{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T22:53:18Z","timestamp":1787698398899,"version":"build-2784847793"},"reference-count":35,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"am","delay-in-days":352,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"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":[[2025,8]]},"DOI":"10.1016\/j.acra.2025.04.060","type":"journal-article","created":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T07:09:23Z","timestamp":1747465763000},"page":"4347-4354","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":11,"title":["Evaluating the Performance of Reasoning Large Language Models on Japanese Radiology Board Examination Questions"],"prefix":"10.1016","volume":"32","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":"Hiroto","family":"Takamure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoki","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaori","family":"Shiraishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naofumi","family":"Yoshida","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":"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":[{"key":"10.1016\/j.acra.2025.04.060_bib1","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3348\/kjr.2023.0997","article-title":"Large language models: a guide for radiologists","volume":"25","author":"Kim","year":"2024","journal-title":"Korean J Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib2","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s11604-024-01552-0","article-title":"The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI","volume":"42","author":"Nakaura","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib3","unstructured":"Pellegrini C., \u00d6zsoy E., Busam B.,\u00a0et al. RaDialog: a large vision-language model for radiology report generation and conversational assistance. arXiv; 2023. doi: 10.48550\/arXiv.2311.18681."},{"key":"10.1016\/j.acra.2025.04.060_bib4","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s11604-023-01487-y","article-title":"Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports","volume":"42","author":"Nakaura","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib5","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1007\/s11547-024-01915-7","article-title":"ChatGPT and radiology report: potential applications and limitations","volume":"129","author":"Parillo","year":"2024","journal-title":"Radiol Med"},{"key":"10.1016\/j.acra.2025.04.060_bib6","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.crad.2023.11.011","article-title":"Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard","volume":"79","author":"Infante","year":"2024","journal-title":"Clin Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib7","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.8895","article-title":"Use of a large language model to assess clinical acuity of adults in the emergency department","volume":"7","author":"Williams","year":"2024","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.acra.2025.04.060_bib8","doi-asserted-by":"crossref","first-page":"3872","DOI":"10.1016\/j.acra.2024.06.046","article-title":"Large language models as tools to generate radiology board-style multiple-choice questions","volume":"31","author":"Mistry","year":"2024","journal-title":"Acad Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib9","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLoS Digit Health Public Libr Sci"},{"key":"10.1016\/j.acra.2025.04.060_bib10","article-title":"How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment","volume":"9","author":"Gilson","year":"2023","journal-title":"JMIR Med"},{"key":"10.1016\/j.acra.2025.04.060_bib11","doi-asserted-by":"crossref","DOI":"10.2196\/50965","article-title":"Comparison of the performance of GPT-3.5 and GPT-4 with that of medical students on the written German medical licensing examination: observational study","volume":"10","author":"Meyer","year":"2024","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.acra.2025.04.060_bib12","doi-asserted-by":"crossref","DOI":"10.1097\/MD.0000000000034673","article-title":"ChatGPT performance in the medical specialty exam: an observational study","volume":"102","author":"Oztermeli","year":"2023","journal-title":"Medicine"},{"key":"10.1016\/j.acra.2025.04.060_bib13","doi-asserted-by":"crossref","unstructured":"Williams S, Huckle J. Easy problems that LLMs get wrong. arXiv; 2024. doi:10.48550\/arXiv.2405.19616.","DOI":"10.1007\/978-3-031-84457-7_19"},{"key":"10.1016\/j.acra.2025.04.060_bib14","unstructured":"Gendron G., Bao Q., Witbrock M., et al. Large language models are not strong abstract reasoners. arXiv; 2024. doi: 10.48550\/arXiv.2305.19555."},{"key":"10.1016\/j.acra.2025.04.060_bib15","unstructured":"Learning to reason with LLMs. Available at: \u3008https:\/\/openai.com\/index\/learning-to-reason-with-llms\/\u3009. Accessed November 25, 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib16","unstructured":"Introducing OpenAI o1. Available at: \u3008https:\/\/openai.com\/index\/introducing-openai-o1-preview\/\u3009. Accessed November 25, 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib17","unstructured":"OpenAI o1 System Card. Available at: \u3008https:\/\/openai.com\/index\/openai-o1-system-card\/\u3009. Accessed November 25, 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib18","unstructured":"Wu S., Peng Z., Du X., et al. A comparative study on reasoning patterns of OpenAI\u2019s O1 model. arXiv; 2024. doi: 10.48550\/arXiv.2410.13639."},{"key":"10.1016\/j.acra.2025.04.060_bib19","doi-asserted-by":"crossref","unstructured":"de Winter J., Dodou D., Eisma Y.B. System 2 thinking in OpenAI\u2019s O1-preview model: near-perfect performance on a mathematics exam. arXiv; 2024. doi: 10.48550\/arXiv.2410.07114.","DOI":"10.3390\/computers13110278"},{"key":"10.1016\/j.acra.2025.04.060_bib20","unstructured":"Gao B., Song F., Yang Z., et al. Omni-MATH: a universal olympiad level mathematic benchmark for large language models. arXiv; 2024. doi: 10.48550\/arXiv.2410.07985."},{"key":"10.1016\/j.acra.2025.04.060_bib21","unstructured":"McCoy RT, Yao S, Friedman D, et al. When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1. arXiv.org; 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib22","unstructured":"Valmeekam K., Stechly K., Kambhampati S. LLMs still can\u2019t plan; can LRMs? A preliminary evaluation of OpenAI\u2019s O1 on PlanBench. arXiv; 2024. doi: 10.48550\/arXiv.2409.13373."},{"key":"10.1016\/j.acra.2025.04.060_bib23","unstructured":"OpenAI Platform. Available at: \u3008https:\/\/platform.openai.com\/docs\/guides\/reasoning\u3009. Accessed November 25, 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib24","unstructured":"Sequoia Capital. OpenAI\u2019s Noam Brown, Ilge Akkaya and Hunter Lightman on O1 and teaching LLMs to reason better. Available at: \u3008https:\/\/www.youtube.com\/watch?v=jPluSXJpdrA\u3009. 2024. Accessed November 25, 2024."},{"key":"10.1016\/j.acra.2025.04.060_bib25","unstructured":"Wei J., Wang X., Schuurmans D., et al. Chain-of-thought prompting elicits reasoning in large language models. arXiv; 2023. doi: 10.48550\/arXiv.2201.11903."},{"key":"10.1016\/j.acra.2025.04.060_bib26","unstructured":"Wang C., Deng Y., Lyu Z., et al. Q*: improving multi-step reasoning for LLMs with deliberative planning. arXiv; 2024. doi: 10.48550\/arXiv.2406.14283."},{"key":"10.1016\/j.acra.2025.04.060_bib27","unstructured":"Kumar A., Zhuang V., Agarwal R., et al. Training language models to self-correct via reinforcement learning. arXiv; 2024. doi: 10.48550\/arXiv.2409.12917."},{"key":"10.1016\/j.acra.2025.04.060_bib28","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"10.1016\/j.acra.2025.04.060_bib29","doi-asserted-by":"crossref","unstructured":"Liu X., Wu Z., Wu X.,\u00a0et al. Are LLMs capable of data-based statistical and causal reasoning? Benchmarking advanced quantitative reasoning with data. arXiv; 2024. doi: 10.48550\/arXiv.2402.17644.","DOI":"10.18653\/v1\/2024.findings-acl.548"},{"key":"10.1016\/j.acra.2025.04.060_bib30","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s11604-023-01491-2","article-title":"Performance evaluation of ChatGPT, GPT-4, and Bard on the official board examination of the Japan Radiology Society","volume":"42","author":"Toyama","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib31","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.2025.04.060_bib32","doi-asserted-by":"crossref","first-page":"2394","DOI":"10.1016\/j.acra.2024.10.035","article-title":"Performance of multimodal large language models in Japanese Diagnostic Radiology Board Examinations (2021\u20132023)","volume":"32","author":"Nakaura","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib33","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1007\/s11604-024-01633-0","article-title":"Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations","volume":"42","author":"Oura","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib34","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1016\/j.acra.2024.11.028","article-title":"Large language models with vision on diagnostic radiology board exam style questions","volume":"32","author":"Sun","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.acra.2025.04.060_bib35","doi-asserted-by":"crossref","first-page":"4365","DOI":"10.1016\/j.acra.2024.09.005","article-title":"Evaluating GPT-4o\u2019s performance in the official European Board of Radiology exam: a comprehensive assessment","volume":"31","author":"Be\u015fler","year":"2024","journal-title":"Acad Radiol"}],"container-title":["Academic Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S107663322500412X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S107663322500412X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:44:33Z","timestamp":1768221873000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S107663322500412X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["S107663322500412X"],"URL":"https:\/\/doi.org\/10.1016\/j.acra.2025.04.060","relation":{},"ISSN":["1076-6332"],"issn-type":[{"value":"1076-6332","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating the Performance of Reasoning Large Language Models on Japanese Radiology Board Examination Questions","name":"articletitle","label":"Article Title"},{"value":"Academic Radiology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.acra.2025.04.060","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Association of Academic Radiology. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}