{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:23:56Z","timestamp":1785770636365,"version":"3.56.0"},"reference-count":47,"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 J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/jbhi.2025.3569491","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T13:47:32Z","timestamp":1747144052000},"page":"8199-8212","source":"Crossref","is-referenced-by-count":7,"title":["Text-Assisted Vision Model for Medical Image Segmentation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7472-4085","authenticated-orcid":false,"given":"Md Motiur","family":"Rahman","sequence":"first","affiliation":[{"name":"School of Engineering Technology, Electrical and Computer Engineering Technology, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7894-4849","authenticated-orcid":false,"given":"Saeka","family":"Rahman","sequence":"additional","affiliation":[{"name":"School of Engineering Technology, Electrical and Computer Engineering Technology, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5376-4491","authenticated-orcid":false,"given":"Smriti","family":"Bhatt","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2684-0887","authenticated-orcid":false,"given":"Miad","family":"Faezipour","sequence":"additional","affiliation":[{"name":"School of Engineering Technology, Electrical and Computer Engineering Technology, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00365"},{"key":"ref3","article-title":"LHU-Net: A light hybrid U-net for cost-efficient, high-performance volumetric medical image segmentation","author":"Sadegheih","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00227-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3225687"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CHASE60773.2024.00029"},{"key":"ref11","article-title":"Medical image understanding with pretrained vision language models: A comprehensive study","author":"Qin","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref17","first-page":"35959","article-title":"PyramidCLIP: Hierarchical feature alignment for vision-language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gao","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-01051-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref21","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"ref23","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3571672"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096683"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3129245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1101\/2020.05.20.20100362","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref35","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"issue":"PMLR","key":"ref37","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02246-w"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_19"},{"key":"ref40","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"issue":"140","key":"ref41","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref43","article-title":"MedGPT: Medical concept prediction from clinical narratives","author":"Kraljevic","year":"2021"},{"key":"ref44","article-title":"Barking up the syntactic tree: Enhancing VLM training with syntactic losses","author":"Luo","year":"2024"},{"key":"ref45","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32674"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2677499"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11231104\/11002644.pdf?arnumber=11002644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:11:36Z","timestamp":1762539096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11002644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":47,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3569491","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}