{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:41:56Z","timestamp":1765305716528,"version":"3.46.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306253"],"award-info":[{"award-number":["62306253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Fund-General Programme","award":["2024A1515010233"],"award-info":[{"award-number":["2024A1515010233"]}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2023A04J1860"],"award-info":[{"award-number":["2023A04J1860"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jbhi.2025.3569428","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T13:45:03Z","timestamp":1747057503000},"page":"7549-7558","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Radiology Report Generation From Noisy Free-Texts"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0974-6851","authenticated-orcid":false,"given":"Yujian","family":"Yuan","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanting","family":"Zheng","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, Guangzhou University of Chinese Medicine, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8235-7852","authenticated-orcid":false,"given":"Liangqiong","family":"Qu","sequence":"additional","affiliation":[{"name":"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.2023.102798"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_10"},{"article-title":"A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities","year":"2024","author":"Hamamci","key":"ref5"},{"key":"ref6","article-title":"Laion-400M: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref8","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref9","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref10","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jain","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.765"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"ref13","first-page":"37995","article-title":"Quilt-1M: One million image-text pairs for histopathology","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"36","author":"Ikezogwo","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2400640"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref16"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511921"},{"key":"ref19","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kojima","year":"2022"},{"key":"ref20","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Info. Process. Syst.","volume":"36","author":"Madaan","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-023-00136-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00402-023-05113-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230725"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10384-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102924"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"article-title":"Towards generalist foundation model for radiology","year":"2023","author":"Wu","key":"ref27"},{"article-title":"Decomposing vision-based LLM predictions for auto-evaluation with GPT-4","year":"2024","author":"Zhu","key":"ref28"},{"article-title":"MAIRA-2: Grounded radiology report generation","year":"2024","author":"Bannur","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00561"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"ref33","first-page":"193","article-title":"Large language models are state-of-the-art evaluators of translation quality","volume-title":"Proc. EAMT","author":"Kocmi","year":"2023"},{"article-title":"ChatGPT as a factual inconsistency evaluator for text summarization","year":"2023","author":"Luo","key":"ref34"},{"article-title":"PandaLM: An automatic evaluation benchmark for LLM instruction tuning optimization","year":"2023","author":"Wang","key":"ref35"},{"article-title":"Collaborative evaluation: Exploring the synergy of large language models and humans for open-ended generation evaluation","year":"2023","author":"Li","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref38","article-title":"Distilled self-critique of LLMs with synthetic data: A Bayesian perspective","volume-title":"Proc. 2nd Tiny Papers Track ICLR","author":"Gallego","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"year":"2024","key":"ref41","article-title":"Radiopaedia"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-020-00864-9"},{"year":"2024","key":"ref43","article-title":"RadReport: ACR reporting and data systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad259"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121442"},{"year":"2024","key":"ref46","article-title":"OpenAI platform documentation"},{"key":"ref47","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52417-z"},{"article-title":"Baichuan-M1: Pushing the medical capability of large language models","year":"2025","author":"Wang","key":"ref49"},{"article-title":"M3D: Advancing 3D medical image analysis with multi-modal large language models","year":"2024","author":"Bai","key":"ref50"},{"article-title":"AutoRG-brain: Grounded report generation for brain MRI","year":"2024","author":"Lei","key":"ref51"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11192794\/11002452.pdf?arnumber=11002452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:34:33Z","timestamp":1765305273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11002452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":51,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3569428","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"type":"print","value":"2168-2194"},{"type":"electronic","value":"2168-2208"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}