{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T16:40:50Z","timestamp":1792687250306,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-19669-1","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:36:18Z","timestamp":1760362578000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Assessment of ChatGPT performance in orbital MRI reporting with multimetric evaluation of transformer based language models"],"prefix":"10.1038","volume":"15","author":[{"given":"Alessandro","family":"Tel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Bolognesi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Michelutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Biglioli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimo","family":"Robiony","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"19669_CR1","unstructured":"Naveed, H. et al. A comprehensive overview of large Language models. ACM Trans. Intell. Syst. Technology (2023)."},{"key":"19669_CR2","unstructured":"Vaswani, A. et al. Polosukhin, L.I. Attention is all you need. Advances in neural information processing systems, 30 (2017)."},{"key":"19669_CR3","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal, K. et al. Toward expert-level medical question answering with large Language models. Nat. Med. 31, 943\u2013950 (2025).","journal-title":"Nat. Med."},{"key":"19669_CR4","doi-asserted-by":"publisher","first-page":"4951","DOI":"10.1016\/j.procs.2024.09.452","volume":"246","author":"S Chai","year":"2024","unstructured":"Chai, S. et al. Ladder fine tuning approach for Sam integrating complementary network. Procedia Comput. Sci. 246, 4951\u20134958 (2024).","journal-title":"Procedia Comput. Sci."},{"key":"19669_CR5","doi-asserted-by":"publisher","first-page":"100021","DOI":"10.1016\/j.ejrai.2025.100021","volume":"2","author":"JP Kao","year":"2025","unstructured":"Kao, J. P. & Kao, H. T. Large Language models in radiology: A technical and clinical perspective. Eur. J. Radiol. Artif. Intell. 2, 100021 (2025).","journal-title":"Eur. J. Radiol. Artif. Intell."},{"issue":"2","key":"19669_CR6","doi-asserted-by":"publisher","first-page":"e242575","DOI":"10.1148\/radiol.242575","volume":"May;315","author":"C Sun","year":"2025","unstructured":"Sun, C. et al. Generative large Language models trained for detecting errors in radiology reports. Radiology May;315 (2), e242575 (2025).","journal-title":"Radiology"},{"key":"19669_CR7","doi-asserted-by":"publisher","first-page":"7057","DOI":"10.3390\/jcm13237057","volume":"13","author":"RW Lee","year":"2024","unstructured":"Lee, R. W., Lee, K. H., Yun, J. S., Kim, M. S. & Choi, H. S. Comparative analysis of M4CXR, an LLM-Based chest X-Ray report generation model, and ChatGPT in radiological interpretation. J. Clin. Med. 13, 7057 (2024).","journal-title":"J. Clin. Med."},{"key":"19669_CR8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3390\/asi8020039","volume":"8","author":"C Dasanayaka","year":"2025","unstructured":"Dasanayaka, C. et al. AI and large Language models for orthopantomography radiology report generation and Q&A. Appl. Syst. Innov. 8, 39 (2025).","journal-title":"Appl. Syst. Innov."},{"key":"19669_CR9","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s44172-024-00271-8","volume":"3","author":"S Wang","year":"2024","unstructured":"Wang, S. et al. Interactive computer-aided diagnosis on medical image using large Language models. Commun. Eng. 3, 133 (2024).","journal-title":"Commun. Eng."},{"key":"19669_CR10","doi-asserted-by":"publisher","first-page":"116442","DOI":"10.1016\/j.neuroimage.2019.116442","volume":"208","author":"RA Brown","year":"2020","unstructured":"Brown, R. A. et al. Deep learning segmentation of orbital fat to calibrate conventional MRI for longitudinal studies. Neuroimage 208, 116442 (2020).","journal-title":"Neuroimage"},{"key":"19669_CR11","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","volume":"97","author":"J Chen","year":"2024","unstructured":"Chen, J. et al. TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of Transformers. Med. Image Anal. 97, 103280 (2024).","journal-title":"Med. Image Anal."},{"key":"19669_CR12","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1186\/s13244-023-01560-0","volume":"14","author":"DP dos Santos","year":"2023","unstructured":"dos Santos, D. P., Kotter, E., Mildenberger, P. & Mart\u00ed-Bonmat\u00ed, L. European society of radiology (ESR). ESR paper on structured reporting in radiology\u2014update 2023. Insights into Imaging. 14, 199 (2023).","journal-title":"Insights into Imaging"},{"key":"19669_CR13","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T. & Zhu, W. J. BLEU: a method for automatic evaluation of machine translation. in Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL \u201902 311Association for Computational Linguistics, Philadelphia, Pennsylvania, (2001). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"19669_CR14","doi-asserted-by":"crossref","unstructured":"Badshah, S. & Sajjad, H. D. A. F. E. LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering. arXiv preprint arXiv:2503.08542, (2025).","DOI":"10.32388\/B69SKY"},{"key":"19669_CR15","unstructured":"Chin-Yew, L. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, 74\u201381, Barcelona, Spain. Association for Computational Linguistics (2004)."},{"key":"19669_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. BERTScore: Evaluating Text Generation with BERT. Preprint at (2020). https:\/\/doi.org\/10.48550\/arXiv.1904.09675","DOI":"10.48550\/arXiv.1904.09675"},{"key":"19669_CR17","unstructured":"Jain, S., Agrawal, A., Saporta, A., Truong, S. Q., Duong, D. N., Bui, T., \u2026 Rajpurkar,P. (2021). Radgraph: Extracting clinical entities and relations from radiology reports.arXiv preprint arXiv:2106.14463."},{"key":"19669_CR18","doi-asserted-by":"publisher","unstructured":"Smit, A. et al. CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT. Preprint at (2020). https:\/\/doi.org\/10.48550\/arXiv.2004.09167","DOI":"10.48550\/arXiv.2004.09167"},{"key":"19669_CR19","first-page":"100488","volume":"13","author":"A de In\u00e1cio","year":"2023","unstructured":"de In\u00e1cio, A., Lopes, H. S. & S. & Evaluation metrics for video captioning: A survey. Mach. Learn. Appl. 13, 100488 (2023).","journal-title":"Mach. Learn. Appl."},{"key":"19669_CR20","doi-asserted-by":"publisher","unstructured":"Liu, Y. et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach. Preprint at (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.11692","DOI":"10.48550\/arXiv.1907.11692"},{"key":"19669_CR21","doi-asserted-by":"publisher","unstructured":"Shor, J. et al. Association for Computational Linguistics, Toronto, Canada,. Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings. in Proceedings of the 5th Clinical Natural Language Processing Workshop 1\u20137 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.clinicalnlp-1.1","DOI":"10.18653\/v1\/2023.clinicalnlp-1.1"},{"key":"19669_CR22","unstructured":"Morgan, A., BERTScore For, L. L. M. & Evaluation Comet (2024). https:\/\/www.comet.com\/site\/blog\/bertscore-for-llm-evaluation\/"},{"key":"19669_CR23","unstructured":"Jain, S., Agrawal, A., Saporta, A. & Truong, S. Q. RadGraph: Extracting Clinical Entities and Relations from Radiology Reports."},{"key":"19669_CR24","doi-asserted-by":"publisher","first-page":"173","DOI":"10.2967\/jnumed.124.268072","volume":"66","author":"TJ Bradshaw","year":"2025","unstructured":"Bradshaw, T. J. et al. Large Language models and large multimodal models in medical imaging: A primer for physicians. J. Nucl. Med. 66, 173\u2013182 (2025).","journal-title":"J. Nucl. Med."},{"key":"19669_CR25","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.21037\/qims-23-892","volume":"14","author":"D Tian","year":"2024","unstructured":"Tian, D., Jiang, S., Zhang, L., Lu, X. & Xu, Y. The role of large Language models in medical image processing: a narrative review. Quant. Imaging Med. Surg. 14, 1108\u20131121 (2024).","journal-title":"Quant. Imaging Med. Surg."},{"key":"19669_CR26","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1016\/j.jacr.2024.06.014","volume":"21","author":"AS Kathait","year":"2024","unstructured":"Kathait, A. S. et al. Assessing laterality errors in radiology: comparing generative artificial intelligence and natural Language processing. J. Am. Coll. Radiol. 21, 1575\u20131582 (2024).","journal-title":"J. Am. Coll. Radiol."},{"key":"19669_CR27","doi-asserted-by":"publisher","DOI":"10.4274\/dir.2024.242854","author":"B Ko\u00e7ak","year":"2025","unstructured":"Ko\u00e7ak, B. et al. Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects. Diagn. Interventional Radiol. https:\/\/doi.org\/10.4274\/dir.2024.242854 (2025).","journal-title":"Diagn. Interventional Radiol."},{"key":"19669_CR28","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A. et al. UNETR: Transformers for 3D Medical Image Segmentation. Preprint at (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.10504","DOI":"10.48550\/arXiv.2103.10504"},{"key":"19669_CR29","unstructured":"GPT-4. (2024). https:\/\/openai.com\/index\/gpt-4-research\/."},{"key":"19669_CR30","unstructured":"Health, C. D. and R. Artificial Intelligence and Machine Learning in Software as a Medical Device. FDA (2025)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19669-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19669-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19669-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:36:22Z","timestamp":1760362582000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19669-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["19669"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-19669-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"4 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"35654"}}