{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:47:54Z","timestamp":1778827674128,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"publisher","award":["62272248"],"award-info":[{"award-number":["62272248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2021-025A"],"award-info":[{"award-number":["CAAIXSJLJJ-2021-025A"]}]},{"name":"AISG Tech Challenge Fundin","award":["AISG2-TC-2021-003"],"award-info":[{"award-number":["AISG2-TC-2021-003"]}]},{"name":"A*STAR CDF","award":["C222812010"],"award-info":[{"award-number":["C222812010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tmi.2023.3264513","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:47:22Z","timestamp":1680716842000},"page":"2763-2775","source":"Crossref","is-referenced-by-count":338,"title":["H2Former: An Efficient Hierarchical Hybrid Transformer for Medical Image Segmentation"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1356-8757","authenticated-orcid":false,"given":"Along","family":"He","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Network and Data Security Technology, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5589-7060","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Network and Data Security Technology, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1697-8022","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengkun","family":"Du","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Network and Data Security Technology, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Xia","sequence":"additional","affiliation":[{"name":"Radiology Department, Tianjin First Central Hospital, Nankai, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-5524","authenticated-orcid":false,"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref12","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref15","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref53","first-page":"253","article-title":"Adaptive context selection for polyp segmentation","author":"zhang","year":"2020","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref52","first-page":"263","article-title":"PraNet: Parallel reverse attention network for polyp segmentation","author":"fan","year":"2020","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"LeViT-UNet: Make faster encoders with transformer for medical image segmentation","author":"xu","year":"2021","journal-title":"arXiv 2107 08623"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref17","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"chen","year":"2021","journal-title":"arXiv 2102 04306"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref19","article-title":"NnFormer: Interleaved transformer for volumetric segmentation","author":"zhou","year":"2021","journal-title":"arXiv 2109 03201"},{"key":"ref18","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","author":"cao","year":"2021","journal-title":"arXiv 2105 05537"},{"key":"ref51","first-page":"302","article-title":"Selective feature aggregation network with area-boundary constraints for polyp segmentation","author":"fang","year":"2019","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","article-title":"Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC)","author":"gutman","year":"2016","journal-title":"arXiv 1605 01397"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/978-3-030-37734-2_37","article-title":"Kvasir-SEG: A segmented polyp dataset","author":"jha","year":"2020","journal-title":"Proc Int Conf Multimedia Modeling"},{"key":"ref48","first-page":"12","article-title":"MICCAI multi-atlas labeling beyond the cranial vault-workshop and challenge","author":"landman","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"ref42","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref7","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref9","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"oktay","year":"2018","journal-title":"arXiv 1804 03999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2903562"},{"key":"ref3","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2791488"},{"key":"ref40","article-title":"MISSFormer: An effective medical image segmentation transformer","author":"huang","year":"2021","journal-title":"arXiv 2109 07162"},{"key":"ref35","first-page":"1","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"171","article-title":"CoTr: Efficiently bridging CNN and transformer for 3D medical image segmentation","author":"xie","year":"2021","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref36","first-page":"14","article-title":"TransFuse: Fusing transformers and CNNs for medical image segmentation","author":"zhang","year":"2021","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996645"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","first-page":"61","article-title":"UTNet: A hybrid transformer architecture for medical image segmentation","author":"gao","year":"2021","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00333"},{"key":"ref24","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume":"34","author":"zhang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref25","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","author":"wang","year":"2021","journal-title":"arXiv 2108 00154"},{"key":"ref20","article-title":"Vision transformer for small-size datasets","author":"lee","year":"2021","journal-title":"arXiv 2112 13492"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref21","first-page":"1","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume":"34","author":"xu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"ref27","first-page":"801","article-title":"Encoder–decoder with Atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053405"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/42\/10236920\/10093768.pdf?arnumber=10093768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T17:56:10Z","timestamp":1698342970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10093768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":55,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2023.3264513","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}