{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:09:18Z","timestamp":1775066958188,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","award":["IO201211-08109-01"],"award-info":[{"award-number":["IO201211-08109-01"]}],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["2019-0-00075"],"award-info":[{"award-number":["2019-0-00075"]}]},{"name":"Artificial Intelligence Graduate School Program"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2020H1D3A2A03100945"],"award-info":[{"award-number":["NRF-2020H1D3A2A03100945"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/jbhi.2022.3207502","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T19:46:30Z","timestamp":1663616790000},"page":"6070-6080","source":"Crossref","is-referenced-by-count":173,"title":["Multi-Modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6708-3918","authenticated-orcid":false,"given":"Jong Hak","family":"Moon","sequence":"first","affiliation":[{"name":"Graduate School of AI, KAIST, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4583-4271","authenticated-orcid":false,"given":"Hyungyung","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate School of AI, KAIST, Daejeon, South Korea"}]},{"given":"Woncheol","family":"Shin","sequence":"additional","affiliation":[{"name":"Graduate School of AI, KAIST, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3610-486X","authenticated-orcid":false,"given":"Young-Hak","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5958-3509","authenticated-orcid":false,"given":"Edward","family":"Choi","sequence":"additional","affiliation":[{"name":"Graduate School of AI, KAIST, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_63"},{"key":"ref38","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref32","article-title":"Learning video representations using contrastive bidirectional transformer","author":"sun","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.11101913"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref10","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Computat Linguistics Hum Lang Technol"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Unsupervised multimodal representation learning across medical images and reports","author":"hsu","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref14","article-title":"Pixel-Bert: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2523081992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743415"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: A pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"lee","year":"2020","journal-title":"Bioinformatics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref4","article-title":"Emixer: End-to-end multimodal x-ray generation via self-supervision","author":"biswal","year":"0","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref27","first-page":"3347","article-title":"Transfusion: Understanding transfer learning for medical imaging","author":"raghu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/jbin.2001.1000"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19992-4_34"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00408"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.03.009"},{"key":"ref7","first-page":"104","article-title":"Uniter: Universal image-text representations learning","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","first-page":"72","article-title":"Publicly available clinical bert embeddings","author":"alsentzer","year":"0","journal-title":"Proc 2nd Clin Natural Lang Process Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref1","first-page":"1","article-title":"A database for using machine learning and data mining techniques for coronary artery disease diagnosis","volume":"6","author":"alizadehsani","year":"2019","journal-title":"Data Science Journal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313289"},{"key":"ref22","first-page":"249","article-title":"Clinically accurate chest X-ray report generation","author":"liu","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref24","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/19689"},{"key":"ref26","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"qi","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221020\/9973412\/09894658.pdf?arnumber=9894658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T16:04:51Z","timestamp":1676822691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9894658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":41,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2022.3207502","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}