{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T04:10:46Z","timestamp":1777003846513,"version":"3.51.4"},"reference-count":62,"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\/501100004787","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["27206123"],"award-info":[{"award-number":["27206123"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004787","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["C5055-24G"],"award-info":[{"award-number":["C5055-24G"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004787","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["T45-401\/22-N"],"award-info":[{"award-number":["T45-401\/22-N"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["ITS\/273\/22"],"award-info":[{"award-number":["ITS\/273\/22"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["GHP\/318\/22GD"],"award-info":[{"award-number":["GHP\/318\/22GD"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201483"],"award-info":[{"award-number":["62201483"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Fund","award":["2024A1515011875"],"award-info":[{"award-number":["2024A1515011875"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tmi.2025.3589928","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T17:39:09Z","timestamp":1752687549000},"page":"5306-5318","source":"Crossref","is-referenced-by-count":2,"title":["Scaling Chest X-Ray Foundation Models From Mixed Supervisions for Dense Prediction"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3313-6479","authenticated-orcid":false,"given":"Fuying","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9315-6527","authenticated-orcid":false,"given":"Lequan","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref2","article-title":"CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning","author":"Rajpurkar","year":"2017","journal-title":"arXiv:1711.05225"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001973"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-021-00968-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3049498"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104227"},{"key":"ref7","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref11","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00536-x"},{"key":"ref14","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":"ref15","article-title":"Advancing radiograph representation learning with masked record modeling","author":"Zhou","year":"2023","journal-title":"arXiv:2301.13155"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh061"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","volume":"33","author":"Caron"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref26","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00965-w"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3"},{"key":"ref29","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":"ref30","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref31","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref33","article-title":"Multi-modal vision-language model for generalizable annotation-free pathology localization and clinical diagnosis","author":"Yang","year":"2024","journal-title":"arXiv:2401.02044"},{"key":"ref34","article-title":"CAT-seg: Cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2023","journal-title":"arXiv:2303.11797"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref37","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_41"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01498-w"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021210136"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797"},{"key":"ref46","volume-title":"RSNA Pneumonia Detection Challenge","year":"2018"},{"key":"ref47","article-title":"Deep learning segmentation model for automated detection of the opacity regions in the chest X-rays of the COVID-19 positive patients and the application for disease severity","author":"Tang","year":"2020","journal-title":"MedRxiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref54","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-58344-x"},{"key":"ref58","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref60","article-title":"Leveraging inductive bias in vit for medical image diagnosis","volume-title":"Proc. Brit. Mach. Vis. Assoc. (BMVA)","author":"Ha"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-85679-8"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11279972\/11081948.pdf?arnumber=11081948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:40:56Z","timestamp":1765219256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11081948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":62,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3589928","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}