{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T14:03:54Z","timestamp":1781273034675,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Department of Medicine and the Intelligent Clinical Care Center at the University of Florida College of Medicine"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/jbhi.2025.3604595","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:31:39Z","timestamp":1756755099000},"page":"2524-2536","source":"Crossref","is-referenced-by-count":19,"title":["Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0696-4658","authenticated-orcid":false,"given":"Yu","family":"Xin","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gorkem Can","family":"Ates","sequence":"additional","affiliation":[{"name":"Department of Medicine, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2669-2610","authenticated-orcid":false,"given":"Kuang","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4931-4839","authenticated-orcid":false,"given":"Wei","family":"Shao","sequence":"additional","affiliation":[{"name":"Department of Medicine, Department of Electrical and Computer Engineering, and the Intelligent Clinical Care Center, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref3","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","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07618-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62385-7"},{"key":"ref7","article-title":"M3D: Advancing 3D medical image analysis with multi-modal large language models","author":"Bai","year":"2024"},{"key":"ref8","article-title":"Dcformer: Efficient 3D vision-language modeling with decomposed convolutions","author":"Ates","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref10","first-page":"24261","article-title":"Mlp-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin","year":"2021"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref14","article-title":"E3D-GPT: Enhanced 3D visual foundation for medical vision-language model","author":"Lai","year":"2024"},{"key":"ref15","article-title":"One model to rule them all: Towards universal segmentation for medical images with text prompts","author":"Zhao","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0119"},{"key":"ref17","article-title":"Text3DSAM: Text-guided 3 D medical image segmentation using SAM-inspired architecture","volume-title":"Proc. CVPR 2025, Found. Models 3D Biomed. Image Segmentation","author":"Xin","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref19","article-title":"Addressing data bias problems for chest x-ray image report generation","author":"Harzig","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref24","article-title":"The refinedweb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Penedo","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref26","first-page":"353","article-title":"Med-flamingo: A multimodal medical few-shot learner","volume-title":"Proc. Mach. Learn. Res.","author":"Moor","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_45"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01599-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63820-7_22"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113993"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/app15062983"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02552-9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","first-page":"12966","article-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Chen","year":"2025"},{"key":"ref41","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref42","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref44","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref45","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. and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref46","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref49","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102995"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01378"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11424173\/11145341.pdf?arnumber=11145341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:05Z","timestamp":1773086345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11145341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3604595","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}