{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T03:55:30Z","timestamp":1790654130957,"version":"4.1.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP23K10899"],"award-info":[{"award-number":["JP23K10899"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Jpn J Radiol"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1007\/s11604-026-02032-3","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T04:25:13Z","timestamp":1784694313000},"page":"1791-1801","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Verification of the impact of differences between objective and subjective evaluation methods on the interpretation of artificial intelligence systems generating mammogram reports using vision-language model"],"prefix":"10.1007","volume":"44","author":[{"given":"Chiharu","family":"Kai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideaki","family":"Tamori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuta","family":"Hirono","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachi","family":"Ishizuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Kondo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsunehiro","family":"Ohtsuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Kasai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"2032_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","volume":"74","author":"F Bray","year":"2024","unstructured":"Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA A Cancer J Clin. 2024;74:229\u201363. https:\/\/doi.org\/10.3322\/caac.21834.","journal-title":"CA A Cancer J Clin"},{"key":"2032_CR2","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1002\/cncr.31840","volume":"125","author":"L Tab\u00e1r","year":"2019","unstructured":"Tab\u00e1r L, Dean PB, Chen THH, Yen AMF, Chen SLS, Fann JCY, et al. The incidence of fatal breast cancer measures the increased effectiveness of therapy in women participating in mammography screening. Cancer. 2019;125:515\u201323. https:\/\/doi.org\/10.1002\/cncr.31840.","journal-title":"Cancer"},{"key":"2032_CR3","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1016\/S1470-2045(20)30398-3","volume":"21","author":"SW Duffy","year":"2020","unstructured":"Duffy SW, Vulkan D, Cuckle H, Parmar D, Sheikh S, Smith RA, et al. Effect of mammographic screening from age 40 years on breast cancer mortality (UK Age trial): final results of a randomised, controlled trial. Lancet Oncol. 2020;21:1165\u201372. https:\/\/doi.org\/10.1016\/S1470-2045(20)30398-3.","journal-title":"Lancet Oncol"},{"key":"2032_CR4","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1080\/17434440.2025.2609759","volume":"23","author":"B Hyams","year":"2026","unstructured":"Hyams B, Lowry KP, Kerlikowske K. Digital screening mammograms: current status and future prospects. Expert Rev Med Devices. 2026;23:173\u201384. https:\/\/doi.org\/10.1080\/17434440.2025.2609759.","journal-title":"Expert Rev Med Devices"},{"key":"2032_CR5","doi-asserted-by":"publisher","first-page":"1343627","DOI":"10.3389\/fonc.2024.1343627","volume":"14","author":"S Hussain","year":"2024","unstructured":"Hussain S, Ali M, Naseem U, Nezhadmoghadam F, Jatoi MA, Gulliver TA, et al. Breast cancer risk prediction using machine learning: a systematic review. Front Oncol. 2024;14:1343627. https:\/\/doi.org\/10.3389\/fonc.2024.1343627.","journal-title":"Front Oncol"},{"key":"2032_CR6","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/S1470-2045(23)00298-X","volume":"24","author":"K L\u00e5ng","year":"2023","unstructured":"L\u00e5ng K, Josefsson V, Larsson AM, Larsson S, H\u00f6gberg C, Sartor H, et al. Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (Masai): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study. Lancet Oncol. 2023;24:936\u201344. https:\/\/doi.org\/10.1016\/S1470-2045(23)00298-X.","journal-title":"Lancet Oncol"},{"key":"2032_CR7","doi-asserted-by":"publisher","first-page":"e175","DOI":"10.1016\/S2589-7500(24)00267-X","volume":"7","author":"V Hernstr\u00f6m","year":"2025","unstructured":"Hernstr\u00f6m V, Josefsson V, Sartor H, Schmidt D, Larsson AM, Hofvind S, et al. Screening performance and characteristics of breast cancer detected in the Mammography Screening with Artificial Intelligence trial (Masai): a randomised, controlled, parallel-group, non-inferiority, single-blinded, screening accuracy study. Lancet Digit Health. 2025;7:e175\u201383. https:\/\/doi.org\/10.1016\/S2589-7500(24)00267-X.","journal-title":"Lancet Digit Health"},{"key":"2032_CR8","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/S0140-6736(25)02464-X","volume":"407","author":"J Gommers","year":"2026","unstructured":"Gommers J, Hernstr\u00f6m V, Josefsson V, Sartor H, Schmidt D, Hjelmgren A, et al. Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the Masai study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial. Lancet. 2026;407:505\u201314. https:\/\/doi.org\/10.1016\/S0140-6736(25)02464-X.","journal-title":"Lancet"},{"key":"2032_CR9","doi-asserted-by":"publisher","unstructured":"Dembrower K, Crippa A, Col\u00f3n E, Eklund M, Strand F; ScreenTrustCAD Trial Consortium. Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study. Lancet Digit Health. 2023;5:e703\u201311. https:\/\/doi.org\/10.1016\/S2589-7500(23)00153-X","DOI":"10.1016\/S2589-7500(23)00153-X"},{"key":"2032_CR10","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.1038\/s41467-025-57469-3","volume":"16","author":"YW Chang","year":"2025","unstructured":"Chang YW, Ryu JK, An JK, Choi N, Park YM, Ko KH, et al. Artificial intelligence for breast cancer screening in mammography (AI-STREAM): preliminary analysis of a prospective multicenter cohort study. Nat Commun. 2025;16:2248. https:\/\/doi.org\/10.1038\/s41467-025-57469-3.","journal-title":"Nat Commun"},{"key":"2032_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100530","volume":"11","author":"N Ashraf","year":"2023","unstructured":"Ashraf N, Tahir MJ, Saeed A, Ghosheh MJ, Alsheikh T, Ahmed A, et al. Incidence and factors associated with burnout in radiologists: a systematic review. Eur J Radiol Open. 2023;11:100530. https:\/\/doi.org\/10.1016\/j.ejro.2023.100530.","journal-title":"Eur J Radiol Open"},{"key":"2032_CR12","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1016\/j.jacr.2023.03.007","volume":"20","author":"IA Weissman","year":"2023","unstructured":"Weissman IA, Van Geertruyden P, Prabhakar AM, Fessell D, Alson M, Lexa FJ. Practice resources to address radiologist burnout. J Am Coll Radiol. 2023;20:494\u20139. https:\/\/doi.org\/10.1016\/j.jacr.2023.03.007.","journal-title":"J Am Coll Radiol"},{"key":"2032_CR13","doi-asserted-by":"publisher","first-page":"108870","DOI":"10.1016\/j.cmpb.2025.108870","volume":"268","author":"Y Sun","year":"2025","unstructured":"Sun Y, Wen X, Zhang Y, Jin L, Yang C, Zhang Q, et al. Visual-language foundation models in medical imaging: a systematic review and meta-analysis of diagnostic and analytical applications. Comput Methods Programs Biomed. 2025;268:108870. https:\/\/doi.org\/10.1016\/j.cmpb.2025.108870.","journal-title":"Comput Methods Programs Biomed"},{"key":"2032_CR14","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock I, Rasool G. Vision-language models for medical report generation and visual question answering: a review. Front Artif Intell. 2024;7:1430984. https:\/\/doi.org\/10.3389\/frai.2024.1430984.","journal-title":"Front Artif Intell"},{"key":"2032_CR15","doi-asserted-by":"publisher","first-page":"103264","DOI":"10.1016\/j.media.2024.103264","volume":"97","author":"G Reale-Nosei","year":"2024","unstructured":"Reale-Nosei G, Amador-Dom\u00ednguez E, Serrano E. From vision to text: a comprehensive review of natural image captioning in medical diagnosis and radiology report generation. Med Image Anal. 2024;97:103264. https:\/\/doi.org\/10.1016\/j.media.2024.103264.","journal-title":"Med Image Anal"},{"key":"2032_CR16","doi-asserted-by":"publisher","DOI":"10.2196\/59505","volume":"26","author":"R AlSaad","year":"2024","unstructured":"AlSaad R, Abd-Alrazaq A, Boughorbel S, Ahmed A, Renault MA, Damseh R, et al. Multimodal large language models in health care: applications, challenges, and future outlook. J Med Internet Res. 2024;26:e59505. https:\/\/doi.org\/10.2196\/59505.","journal-title":"J Med Internet Res"},{"key":"2032_CR17","doi-asserted-by":"publisher","first-page":"106227","DOI":"10.1016\/j.ijmedinf.2025.106227","volume":"208","author":"N Dutta","year":"2026","unstructured":"Dutta N, Bose K, Syailendra E, Chu L, Gupta P. Vision-language models in diagnostic imaging: review of technical advances, clinical validation, and practical deployment. Int J Med Inform. 2026;208:106227. https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.106227.","journal-title":"Int J Med Inform"},{"key":"2032_CR18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240885","volume":"312","author":"L Zhang","year":"2024","unstructured":"Zhang L, Liu M, Wang L, Zhang Y, Xu X, Pan Z, et al. Constructing a large language model to generate impressions from findings in radiology reports. Radiology. 2024;312:e240885. https:\/\/doi.org\/10.1148\/radiol.240885.","journal-title":"Radiology"},{"key":"2032_CR19","doi-asserted-by":"publisher","first-page":"1535168","DOI":"10.3389\/fdgth.2025.1535168","volume":"7","author":"P Singh","year":"2025","unstructured":"Singh P, Singh S. ChestX-Transcribe: a multimodal transformer for automated radiology report generation from chest x-rays. Frontiers in Digital Health. 2025;7:1535168. https:\/\/doi.org\/10.3389\/fdgth.2025.1535168.","journal-title":"Frontiers in Digital Health"},{"key":"2032_CR20","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","volume":"30","author":"K Zhang","year":"2024","unstructured":"Zhang K, Zhou R, Adhikarla E, Yan Z, Liu Y, Yu J, et al. A generalist vision-language foundation model for diverse biomedical tasks. Nat Med. 2024;30:3129\u201341. https:\/\/doi.org\/10.1038\/s41591-024-03185-2.","journal-title":"Nat Med"},{"key":"2032_CR21","doi-asserted-by":"publisher","first-page":"103299","DOI":"10.1016\/j.media.2024.103299","volume":"97","author":"W Huang","year":"2024","unstructured":"Huang W, Li C, Yang H, Liu J, Liang Y, Zheng H, et al. Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement. Med Image Anal. 2024;97:103299. https:\/\/doi.org\/10.1016\/j.media.2024.103299.","journal-title":"Med Image Anal"},{"key":"2032_CR22","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s44172-024-00271-8","volume":"3","author":"S Wang","year":"2024","unstructured":"Wang S, Zhao Z, Ouyang X, Liu T, Wang Q, Shen D. Interactive computer-aided diagnosis on medical image using large language models. Commun Eng. 2024;3:133. https:\/\/doi.org\/10.1038\/s44172-024-00271-8.","journal-title":"Commun Eng"},{"key":"2032_CR23","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1038\/s41586-026-10181-8","volume":"652","author":"L Blankemeier","year":"2026","unstructured":"Blankemeier L, Kumar A, Cohen JP, Liu J, Liu L, Veen DV, et al. Merlin: a vision language foundation model for 3D computed tomography. Nature. 2026;652:1318\u201328. https:\/\/doi.org\/10.1038\/s41586-026-10181-8.","journal-title":"Nature"},{"key":"2032_CR24","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.243774","volume":"316","author":"S Zheng","year":"2025","unstructured":"Zheng S, Zhao N, Wang J, Yu T, Yue D, Zhang W, et al. Comparison of a specialized large language model with GPT-4o for CT and MRI radiology report summarization. Radiology. 2025;316:e243774. https:\/\/doi.org\/10.1148\/radiol.243774.","journal-title":"Radiology"},{"key":"2032_CR25","doi-asserted-by":"publisher","unstructured":"Guo Z, Jin R, Liu C, Huang Y, Shi D, Supryadi, et al. Evaluating large language models: a comprehensive survey. arXiv preprint arXiv:2310.19736. 2023. https:\/\/doi.org\/10.48550\/arXiv.2310.19736","DOI":"10.48550\/arXiv.2310.19736"},{"key":"2032_CR26","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1186\/s12911-024-02757-z","volume":"24","author":"CN Ho","year":"2024","unstructured":"Ho CN, Tian T, Ayers AT, Aaron RE, Phillips V, Wolf RM, et al. Qualitative metrics from the biomedical literature for evaluating large language models in clinical decision-making: a narrative review. BMC Med Inform Decis Mak. 2024;24:357. https:\/\/doi.org\/10.1186\/s12911-024-02757-z.","journal-title":"BMC Med Inform Decis Mak"},{"key":"2032_CR27","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.24.31093","volume":"223","author":"HL Haver","year":"2024","unstructured":"Haver HL, Yi PH, Jeudy J, Bahl M. Use of ChatGPT to assign BI-RADS assessment categories to breast imaging reports. AJR Am J Roentgenol. 2024;223:e2431093. https:\/\/doi.org\/10.2214\/AJR.24.31093.","journal-title":"AJR Am J Roentgenol"},{"key":"2032_CR28","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.1016\/j.crad.2023.09.009","volume":"79","author":"P L\u00f3pez-\u00dabeda","year":"2024","unstructured":"L\u00f3pez-\u00dabeda P, Mart\u00edn-Noguerol T, Luna A. Automatic classification and prioritisation of actionable BI-RADS categories using natural language processing models. Clin Radiol. 2024;79:e1\u20137. https:\/\/doi.org\/10.1016\/j.crad.2023.09.009.","journal-title":"Clin Radiol"},{"key":"2032_CR29","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf128","volume":"8","author":"F Dennst\u00e4dt","year":"2025","unstructured":"Dennst\u00e4dt F, Lerch L, Schmerder M, Cihoric N, Cereghetti GM, Gaio R, et al. A comparative performance analysis of regular expressions and a large language model-based approach to extract the BI-RADS score from radiological reports. JAMIA Open. 2025;8:ooaf128. https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf128.","journal-title":"JAMIA Open"},{"key":"2032_CR30","doi-asserted-by":"publisher","first-page":"4988","DOI":"10.1016\/j.acra.2025.05.065","volume":"32","author":"D Pisarcik","year":"2025","unstructured":"Pisarcik D, Kissling M, Heimer J, Farkas M, Leo C, Kubik-Huch RA, et al. Artificial intelligence language models to translate professional radiology mammography reports into plain language\u2014impact on interpretability and perception by patients. Acad Radiol. 2025;32:4988\u201396. https:\/\/doi.org\/10.1016\/j.acra.2025.05.065.","journal-title":"Acad Radiol"},{"key":"2032_CR31","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1186\/s41747-024-00526-1","volume":"8","author":"R Maroncelli","year":"2024","unstructured":"Maroncelli R, Rizzo V, Pasculli M, Cicciarelli F, Macera M, Galati F, et al. Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o. Eur Radiol Exp. 2024;8:124. https:\/\/doi.org\/10.1186\/s41747-024-00526-1.","journal-title":"Eur Radiol Exp"},{"key":"2032_CR32","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-031-96625-5_17","volume-title":"Information processing in medical imaging","author":"Y Du","year":"2026","unstructured":"Du Y, Onofrey JA, Dvornek NC. Multi-view and multi-scale alignment for contrastive language-image pre-training in mammography. In: Oguz I, Zhang S, Metaxas DN, editors. Information processing in medical imaging, vol. 15830. Cham: Springer; 2026. p. 247\u201362. https:\/\/doi.org\/10.1007\/978-3-031-96625-5_17."},{"key":"2032_CR33","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1177\/09691413251334587","volume":"32","author":"DE Tekcan Sanli","year":"2025","unstructured":"Tekcan Sanli DE, Sanli AN, Yildirim D, Dogan I. Can ChatGPT detect breast cancer on mammography? J Med Screen. 2025;32:172\u20135. https:\/\/doi.org\/10.1177\/09691413251334587.","journal-title":"J Med Screen"},{"key":"2032_CR34","doi-asserted-by":"publisher","first-page":"108334","DOI":"10.1016\/j.cmpb.2024.108334","volume":"255","author":"P L\u00f3pez-\u00dabeda","year":"2024","unstructured":"L\u00f3pez-\u00dabeda P, Mart\u00edn-Noguerol T, Paulano-Godino F, Luna A. Comparative evaluation of image-based vs. text-based vs. multimodal AI approaches for automatic breast density assessment in mammograms. Comput Methods Programs Biomed. 2024;255:108334. https:\/\/doi.org\/10.1016\/j.cmpb.2024.108334.","journal-title":"Comput Methods Programs Biomed"},{"key":"2032_CR35","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s12672-025-02005-4","volume":"16","author":"F Pesapane","year":"2025","unstructured":"Pesapane F, Nicosia L, Rotili A, Penco S, Dominelli V, Trentin C, et al. A preliminary investigation into the potential, pitfalls, and limitations of large language models for mammography interpretation. Discov Onc. 2025;16:233. https:\/\/doi.org\/10.1007\/s12672-025-02005-4.","journal-title":"Discov Onc"},{"key":"2032_CR36","doi-asserted-by":"publisher","first-page":"3229","DOI":"10.1016\/j.csbj.2025.07.018","volume":"27","author":"E Godoy","year":"2025","unstructured":"Godoy E, Mellado D, de Ferrari J, Querales M, Saez A, Chabert S, et al. Hybrid framework for automated generation of mammography radiology reports. Comput Struct Biotechnol J. 2025;27:3229\u201339. https:\/\/doi.org\/10.1016\/j.csbj.2025.07.018.","journal-title":"Comput Struct Biotechnol J"},{"key":"2032_CR37","doi-asserted-by":"publisher","unstructured":"Sung NJ, Lee D, Choi BH, Park CJ. AMRG: extend vision language models for automatic mammography report generation. arXiv preprint arXiv:2508.09225; 2025. https:\/\/doi.org\/10.48550\/arXiv.2508.09225","DOI":"10.48550\/arXiv.2508.09225"},{"key":"2032_CR38","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1038\/s41597-022-01238-0","volume":"9","author":"R Khaled","year":"2022","unstructured":"Khaled R, Helal M, Alfarghaly O, Mokhtar O, Elkorany A, El Kassas H, et al. Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research. Sci Data. 2022;9:122. https:\/\/doi.org\/10.1038\/s41597-022-01238-0.","journal-title":"Sci Data"},{"key":"2032_CR39","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat Med. 2025;31:60\u20139. https:\/\/doi.org\/10.1038\/s41591-024-03425-5.","journal-title":"Nat Med"},{"key":"2032_CR40","doi-asserted-by":"publisher","unstructured":"Wang P, Bai S, Tan S, Wang S, Fan Z, Bai J, et al. Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191. 2024. https:\/\/doi.org\/10.48550\/arXiv.2409.12191","DOI":"10.48550\/arXiv.2409.12191"},{"key":"2032_CR41","doi-asserted-by":"publisher","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, et al. Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685v2. 2021. https:\/\/doi.org\/10.48550\/arXiv.2106.09685","DOI":"10.48550\/arXiv.2106.09685"},{"key":"2032_CR42","unstructured":"Rouge LCY. A package for automatic evaluation of summaries. In: Proceedings of the ACL workshop on text summarization branches out; 2004; Barcelona, Spain; p. 74\u201381. https:\/\/aclanthology.org\/W04-1013. Accessed February 20, 2026"},{"key":"2032_CR43","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on Association for Computational Linguistics\u2014ACL \u201902. Morristown, NJ: Association for Computational Linguistics; 2001; p. 311. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"2032_CR44","doi-asserted-by":"crossref","unstructured":"Post M. A call for clarity in reporting BLEU scores. In: Proceedings of the third conference on machine translation [Research papers]; 2018; p. 186\u201391","DOI":"10.18653\/v1\/W18-6319"},{"key":"2032_CR45","doi-asserted-by":"publisher","unstructured":"Zheng L, Chiang WL, Sheng Y, Zhuang S, Wu Z, Zhuang Y, et al. Judging LLM-as-a-judge with MT-Bench and chatbot arena. arXiv preprint arXiv:2306.05685. 2023. https:\/\/doi.org\/10.48550\/arXiv.2306.05685","DOI":"10.48550\/arXiv.2306.05685"},{"key":"2032_CR46","first-page":"14","volume":"34","author":"K Suzuki","year":"2017","unstructured":"Suzuki K. Machine learning in medical imaging before and after introduction of deep learning. J Med Imaging Inf Sci. 2017;34:14\u201324.","journal-title":"J Med Imaging Inf Sci"},{"key":"2032_CR47","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/s11604-025-01907-1","volume":"44","author":"D Ueda","year":"2025","unstructured":"Ueda D, Walston SL, Kurokawa R, Saida T, Honda M, Iima M, et al. Artificial superintelligence alignment in healthcare. Jpn J Radiol. 2025;44:627\u201340. https:\/\/doi.org\/10.1007\/s11604-025-01907-1.","journal-title":"Jpn J Radiol"}],"container-title":["Japanese Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-026-02032-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11604-026-02032-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-026-02032-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T03:08:51Z","timestamp":1790651331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11604-026-02032-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":47,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["2032"],"URL":"https:\/\/doi.org\/10.1007\/s11604-026-02032-3","relation":{},"ISSN":["1867-1071","1867-108X"],"issn-type":[{"value":"1867-1071","type":"print"},{"value":"1867-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"31 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Chiharu Kai, Sachi Ishizuka, and Satoshi Kasai received a research grant and research support from KONICA MINOLTA, INC. Satoshi Kasai was a consultant to KONICA MINOLTA, INC. Tsunehiro Ohtsuka received payment for expert testimony from KONICA MINOLTA, INC. Satoshi Kondo received research support from KONICA MINOLTA, INC. Hideaki Tamori is affiliated with The Asahi Shimbun Company. Yuta Hirono is affiliated with TOITU CO., LTD.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Institutional Review Board of Fujita Health University (approval number: HM25-534).","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}}]}}