{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:11:26Z","timestamp":1785604286933,"version":"3.56.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP200103748"],"award-info":[{"award-number":["DP200103748"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tmi.2025.3534436","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T18:54:37Z","timestamp":1738176877000},"page":"2463-2476","source":"Crossref","is-referenced-by-count":9,"title":["Enhancing Medical Vision-Language Contrastive Learning via Inter-Matching Relation Modeling"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5591-5385","authenticated-orcid":false,"given":"Mingjian","family":"Li","sequence":"first","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9562-1613","authenticated-orcid":false,"given":"Mingyuan","family":"Meng","sequence":"additional","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0602-6319","authenticated-orcid":false,"given":"Michael","family":"Fulham","sequence":"additional","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3381-214X","authenticated-orcid":false,"given":"David Dagan","family":"Feng","sequence":"additional","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9759-0200","authenticated-orcid":false,"given":"Lei","family":"Bi","sequence":"additional","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5960-1060","authenticated-orcid":false,"given":"Jinman","family":"Kim","sequence":"additional","affiliation":[{"name":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00811-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00914-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104482"},{"key":"ref7","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wang","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_39"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102272"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_16"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3151666"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3194517"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv:1810.04805"},{"key":"ref24","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019","journal-title":"arXiv:1904.03323"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref28","first-page":"10","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round)","author":"Jain"},{"key":"ref29","article-title":"CLIP in medical imaging: A comprehensive survey","author":"Zhao","year":"2023","journal-title":"arXiv:2312.07353"},{"key":"ref30","first-page":"1","article-title":"Med-UniC: Unifying cross-lingual medical vision-language pre-training by diminishing bias","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Wan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref33","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Velickovic"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref35","volume-title":"SIIM-ACR pneumothorax segmentation","author":"Zawacki","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00272"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref41","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref42","first-page":"1","article-title":"Advancing radiograph representation learning with masked record modeling","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103018"},{"key":"ref44","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02139"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11023641\/10858000.pdf?arnumber=10858000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:22:42Z","timestamp":1749097362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3534436","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}