{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:06:39Z","timestamp":1784390799330,"version":"3.55.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}]},{"name":"National Key R&D Program of China","award":["2022YFC2502800"],"award-info":[{"award-number":["2022YFC2502800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272450"],"award-info":[{"award-number":["62272450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82471066"],"award-info":[{"award-number":["82471066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M721743"],"award-info":[{"award-number":["2022M721743"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3598734","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:34:24Z","timestamp":1755106464000},"page":"11848-11862","source":"Crossref","is-referenced-by-count":11,"title":["VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced With Clinical Knowledge"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3839-0611","authenticated-orcid":false,"given":"Zihan","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5413-7702","authenticated-orcid":false,"given":"Diping","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zefeng","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7040-0577","authenticated-orcid":false,"given":"Deming","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6211-6306","authenticated-orcid":false,"given":"Fei","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiulan","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6461-3306","authenticated-orcid":false,"given":"Paul E.","family":"Kinahan","sequence":"additional","affiliation":[{"name":"Department of Bioengineering and the Department of Radiology, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23458-5"},{"key":"ref3","article-title":"Living with two or more eye diseases","author":"Kern","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref8","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref9","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref10","article-title":"LLaMA-Adapter: Efficient fine-tuning of large language models with zero-initialized attention","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref11","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref12","article-title":"LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref17","article-title":"Retina image bank dataset","year":"2012"},{"key":"ref19","article-title":"APTOS 2019 blindness detection","author":"Karthik Maggie","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100512"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570"},{"key":"ref22","article-title":"InternLM: A multilingual language model with progressively enhanced capabilities","author":"Team","year":"2023"},{"key":"ref23","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref26","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref27","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/154860"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2011.2159619"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2587062"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_54"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207664"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102938"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5626137"},{"key":"ref35","article-title":"PALM: Pathologic myopia challenge","author":"Fu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/data6020014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/data8020029"},{"key":"ref38","article-title":"Diabetic retinopathy detection","author":"Emma Dugas","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3172773"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-019-0649-y"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2013.1743"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25138-w"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00249"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01082"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01388-1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/42.845178"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01564-3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICoDT255437.2022.9787482"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2013.01.010"},{"key":"ref52","article-title":"A Brazilian multilabel ophthalmological dataset (BRSET)","volume":"13026","author":"Nakayama","year":"2023","journal-title":"PhysioNet"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3214086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.06.011"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00755-0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0179790"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0096814"},{"key":"ref59","article-title":"Machine learn for glaucoma","author":"Kim","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5566\/ias.2346"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01943-4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5244\/C.21.15"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_12"},{"key":"ref64","article-title":"Glaucoma and non-glaucoma classification using ML\/DL and ensemble approaches using image feature extraction using hog","author":"Nandi","year":"2022"},{"key":"ref66","article-title":"Derbi Hackathon retinal fundus image dataset","author":"Devarasetti","year":"2021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3359701"},{"key":"ref69","article-title":"Machine learning for pseudopapilledema","author":"Kim","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3139160"},{"key":"ref71","article-title":"The William F. Hoyt neuro-ophthalmology collection","author":"Hoyt","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.14-15949"},{"key":"ref73","article-title":"Retinal occlusion dataset","author":"Binu","year":"2022"},{"key":"ref74","article-title":"Diagnosis of diabetic retinopathy","author":"Darabi","year":"2022"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3313786"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.2307\/2276774"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1032280214"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref79","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref80","article-title":"Mini-Gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024"},{"key":"ref81","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref82","article-title":"Visual instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref83","first-page":"353","article-title":"Med-Flamingo: A multimodal medical few-shot learner","volume-title":"Proc. Int. Conf. Mach. Learn. Health","author":"Moor"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11124413.pdf?arnumber=11124413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:14Z","timestamp":1762455194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":78,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3598734","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}