{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:52:21Z","timestamp":1782485541471,"version":"3.54.5"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100014103","name":"Key Technology Research and Development Program of Shandong","doi-asserted-by":"publisher","award":["2024TSGC0755"],"award-info":[{"award-number":["2024TSGC0755"]}],"id":[{"id":"10.13039\/100014103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732022"],"award-info":[{"award-number":["2023M732022"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013050","name":"Guangdong Provincial Applied Science and Technology Research and Development Program","doi-asserted-by":"publisher","award":["2024A1515140010"],"award-info":[{"award-number":["2024A1515140010"]}],"id":[{"id":"10.13039\/501100013050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016087","name":"Qufu Normal University","doi-asserted-by":"publisher","award":["2025JG14"],"award-info":[{"award-number":["2025JG14"]}],"id":[{"id":"10.13039\/100016087","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.asoc.2026.115752","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T06:47:28Z","timestamp":1781506048000},"page":"115752","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Transformer UNet with super token attention for medical image segmentation"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2230-3937","authenticated-orcid":false,"given":"Peng","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling-Xin","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ru-Yue","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115752_bib0005","article-title":"A comprehensive review of deep learning for medical image segmentation","author":"Xia","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115752_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2026.113727","article-title":"An effective unet using feature interaction and fusion for organ segmentation in medical image","volume":"167","author":"Gou","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115752_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129077","article-title":"Mlfinet: A multi-level feature interaction 3d medical image segmentation network","volume":"618","author":"Liao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115752_bib0020","series-title":"Proceedings of the International Conference on 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.asoc.2026.115752_bib0025","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/TIFS.2025.3648551","article-title":"Towards patch-based noise compression for adversarial attack against transformer-based visual tracking","volume":"21","author":"Gao","year":"2026","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.asoc.2026.115752_bib0030","article-title":"A hybrid transformer network with residual-like connections for medical image segmentation","author":"Feng","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115752_bib0035","doi-asserted-by":"crossref","DOI":"10.1007\/s44443-026-00746-y","article-title":"Towards adversarial defense with receptive field enhancement fusion and denoising u-net for visual tracking","author":"Gao","year":"2026","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"10.1016\/j.asoc.2026.115752_bib0040","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.asoc.2026.115752_bib0045","author":"Li"},{"key":"10.1016\/j.asoc.2026.115752_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22690","article-title":"Vision transformer with super token sampling","author":"Huang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115752_bib0055","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"352","article-title":"Superpixel sampling networks","author":"Jampani","year":"2018"},{"key":"10.1016\/j.asoc.2026.115752_bib0060","author":"Chu"},{"key":"10.1016\/j.asoc.2026.115752_bib0065","doi-asserted-by":"crossref","first-page":"14596","DOI":"10.52202\/068431-1061","article-title":"Orthogonal transformer: An efficient vision transformer backbone with token orthogonalization","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115752_bib0070","author":"Vasa"},{"key":"10.1016\/j.asoc.2026.115752_bib0075","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"601","article-title":"Selfreg-unet: Self-regularized unet for medical image segmentation","author":"Zhu","year":"2024"},{"key":"10.1016\/j.asoc.2026.115752_bib0080","author":"Dosovitskiy"},{"key":"10.1016\/j.asoc.2026.115752_bib0085","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12124","article-title":"Cswin transformer: A general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.1016\/j.asoc.2026.115752_bib0090","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"603","article-title":"Ccnet: Criss-cross attention for semantic segmentation","author":"Huang","year":"2019"},{"key":"10.1016\/j.asoc.2026.115752_bib0095","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"568","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.asoc.2026.115752_bib0100","first-page":"12992","article-title":"Glance-and-gaze vision transformer","volume":"34","author":"Yu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.asoc.2026.115752_bib0105","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"Crossformer++: A versatile vision transformer hinging on cross-scale attention","volume":"46","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115752_bib0110","author":"Kitaev"},{"key":"10.1016\/j.asoc.2026.115752_bib0115","first-page":"1","article-title":"Multi-frequency integration and scale-frequency linear attention for aerial tracking","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.asoc.2026.115752_bib0120","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.neucom.2020.11.046","article-title":"Csart: Channel and spatial attention-guided residual learning for real-time object tracking","volume":"436","author":"Zhang","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115752_bib0125","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"405","article-title":"Glka-unet: A global-local aware unet with kan attention for infrared small target detection","author":"Zhang","year":"2025"},{"key":"10.1016\/j.asoc.2026.115752_bib0130","author":"Chen"},{"key":"10.1016\/j.asoc.2026.115752_bib0135","first-page":"1","article-title":"Ds-transunet: Dual swin transformer u-net for medical image segmentation","volume":"71","author":"Lin","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.asoc.2026.115752_bib0140","series-title":"Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"14","article-title":"Transfuse: Fusing transformers and cnns for medical image segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.asoc.2026.115752_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109228","article-title":"An effective cnn and transformer complementary network for medical image segmentation","volume":"136","author":"Yuan","year":"2023","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.asoc.2026.115752_bib0150","doi-asserted-by":"crossref","first-page":"8045","DOI":"10.1109\/TCE.2025.3593784","article-title":"Hcmnet: A hybrid cnn-mamba network for breast ultrasound segmentation for consumer assisted diagnosis","volume":"71","author":"Xiong","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.asoc.2026.115752_bib0155","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.asoc.2026.115752_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129690","article-title":"An active learning model based on image similarity for skin lesion segmentation","volume":"630","author":"Shu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115752_bib0165","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3007","article-title":"Carafe: Content-aware reassembly of features","author":"Wang","year":"2019"},{"key":"10.1016\/j.asoc.2026.115752_bib0170","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115752_bib0175","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7028","article-title":"Cross-layer distillation with semantic calibration","volume":"vol. 35","author":"Chen","year":"2021"},{"key":"10.1016\/j.asoc.2026.115752_bib0180","series-title":"European Conference on Computer Vision","first-page":"347","article-title":"Self-regulated feature learning via teacher-free feature distillation","author":"Li","year":"2022"},{"key":"10.1016\/j.asoc.2026.115752_bib0185","series-title":"International Conference on Machine Learning, PMLR","first-page":"2006","article-title":"Feature-map-level online adversarial knowledge distillation","author":"Chung","year":"2020"},{"key":"10.1016\/j.asoc.2026.115752_bib0190","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2780","article-title":"Variational convolutional neural network pruning","author":"Zhao","year":"2019"},{"key":"10.1016\/j.asoc.2026.115752_bib0195","article-title":"Learning structured sparsity in deep neural networks","volume":"29","author":"Wen","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.asoc.2026.115752_bib0200","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.jksuci.2023.02.012","article-title":"Ib-transunet: combining information bottleneck and transformer for medical image segmentation","volume":"35","author":"Li","year":"2023","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"10.1016\/j.asoc.2026.115752_bib0205","series-title":"Data from pancreas-ct","author":"Roth","year":"2016"},{"issue":"10","key":"10.1016\/j.asoc.2026.115752_bib0210","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (brats)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.asoc.2026.115752_bib0215","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4981","article-title":"Segformer3d: an efficient transformer for 3d medical image segmentation","author":"Perera","year":"2024"},{"key":"10.1016\/j.asoc.2026.115752_bib0220","author":"Oktay"},{"key":"10.1016\/j.asoc.2026.115752_bib0225","series-title":"Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"656","article-title":"Domain adaptive relational reasoning for 3d multi-organ segmentation","author":"Fu","year":"2020"},{"key":"10.1016\/j.asoc.2026.115752_bib0230","series-title":"Proceedings of the International Conference on 3D Vision","first-page":"565","article-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"10.1016\/j.asoc.2026.115752_bib0235","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"6202","article-title":"Hiformer: Hierarchical multi-scale representations using transformers for medical image segmentation","author":"Heidari","year":"2023"},{"key":"10.1016\/j.asoc.2026.115752_bib0240","series-title":"Proceedings of the IEEE international conference on acoustics, speech and signal processing","first-page":"2390","article-title":"Mixed transformer u-net for medical image segmentation","author":"Wang","year":"2022"},{"issue":"9","key":"10.1016\/j.asoc.2026.115752_bib0245","doi-asserted-by":"crossref","first-page":"5396","DOI":"10.1109\/JBHI.2024.3406786","article-title":"A novel skip-connection strategy by fusing spatial and channel wise features for multi-region medical image segmentation","volume":"28","author":"Tan","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.asoc.2026.115752_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.mri.2025.110502","article-title":"Df-transunet: A novel transunet model of pixel level classification for cardiac mr image segmentation","author":"Zheng","year":"2025","journal-title":"Magn. Reson. Imaging"},{"key":"10.1016\/j.asoc.2026.115752_bib0255","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"6222","article-title":"Medical image segmentation via cascaded attention decoding","author":"Rahman","year":"2023"},{"key":"10.1016\/j.asoc.2026.115752_bib0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102634","article-title":"Cswin-unet: Transformer unet with cross-shaped windows for medical image segmentation","volume":"113","author":"Liu","year":"2025","journal-title":"Inf. Fusion"},{"issue":"6","key":"10.1016\/j.asoc.2026.115752_bib0265","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."},{"issue":"2","key":"10.1016\/j.asoc.2026.115752_bib0270","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":"Nat. Methods"},{"key":"10.1016\/j.asoc.2026.115752_bib0275","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"574","article-title":"Unetr: Transformers for 3d medical image segmentation","author":"Hatamizadeh","year":"2022"},{"key":"10.1016\/j.asoc.2026.115752_bib0280","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"109","article-title":"Transbts: Multimodal brain tumor segmentation using transformer","author":"Wang","year":"2021"},{"key":"10.1016\/j.asoc.2026.115752_bib0285","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2021"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012007?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012007?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:44:19Z","timestamp":1782485059000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626012007"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":57,"alternative-id":["S1568494626012007"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115752","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Transformer UNet with super token attention for medical image segmentation","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115752","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115752"}}