{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T13:32:02Z","timestamp":1782135122748,"version":"3.54.5"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA272991"],"award-info":[{"award-number":["R01CA272991"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EB032680"],"award-info":[{"award-number":["R01EB032680"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01DE033512"],"award-info":[{"award-number":["R01DE033512"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54CA274513"],"award-info":[{"award-number":["U54CA274513"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tmi.2026.3661001","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:54:59Z","timestamp":1770152099000},"page":"2727-2737","source":"Crossref","is-referenced-by-count":15,"title":["Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models"],"prefix":"10.1109","volume":"45","author":[{"given":"Yuxiang","family":"Lai","sequence":"first","affiliation":[{"name":"Department of Computer Science and Informatics, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jike","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0249-8952","authenticated-orcid":false,"given":"Yuheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Emory and Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6342-1078","authenticated-orcid":false,"given":"Konstantinos","family":"Psounis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9023-5855","authenticated-orcid":false,"given":"Xiaofeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Emory and Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref2","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv:2403.05530"},{"key":"ref3","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref4","article-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2022","journal-title":"arXiv:2211.12588"},{"key":"ref5","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref6","first-page":"353","article-title":"Med-flamingo: A multimodal medical few-shot learner","volume-title":"Proc. Mach. Learn. Health (ML4H)","author":"Moor"},{"key":"ref7","article-title":"PMC-VQA: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023","journal-title":"arXiv:2305.10415"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref9","article-title":"HuatuoGPT-vision, towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024","journal-title":"arXiv:2406.19280"},{"key":"ref10","article-title":"Towards universal text-driven CT image segmentation","author":"Li","year":"2025","journal-title":"arXiv:2503.06030"},{"key":"ref11","article-title":"SFT memorizes, RL generalizes: A comparative study of foundation model post-training","author":"Chu","year":"2025","journal-title":"arXiv:2501.17161"},{"key":"ref12","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv:2402.03300"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref15","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref16","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref17","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04981-0_32"},{"key":"ref21","article-title":"Vision-r1: Incentivizing reasoning capability in multimodal large language models","author":"Huang","year":"2025","journal-title":"arXiv:2503.06749"},{"key":"ref22","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref24","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref25","article-title":"Think or not think: A study of explicit thinking in rule-based visual reinforcement fine-tuning","author":"Li","year":"2025","journal-title":"arXiv:2503.16188"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref28","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref29","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref30","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref31","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref32","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data","author":"Wu","year":"2023","journal-title":"arXiv:2308.02463"},{"key":"ref33","article-title":"HealthGPT: A medical large vision-language model for unifying comprehension and generation via heterogeneous knowledge adaptation","author":"Lin","year":"2025","journal-title":"arXiv:2502.09838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref36","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref37","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv:2307.08691"},{"key":"ref38","article-title":"Reasoning or memorization? Unreliable results of reinforcement learning due to data contamination","author":"Wu","year":"2025","journal-title":"arXiv:2507.10532"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11550367\/11371404.pdf?arnumber=11371404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:17Z","timestamp":1780602977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11371404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2026.3661001","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}