{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T07:27:58Z","timestamp":1769844478216,"version":"3.49.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER Award OAC 2046708"],"award-info":[{"award-number":["CAREER Award OAC 2046708"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tmi.2024.3484294","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T13:20:04Z","timestamp":1729516804000},"page":"3984-3996","source":"Crossref","is-referenced-by-count":3,"title":["Disease-Informed Adaptation of Vision-Language Models"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6516-4012","authenticated-orcid":false,"given":"Jiajin","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering and the Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2656-7705","authenticated-orcid":false,"given":"Ge","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and the Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9938-7476","authenticated-orcid":false,"given":"Mannudeep K.","family":"Kalra","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9779-2141","authenticated-orcid":false,"given":"Pingkun","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and the Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26216-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref12","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"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref16","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","author":"Zhang","year":"2021","journal-title":"arXiv:2111.03930"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref19","first-page":"15558","article-title":"K-lite: Learning transferable visual models with external knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shen"},{"key":"ref20","article-title":"Medical image understanding with pretrained vision language models: A comprehensive study","author":"Qin","year":"2022","journal-title":"arXiv:2209.15517"},{"key":"ref21","first-page":"6704","article-title":"CyCLIP: Cyclic contrastive language-image pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Goel"},{"key":"ref22","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref23","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lu"},{"key":"ref24","article-title":"LISA: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv:2308.00692"},{"key":"ref25","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref26","first-page":"1","article-title":"LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref28","first-page":"1","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref30","article-title":"Cross-modal memory networks for radiology report generation","volume-title":"arXiv:2204.13258","author":"Chen","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_69"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2864759"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038909"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242141"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3536934"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611858"},{"key":"ref41","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv:1904.03323"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-15013-z"},{"key":"ref48","volume-title":"Actualmed COVID-19 Chest X-Ray Dataset Initiative","author":"Wang","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010287"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2020-48g7"},{"key":"ref51","volume-title":"Figure 1 COVID-19 Chest X-Ray Dataset Initiative","author":"Wang","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104319"},{"key":"ref55","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"11","key":"ref58","first-page":"248","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.008"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/42\/11218268\/10723745-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11218268\/10723745.pdf?arnumber=10723745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:35:33Z","timestamp":1761759333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10723745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3484294","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}