{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:54:17Z","timestamp":1783576457400,"version":"3.55.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62476196"],"award-info":[{"award-number":["62476196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Agency for Science, Technology and Research (A*STAR) Central Research Fund \u201cRobust and Trustworthy AI System for Multi-Modality Healthcare"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tmi.2024.3507076","type":"journal-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T18:53:53Z","timestamp":1732820033000},"page":"1505-1517","source":"Crossref","is-referenced-by-count":5,"title":["Topicwise Separable Sentence Retrieval for Medical Report Generation"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2390-1184","authenticated-orcid":false,"given":"Junting","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR), Institute of High Performance Computing (IHPC), Agency for Science, Fusionopolis Way, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1686-9854","authenticated-orcid":false,"given":"Zhihao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-5524","authenticated-orcid":false,"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[{"name":"Technology and Research (A*STAR), Institute of High Performance Computing (IHPC), Agency for Science, Fusionopolis Way, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5501-9575","authenticated-orcid":false,"given":"Liang","family":"Wan","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref5","first-page":"1","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref8","article-title":"MedXChat: A unified multimodal large language model framework towards CXRs understanding and generation","author":"Yang","year":"2023","journal-title":"arXiv:2312.02233"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3171661"},{"key":"ref10","first-page":"16266","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","volume-title":"Proc. NeurIPS","volume":"34","author":"Liu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref12","article-title":"RaDialog: A large vision-language model for radiology report generation and conversational assistance","volume-title":"arXiv:2311.18681","author":"Pellegrini","year":"2023"},{"key":"ref13","first-page":"209","article-title":"Retrieval-based chest X-ray report generation using a pre-trained contrastive language-image model","volume-title":"Proc. Mach. Learn. Health","author":"Endo"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00937-3_22"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_58"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_56"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01013-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3049498"},{"key":"ref27","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.176"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102982"},{"key":"ref34","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref35","first-page":"1","article-title":"Vision transformers need registers","volume-title":"Proc. ICLR","author":"Darcet"},{"key":"ref36","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref37","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Alayrac"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9081295"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_35"},{"key":"ref46","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref48","first-page":"188","article-title":"NegBio: A high-performance tool for negation and uncertainty detection in radiology reports","volume-title":"AMIA Summits Transl. Sci. Proc.","volume":"2018","author":"Peng","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref50","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref53","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3245608"},{"key":"ref55","volume-title":"Hugging Face","year":"2024"},{"key":"ref56","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3236661"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref60","first-page":"5110","article-title":"Semi-supervised medical report generation via graph-guided hybrid feature consistency","volume-title":"IEEE Trans. Multimedia","volume":"60","author":"Zhang","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10930313\/10770258.pdf?arnumber=10770258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:37:04Z","timestamp":1742319424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10770258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":61,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3507076","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}