{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:16Z","timestamp":1776888436941,"version":"3.51.2"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tmi.2025.3573018","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:04:48Z","timestamp":1748005488000},"page":"4307-4322","source":"Crossref","is-referenced-by-count":3,"title":["AMVLM: Alignment-Multiplicity Aware Vision-Language Model for Semi-Supervised Medical Image Segmentation"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8939-9559","authenticated-orcid":false,"given":"Qingtao","family":"Pan","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1459-0557","authenticated-orcid":false,"given":"Zhengrong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9851-0428","authenticated-orcid":false,"given":"Wenhao","family":"Qiao","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjiao","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1039-8650","authenticated-orcid":false,"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7344-7733","authenticated-orcid":false,"given":"Guang","family":"Yang","sequence":"additional","affiliation":[{"name":"Bioengineering Department and Imperial-X, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1326-4120","authenticated-orcid":false,"given":"Bing","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/467"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102146"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00683"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Mach. Learn. Res. (PMLR)","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref10","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00064"},{"key":"ref14","article-title":"Improving semantic segmentation via self-training","author":"Zhu","year":"2020","journal-title":"arXiv:2004.14960"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3347689"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3400840"},{"key":"ref19","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Tarvainen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2995319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref25","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref27","article-title":"DMT: Dynamic mutual training for semi-supervised learning","author":"Feng","year":"2020","journal-title":"arXiv:2004.08514"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102603"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref30","article-title":"Word representations via Gaussian embedding","author":"Vilnis","year":"2014","journal-title":"arXiv:1412.6623"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_4"},{"key":"ref33","first-page":"104","article-title":"UNITER: Learning universal image-text representations","volume-title":"Proc. ECCV","author":"Chen"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.4.366"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120376"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2677499"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3025087"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref42","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv:1904.03323"},{"key":"ref43","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093360"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_48"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32674"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"ref51","article-title":"SemiSAM: Enhancing semi-supervised medical image segmentation via SAM-assisted consistency regularization","author":"Zhang","year":"2023","journal-title":"arXiv:2312.06316"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3530097"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_16"},{"key":"ref54","article-title":"Locality alignment improves vision-language models","author":"Covert","year":"2024","journal-title":"arXiv:2410.11087"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02499-w"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref57","article-title":"SAM-Med2D","author":"Cheng","year":"2023","journal-title":"arXiv:2308.16184"},{"key":"ref58","article-title":"SAM-Med3D: Towards general-purpose segmentation models for volumetric medical images","author":"Wang","year":"2023","journal-title":"arXiv:2310.15161"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-66958-3_14"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_60"},{"key":"ref61","article-title":"Segment anything model with uncertainty rectification for auto-prompting medical image segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2311.10529"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635501"},{"key":"ref63","first-page":"5665","article-title":"Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Mallasto"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01771"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/117"},{"key":"ref66","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Bachman"},{"key":"ref67","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Devon Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"key":"ref68","first-page":"15604","article-title":"Wasserstein dependency measure for representation learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Ozair"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11230061\/11014494.pdf?arnumber=11014494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:55:49Z","timestamp":1762408549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11014494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":68,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3573018","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}