{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T15:45:10Z","timestamp":1794498310862,"version":"4.9.1"},"reference-count":17,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["academicradiology.org","clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Academic Radiology"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.acra.2025.10.051","type":"journal-article","created":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T04:46:22Z","timestamp":1764391582000},"page":"348-358","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"title":["Performance of State-of-the-Art Multimodal Large Language Models on an Image-Rich Radiology Board Examination: Comparison to Human Examinees"],"prefix":"10.1016","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-0341","authenticated-orcid":false,"given":"Takeshi","family":"Nakaura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoki","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takanori","family":"Masuda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasunori","family":"Nagayama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Uetani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masafumi","family":"Kidoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seitaro","family":"Oda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshinori","family":"Funama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshinori","family":"Hirai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.acra.2025.10.051_bib1","article-title":"Comparing the performance of popular large language models on the national board of medical examiners sample questions","volume":"16","author":"Abbas","year":"2024","journal-title":"Cureus"},{"key":"10.1016\/j.acra.2025.10.051_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2024.105673","article-title":"Evaluating the effectiveness of advanced large language models in medical knowledge: a comparative study using Japanese national medical examination","volume":"193","author":"Liu","year":"2025","journal-title":"Int J Med Inform"},{"issue":"3","key":"10.1016\/j.acra.2025.10.051_bib3","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1007\/s00330-024-11115-6","article-title":"Revolution or risk?-Assessing the potential and challenges of GPT-4V in radiologic image interpretation","volume":"35","author":"Huppertz","year":"2025","journal-title":"Eur Radiol"},{"issue":"8","key":"10.1016\/j.acra.2025.10.051_bib4","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1007\/s11604-024-01561-z","article-title":"GPT-4 turbo with vision fails to outperform text-only GPT-4 turbo in the Japan Diagnostic Radiology Board Examination","volume":"42","author":"Hirano","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.acra.2025.10.051_bib5","first-page":"2394","article-title":"Performance of multimodal large language models in Japanese Diagnostic Radiology Board Examinations (2021-2023)","volume":"32","author":"Nakaura","year":"2025"},{"key":"10.1016\/j.acra.2025.10.051_bib6","unstructured":"Yao H, Yin Q, Zhang J, et al. R1-ShareVL: incentivizing reasoning capability of multimodal large language models via share-GRPO. 2025; arXiv:2505.16673. https:\/\/doi.org\/10.48550\/arXiv.2505.16673."},{"key":"10.1016\/j.acra.2025.10.051_bib7","unstructured":"Zhou G, Qiu P, Chen C, et al. Reinforced MLLM: a survey on RL-based reasoning in multimodal large language models. 2025; arXiv:2504.21277. https:\/\/doi.org\/10.48550\/arXiv.2504.21277."},{"key":"10.1016\/j.acra.2025.10.051_bib8","unstructured":"Shi M, Liu F, Wang S, et al. Eagle: exploring the design space for multimodal LLMs with mixture of encoders. 2025; arXiv:2408.15998. https:\/\/doi.org\/10.48550\/arXiv.2408.15998."},{"key":"10.1016\/j.acra.2025.10.051_bib9","doi-asserted-by":"crossref","unstructured":"Jain J, Yang J, Shi H. VCoder: versatile vision encoders for multimodal large language models. 2023; arXiv:2312.14233. https:\/\/doi.org\/10.48550\/arXiv.2312.14233.","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"10.1016\/j.acra.2025.10.051_bib10","unstructured":"Wei J, Wang X, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models. 2023; arXiv:2201.11903. https:\/\/doi.org\/10.48550\/arXiv.2201.11903."},{"key":"10.1016\/j.acra.2025.10.051_bib11","first-page":"277","article-title":"Science in the age of large language models","author":"Birhane","year":"2023"},{"key":"10.1016\/j.acra.2025.10.051_bib12","unstructured":"Ouyang L, Wu J, Jiang X, et al. Training language models to follow instructions with human feedback. 2022; arXiv:2203.02155. https:\/\/doi.org\/10.48550\/arXiv.2203.02155."},{"key":"10.1016\/j.acra.2025.10.051_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102888","article-title":"A comprehensive survey of large language models and multimodal large language models in medicine","volume":"117","author":"Xiao","year":"2025","journal-title":"Inform Fusion"},{"key":"10.1016\/j.acra.2025.10.051_bib14","unstructured":"Sukeda I. Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources. 2024; arXiv:2409.11783. https:\/\/doi.org\/10.48550\/arXiv.2409.11783."},{"key":"10.1016\/j.acra.2025.10.051_bib15","unstructured":"Alaa A, Hartvigsen T, Golchini N, et al. Medical large language model benchmarks should prioritize construct validity. 2025; arXiv:2503.10694v1, Accessed May 27, 2025 \u3008https:\/\/arxiv.org\/abs\/2503.10694v1\u3009"},{"key":"10.1016\/j.acra.2025.10.051_bib16","unstructured":"Cheng Y, Chang Y, Wu Y. A survey on data contamination for large language models. 2025; arXiv:2502.14425. https:\/\/doi.org\/10.48550\/arXiv.2502."},{"key":"10.1016\/j.acra.2025.10.051_bib17","article-title":"When artificial intelligence steers the boat: utilization scenarios for low-dose CT lung cancer screening","volume":"17","author":"Wu","year":"2025","journal-title":"Am J Roentgenol"}],"container-title":["Academic Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1076633225010372?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1076633225010372?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T19:41:53Z","timestamp":1768938113000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1076633225010372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":17,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["S1076633225010372"],"URL":"https:\/\/doi.org\/10.1016\/j.acra.2025.10.051","relation":{},"ISSN":["1076-6332"],"issn-type":[{"value":"1076-6332","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Performance of State-of-the-Art Multimodal Large Language Models on an Image-Rich Radiology Board Examination: Comparison to Human Examinees","name":"articletitle","label":"Article Title"},{"value":"Academic Radiology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.acra.2025.10.051","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Association of Academic Radiology. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}]}}