{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:44:55Z","timestamp":1775324695102,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62125201"],"award-info":[{"award-number":["62125201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2040"],"award-info":[{"award-number":["U21B2040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020032"],"award-info":[{"award-number":["LQ24F020032"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tmi.2024.3412402","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:29:32Z","timestamp":1718130572000},"page":"4017-4028","source":"Crossref","is-referenced-by-count":18,"title":["Token-Mixer: Bind Image and Text in One Embedding Space for Medical Image Reporting"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-1692","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-7190","authenticated-orcid":false,"given":"Zhenqi","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9855-003X","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4348-2671","authenticated-orcid":false,"given":"Ting","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1230-5772","authenticated-orcid":false,"given":"Xianyun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0902-882X","authenticated-orcid":false,"given":"Hanliang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"}]},{"given":"Junhui","family":"Lv","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-3671","authenticated-orcid":false,"given":"Weidong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Colorectal Medical Oncology, Zhejiang Cancer Hospital, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0052-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2393193"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00937-3_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_67"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_58"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122542"},{"key":"ref7","first-page":"1","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Ranzato"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref9","first-page":"16266","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021","journal-title":"Proc. ICML"},{"key":"ref12","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref14","first-page":"1","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref15","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref16","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref23","first-page":"1","article-title":"Advancing radiograph representation learning with masked record modeling","volume-title":"Proc. 11th Int. Conf. Learn. Represent. ICLR","author":"Zhou"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3273390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3245608"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3171661"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_54"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3099165"},{"key":"ref41","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref43","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref44","article-title":"Can GPT-4 V(ision) serve medical applications? Case studies on GPT-4 V for multimodal medical diagnosis","author":"Wu","year":"2023","journal-title":"arXiv:2310.09909"},{"key":"ref45","article-title":"ChatCAD: Interactive computer-aided diagnosis on medical image using large language models","author":"Wang","year":"2023","journal-title":"arXiv:2302.07257"},{"key":"ref46","article-title":"LLaVA-med: Training a large Language-and-Vision assistant for biomedicine in one day","author":"Li","year":"2023","journal-title":"arXiv:2306.00890"},{"key":"ref47","article-title":"Towards generalist biomedical AI","author":"Tu","year":"2023","journal-title":"arXiv:2307.14334"},{"key":"ref48","article-title":"CheXagent: Towards a foundation model for chest X-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv:2401.12208"},{"key":"ref49","first-page":"1","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref50","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref55","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref60","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref62","article-title":"Grad-CAM: Why did you say that? visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2016","journal-title":"arXiv:1610.02391"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10741897\/10552817.pdf?arnumber=10552817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:26:25Z","timestamp":1732667185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":62,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3412402","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}