{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:57:51Z","timestamp":1777665471770,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province of China","doi-asserted-by":"publisher","award":["2020J01006"],"award-info":[{"award-number":["2020J01006"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011160","name":"Open Project Program of the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","doi-asserted-by":"publisher","award":["VRLAB2022AC04"],"award-info":[{"award-number":["VRLAB2022AC04"]}],"id":[{"id":"10.13039\/501100011160","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ITC-InnoHK Projects at the Hong Kong Centre for Cerebro-Cardiovascular Health Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tmi.2023.3291719","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:11:16Z","timestamp":1688407876000},"page":"96-107","source":"Crossref","is-referenced-by-count":248,"title":["LViT: Language Meets Vision Transformer in Medical Image Segmentation"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3839-0611","authenticated-orcid":false,"given":"Zihan","family":"Li","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0622-4710","authenticated-orcid":false,"given":"Yunxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5998-7565","authenticated-orcid":false,"given":"Qingde","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Hull, Hull, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2657-6051","authenticated-orcid":false,"given":"Puyang","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}]},{"given":"Dazhou","family":"Guo","sequence":"additional","affiliation":[{"name":"The DAMO Academy, Alibaba Group, New York, NY, USA"}]},{"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"The DAMO Academy, Alibaba Group, New York, NY, USA"}]},{"given":"Dakai","family":"Jin","sequence":"additional","affiliation":[{"name":"The DAMO Academy, Alibaba Group, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8033-2755","authenticated-orcid":false,"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana--Champaign, Urbana, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9996-6870","authenticated-orcid":false,"given":"Qingqi","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Digital Media Technology, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Med3D: Transfer learning for 3D medical image analysis","author":"Chen","year":"2019","journal-title":"arXiv:1904.00625"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59728-3_73"},{"key":"ref4","article-title":"Self-supervised tumor segmentation through layer decomposition","author":"Zhang","year":"2021","journal-title":"arXiv:2109.03230"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15937-4_65"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_65"},{"key":"ref10","first-page":"21271","article-title":"Bootstrap your own latent\u2014A new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Grill"},{"key":"ref11","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020","journal-title":"arXiv:2005.06465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-020-00173-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2022.10.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669868"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-022-00105-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_40"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2995518"},{"key":"ref23","article-title":"Semi-WTC: A practical semi-supervised framework for attack categorization through weight-task consistency","author":"Li","year":"2022","journal-title":"arXiv:2205.09669"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101766"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref26","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref30","article-title":"The devil is in the labels: Semantic segmentation from sentences","author":"Yin","year":"2022","journal-title":"arXiv:2202.02002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_53"},{"key":"ref33","article-title":"Joint learning of localized representations from medical images and reports","volume-title":"arXiv:2112.02889","author":"M\u00fcller","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2020.2973971"},{"key":"ref38","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref39","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3129245"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096683"},{"key":"ref42","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref43","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv:1804.03999"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref45","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2102.04306"},{"key":"ref46","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv:2105.05537"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref48","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2020","journal-title":"arXiv:2010.00747"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17066"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102792"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102530"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/42\/10379496\/10172039.pdf?arnumber=10172039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:22:29Z","timestamp":1705026149000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10172039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2023.3291719","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}