{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:21:41Z","timestamp":1783131701636,"version":"3.54.6"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["14380079"],"award-info":[{"award-number":["14380079"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.cviu.2026.104787","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:09:10Z","timestamp":1777129750000},"page":"104787","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A hybrid Mamba-Transformer model with progressive feature enhancement for medical image segmentation"],"prefix":"10.1016","volume":"269","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5296-6501","authenticated-orcid":false,"given":"Huanhuan","family":"Lv","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanqi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songru","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104787_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103910","article-title":"Twin-SegNet: Dynamically coupled complementary segmentation networks for generalized medical image segmentation","volume":"240","author":"Ahmed","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104787_b2","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3435571","article-title":"Medical image segmentation review: The success of u-net","author":"Azad","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104787_b3","series-title":"ISIC 2017-skin lesion analysis towards melanoma detection","author":"Berseth","year":"2017"},{"key":"10.1016\/j.cviu.2026.104787_b4","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104787_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104436","article-title":"UM-Mamba: An efficient U-network with medical visual state space for medical image segmentation","author":"Chen","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104787_b6","doi-asserted-by":"crossref","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","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.cviu.2026.104787_b7","series-title":"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic)","author":"Codella","year":"2019"},{"key":"10.1016\/j.cviu.2026.104787_b8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","volume":"107","author":"Elfwing","year":"2018","journal-title":"Neural Netw."},{"key":"10.1016\/j.cviu.2026.104787_b9","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104787_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110491","article-title":"UCTNet: Uncertainty-guided CNN-transformer hybrid networks for medical image segmentation","volume":"152","author":"Guo","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104787_b11","article-title":"Improving a segment anything model for segmenting low-quality medical images via an adapter","author":"Han","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104787_b12","doi-asserted-by":"crossref","unstructured":"Hatamizadeh,\u00a0A., Kautz,\u00a0J., 2025. Mambavision: A hybrid mamba-transformer vision backbone. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision.","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"10.1016\/j.cviu.2026.104787_b13","series-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"10.1016\/j.cviu.2026.104787_b14","series-title":"International Conference on Machine Learning","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"issue":"2","key":"10.1016\/j.cviu.2026.104787_b15","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"NnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nature Methods"},{"key":"10.1016\/j.cviu.2026.104787_b16","series-title":"Proc. MICCAI Multi-Atlas Labeling beyond Cranial Vault\u2014Workshop Challenge","first-page":"12","article-title":"Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge","volume":"Vol. 5","author":"Landman","year":"2015"},{"issue":"4","key":"10.1016\/j.cviu.2026.104787_b17","doi-asserted-by":"crossref","first-page":"2083","DOI":"10.1109\/TCSVT.2023.3300846","article-title":"ERDUnet: An efficient residual double-coding unet for medical image segmentation","volume":"34","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2026.104787_b18","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0Z., Lin,\u00a0Y., Cao,\u00a0Y., Hu,\u00a0H., Wei,\u00a0Y., Zhang,\u00a0Z., Lin,\u00a0S., Guo,\u00a0B., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.cviu.2026.104787_b19","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"Vmamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104787_b20","article-title":"Multi-scale feature fusion based SAM for high-quality few-shot medical image segmentation","author":"Liu","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"issue":"5","key":"10.1016\/j.cviu.2026.104787_b21","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1109\/TMI.2024.3354673","article-title":"Cosst: Multi-organ segmentation with partially labeled datasets using comprehensive supervisions and self-training","volume":"43","author":"Liu","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.cviu.2026.104787_b22","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.cviu.2026.104787_b23","series-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"10.1016\/j.cviu.2026.104787_b24","series-title":"Attention U-Net: Learning where to look for the pancreas. in: medical imaging with deep learning","author":"Oktay","year":"2018"},{"key":"10.1016\/j.cviu.2026.104787_b25","doi-asserted-by":"crossref","unstructured":"Perera,\u00a0S., Navard,\u00a0P., Yilmaz,\u00a0A., 2024. Segformer3d: an efficient transformer for 3d medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4981\u20134988.","DOI":"10.1109\/CVPRW63382.2024.00503"},{"key":"10.1016\/j.cviu.2026.104787_b26","series-title":"Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.cviu.2026.104787_b27","series-title":"Vm-unet: Vision mamba unet for medical image segmentation","author":"Ruan","year":"2024"},{"key":"10.1016\/j.cviu.2026.104787_b28","series-title":"IEEE International Conference on Bioinformatics and Biomedicine","first-page":"1150","article-title":"Malunet: A multi-attention and light-weight unet for skin lesion segmentation","author":"Ruan","year":"2022"},{"key":"10.1016\/j.cviu.2026.104787_b29","series-title":"MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation","author":"Ruan","year":"2022"},{"key":"10.1016\/j.cviu.2026.104787_b30","series-title":"2023 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"2213","article-title":"An improved vision-transformer network for skin cancer classification","author":"Shajimon","year":"2023"},{"key":"10.1016\/j.cviu.2026.104787_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118625","article-title":"Multi-organ segmentation network for abdominal CT images based on spatial attention and deformable convolution","volume":"211","author":"Shen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104787_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104151","article-title":"HAD-Net: An attention U-based network with hyper-scale shifted aggregating and max-diagonal sampling for medical image segmentation","volume":"249","author":"Sun","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104787_b33","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104787_b34","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0W., Dai,\u00a0J., Chen,\u00a0Z., Huang,\u00a0Z., Li,\u00a0Z., Zhu,\u00a0X., Hu,\u00a0X., Lu,\u00a0T., Lu,\u00a0L., Li,\u00a0H., et al., 2023. Internimage: Exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14408\u201314419.","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"10.1016\/j.cviu.2026.104787_b35","doi-asserted-by":"crossref","unstructured":"Wu,\u00a0J., Ji,\u00a0W., Fu,\u00a0H., Xu,\u00a0M., Jin,\u00a0Y., Xu,\u00a0Y., 2024. Medsegdiff-v2: Diffusion-based medical image segmentation with transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38, pp. 6030\u20136038.","DOI":"10.1609\/aaai.v38i6.28418"},{"key":"10.1016\/j.cviu.2026.104787_b36","article-title":"H-vmunet: High-order vision mamba unet for medical image segmentation","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cviu.2026.104787_b37","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"578","article-title":"Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation","author":"Xing","year":"2024"},{"key":"10.1016\/j.cviu.2026.104787_b38","series-title":"Hc-mamba: Vision mamba with hybrid convolutional techniques for medical image segmentation","author":"Xu","year":"2024"},{"key":"10.1016\/j.cviu.2026.104787_b39","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24","first-page":"14","article-title":"Transfuse: Fusing transformers and cnns for medical image segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.cviu.2026.104787_b40","series-title":"Nnformer: Interleaved transformer for volumetric segmentation","author":"Zhou","year":"2021"},{"issue":"6","key":"10.1016\/j.cviu.2026.104787_b41","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"Unet++: Redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.cviu.2026.104787_b42","article-title":"Merging context clustering with visual state space models for medical image segmentation","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001542?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001542?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T01:56:58Z","timestamp":1783130218000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":42,"alternative-id":["S1077314226001542"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104787","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A hybrid Mamba-Transformer model with progressive feature enhancement for medical image segmentation","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104787","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104787"}}