{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:55:25Z","timestamp":1777499725877,"version":"3.51.4"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000769","name":"University of Oxford","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000769","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIHR Research Professorship"},{"name":"Royal Academy of Engineering Research Chair"},{"name":"Well-come Trust-funded VITAL project"},{"name":"U.K. Research and Innovation"},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Hong Kong Centre for Cerebro-cardiovascular Engineering"},{"name":"MRC Confidence in Concept"},{"DOI":"10.13039\/501100014748","name":"Clarendon Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014748","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":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3534586","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:47:18Z","timestamp":1738003638000},"page":"3332-3343","source":"Crossref","is-referenced-by-count":8,"title":["Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7715-5228","authenticated-orcid":false,"given":"Fenglin","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1118-9710","authenticated-orcid":false,"given":"Xian","family":"Wu","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0081-4106","authenticated-orcid":false,"given":"Jinfa","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2019-0377","authenticated-orcid":false,"given":"Bang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"given":"Kim","family":"Branson","sequence":"additional","affiliation":[{"name":"GlaxoSmithKline, London, U.K."}]},{"given":"Patrick","family":"Schwab","sequence":"additional","affiliation":[{"name":"GlaxoSmithKline, London, U.K."}]},{"given":"Lei","family":"Clifton","sequence":"additional","affiliation":[{"name":"Nuffield Department of Primary Care Health Sciences, Applied Digital Health (ADH), University of Oxford, Oxford, U.K."}]},{"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2195-2847","authenticated-orcid":false,"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-8555","authenticated-orcid":false,"given":"David A.","family":"Clifton","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref2","first-page":"1537","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref3","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1657"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79942-9_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2020.102589"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09985-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909"},{"key":"ref18","article-title":"Recent advances in autoencoder-based representation learning","author":"Tschannen","year":"2018"},{"key":"ref19","article-title":"DeCap: Decoding CLIP latents for zero-shot captioning via text-only training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3371376"},{"key":"ref21","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.664"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.861680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2020-48g7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2020-48g7"},{"key":"ref39","article-title":"BIMCV COVID-19+: A large annotated dataset of RX and CT images from COVID-19 patients","author":"de la Iglesia-Vay\u00e1","year":"2020","journal-title":"arXiv:2006.01174"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01013-6"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref44","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref45","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","article-title":"Advancing radiograph representation learning with masked record modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref49","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_39"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3060634"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101840"},{"key":"ref55","article-title":"BiomedGPT: A unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks","author":"Zhang","year":"2023"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref58","first-page":"978","article-title":"Multimodal image-text matching improves retrieval-based chest X-ray report generation","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Jeong"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref61","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":"ref62","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref63","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref64","article-title":"A survey of large language models in medicine: Progress, application, and challenge","author":"Zhou","year":"2023"},{"key":"ref65","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tsimpoukelli"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104458"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50641-4_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669825"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_59"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10854911.pdf?arnumber=10854911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T17:33:32Z","timestamp":1745861612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10854911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":69,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3534586","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":[[2025,5]]}}}