{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:36:19Z","timestamp":1782394579462,"version":"3.54.5"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62203303"],"award-info":[{"award-number":["62203303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/jbhi.2025.3609739","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:38:25Z","timestamp":1757957905000},"page":"1506-1519","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing 3D Medical Image Understanding With Pretraining Aided by 2D Multimodal Large Language Models"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1210-1306","authenticated-orcid":false,"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuancheng","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huping","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9065-3691","authenticated-orcid":false,"given":"Yi","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Med3D: Transfer learning for 3D medical image analysis","author":"Chen","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293771"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_42"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230477"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_58"},{"key":"ref16","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref17","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref18","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_6"},{"key":"ref20","article-title":"Generative text-guided 3D vision-language pretraining for unified medical image segmentation","author":"Chen","year":"2023"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1101\/2023.10.26.23297629","article-title":"Performance of multimodal GPT-4V on USMLE with image: Potential for imaging diagnostic support with explanations","author":"Yang","year":"2023"},{"key":"ref22","article-title":"Can GPT-4V(ision) serve medical applications? Case studies on GPT-4V for multimodal medical diagnosis","author":"Wu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","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","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62385-7"},{"key":"ref34","article-title":"M3D: Advancing 3D medical image analysis with multi-modal large language models","author":"Bai","year":"2024"},{"key":"ref35","article-title":"Utilizing synthetic data for medical vision-language pre-training: Bypassing the need for real images","author":"Liu","year":"2023"},{"key":"ref36","article-title":"RoentGen: Vision-language foundation model for chest X-ray generation","author":"Chambon","year":"2022"},{"key":"ref37","article-title":"Medimp: 3D medical images with clinical prompts from limited tabular data for renal transplantation","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Milecki","year":"2023"},{"key":"ref38","article-title":"Joint distribution optimal transportation for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Courty","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3349284"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3406559"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548067"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612087"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3238067"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3412420"},{"issue":"80","key":"ref46","first-page":"1","article-title":"Learning to match via inverse optimal transport","volume":"20","author":"Li","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/19M1261122"},{"key":"ref48","article-title":"Data efficient language-supervised zero-shot recognition with optimal transport distillation","author":"Wu","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s002110050002"},{"key":"ref50","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi","year":"2013"},{"key":"ref51","article-title":"Revisiting deep audio-text retrieval through the lens of transportation","author":"Luong","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7439(99)00047-7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1090\/mcom\/3303"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/141000439"},{"issue":"1","key":"ref57","first-page":"533","article-title":"Ground metric learning","volume":"15","author":"Cuturi","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(80)90054-4"},{"key":"ref59","first-page":"2504","article-title":"A swiss army knife for minimax optimal transport","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dhouib","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.02.006"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30695-9"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101950"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3100536"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.9.1498"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.nic.2005.09.008"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-01064-w"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21407"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.pneurobio.2011.09.005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_15"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02158"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2400640"},{"key":"ref76","article-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"key":"ref77","article-title":"HuatuoGPT-vision, towards injecting medical visual knowledge into multimodal llms at scale","author":"Chen","year":"2024"},{"key":"ref78","article-title":"MONAI: An open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022"},{"issue":"11","key":"ref79","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4314"},{"key":"ref81","first-page":"717612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang","year":"2022"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11372623\/11164292.pdf?arnumber=11164292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:07:40Z","timestamp":1770671260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":82,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3609739","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}