":"Xing","year":"2022"},{"issue":"4","key":"10.7717\/peerj-cs.3941\/ref-51","doi-asserted-by":"publisher","first-page":"2115","DOI":"10.1109\/JBHI.2024.3360239","article-title":"Hybrid masked image modeling for 3D medical image segmentation","volume":"28","author":"Xing","year":"2024b","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.7717\/peerj-cs.3941\/ref-52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.05007","article-title":"HC-Mamba: vision mamba with hybrid convolutional techniques for medical image segmentation","author":"Xu","year":"2024"},{"issue":"8","key":"10.7717\/peerj-cs.3941\/ref-53","doi-asserted-by":"publisher","first-page":"106626","DOI":"10.1016\/j.compbiomed.2023.106626","article-title":"DCSAU-Net: a deeper and more compact split-attention U-Net for medical image segmentation","volume":"154","author":"Xu","year":"2023","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.3941\/ref-54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.03849","article-title":"MedMamba: vision mamba for medical image classification","author":"Yue","year":"2024"},{"key":"10.7717\/peerj-cs.3941\/ref-55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.11289","article-title":"HMT-UNet: a hybird mamba-transformer vision UNet for medical image segmentation","author":"Zhang","year":"2024a"},{"key":"10.7717\/peerj-cs.3941\/ref-56","first-page":"335","article-title":"VM-UNet-v2: rethinking vision mamba UNet for medical image segmentation","author":"Zhang","year":"2024b"},{"key":"10.7717\/peerj-cs.3941\/ref-57","first-page":"3","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"10.7717\/peerj-cs.3941\/ref-58","first-page":"10323","article-title":"BiFormer: vision transformer with bi-level routing attention","author":"Zhu","year":"2023"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3941.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3941.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3941.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3941.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:07:57Z","timestamp":1784102877000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3941"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":58,"alternative-id":["10.7717\/peerj-cs.3941"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3941","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"e3941"}}