{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T08:27:23Z","timestamp":1773476843292,"version":"3.50.1"},"reference-count":30,"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":"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":[{"name":"OpenAI Researcher Access Program"},{"name":"ERC IMI","award":["101005122"],"award-info":[{"award-number":["101005122"]}]},{"name":"ERC IMI","award":["H2020"],"award-info":[{"award-number":["H2020"]}]},{"name":"ERC IMI","award":["952172"],"award-info":[{"award-number":["952172"]}]},{"name":"MRC","award":["MC\/PC\/21013"],"award-info":[{"award-number":["MC\/PC\/21013"]}]},{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["IEC\\NSFC\\211235;"],"award-info":[{"award-number":["IEC\\NSFC\\211235;"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NVIDIA Academic Hardware Grant Program"},{"DOI":"10.13039\/501100000288","name":"SABER Project of Boehringer Ingelheim Ltd.,","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013342","name":"NIHR Imperial Biomedical Research Centre","doi-asserted-by":"publisher","award":["RDA01"],"award-info":[{"award-number":["RDA01"]}],"id":[{"id":"10.13039\/501100013342","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wellcome Leap Dynamic Resilience"},{"name":"UKRI MRC Research Grant, TFS Research","award":["MR\/U506710\/1"],"award-info":[{"award-number":["MR\/U506710\/1"]}]},{"name":"UKRI guarantee funding for Horizon Europe MSCA Postdoctoral Fellowships under","award":["EP\/Z002206\/1"],"award-info":[{"award-number":["EP\/Z002206\/1"]}]},{"name":"UKRI Future Leaders Fellowship","award":["MR\/V023799\/1"],"award-info":[{"award-number":["MR\/V023799\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3558857","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T13:06:20Z","timestamp":1745499980000},"page":"17623-17634","source":"Crossref","is-referenced-by-count":2,"title":["Beyond the Hype: A Dispassionate Look at Vision\u2013Language Models in Medical Scenario"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-3336","authenticated-orcid":false,"given":"Yang","family":"Nan","sequence":"first","affiliation":[{"name":"Bioengineering Department and Imperial-X, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huichi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Bioengineering Department and Imperial-X, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2468-9266","authenticated-orcid":false,"given":"Xiaodan","family":"Xing","sequence":"additional","affiliation":[{"name":"GSK, London, U.K."}],"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref5","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref6","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref7","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref9","first-page":"353","article-title":"Med-flamingo: A multimodal medical few-shot learner","volume-title":"Proc. Mach. Learn. Health (ML4H)","author":"Moor"},{"key":"ref10","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref11","article-title":"BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62385-7"},{"key":"ref13","article-title":"HuatuoGPT-vision, towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024","journal-title":"arXiv:2406.19280"},{"key":"ref14","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref15","article-title":"Yi: Open foundation models by 01.AI","author":"Open AI","year":"2024","journal-title":"arXiv:2403.04652"},{"key":"ref16","article-title":"PathVQA: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv:2003.10286"},{"key":"ref17","article-title":"CARES: A comprehensive benchmark of trustworthiness in medical vision language models","author":"Xia","year":"2024","journal-title":"arXiv:2406.06007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024.podcast"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241613"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3260169"},{"key":"ref21","first-page":"1","article-title":"SARS-CoV-2 CT-scan dataset: A large dataset of real patients CT scans for SARS-CoV-2 identification","volume":"2020","author":"Soares","year":"2020","journal-title":"MedRxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.01.001"},{"key":"ref23","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref25","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref26","article-title":"MLLM-as-a-judge: Assessing multimodal LLM-as-a-judge with vision\u2013language benchmark","author":"Chen","year":"2024","journal-title":"arXiv:2402.04788"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3297103"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/10976244.pdf?arnumber=10976244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:37Z","timestamp":1759945117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":30,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3558857","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}