{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T21:31:15Z","timestamp":1791495075059,"version":"4.3.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:sec>\n                    <jats:title>Abstract<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) and large language models (LLMs) are increasingly integrated into radiology, offering new possibilities for advanced imaging techniques, including cardiovascular magnetic resonance (CMR). This proof-of-concept study assessed four high-performing LLMs (Gemini 2.5 Pro, ChatGPT 4.1, DeepSeek V3, and Claude Opus 4) on their ability to generate CMR protocols for 140 hypothetical cardiac cases. AI-generated protocols were compared against a reference standard established by a consensus between two experienced cardiovascular radiologists, following the Society for Cardiovascular Magnetic Resonance (SCMR) recommendations. Descriptive statistics were used to quantify the concordance of LLM-generated sequences with the SCMR guidelines. Statistical agreement was measured using Cohen and Fleiss \u03ba statistics. Gemini 2.5 Pro achieved the highest concordance, aligning with the SCMR guidelines in 71.5% of all evaluated scenarios. Overall, LLMs showed moderate agreement with the SCMR protocols, with Gemini 2.5 Pro again performing best (Cohen \u03ba\u2009=\u20090.55). Agreement was substantial for mandatory CMR sequences (Fleiss \u03ba \u2208 [0.69, 0.74]) and predominantly fair for optional sequences. The tested LLMs demonstrate a potential to generate efficient and pathology-adapted CMR protocols. Under expert supervision, this capability could streamline the imaging workflow and help extend CMR to primary healthcare centers through protocol automation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>The potential of Gemini 2.5 Pro, ChatGPT 4.1, DeepSeek V3, and Claude Opus 4 to suggest pathology-adapted CMR protocols could improve imaging throughput and help to expand access to advanced cardiac diagnostics in primary healthcare centers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>The tested large language models show potential for generating CMR protocols.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Substantial agreement on mandatory CMR sequences promises more efficient examinations.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Automation of CMR protocols could help to improve access to this advanced technique outside major medical institutions.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-025-00671-1","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T12:33:49Z","timestamp":1769430829000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Reliability of Gemini 2.5 Pro, ChatGPT 4.1, DeepSeek V3, and Claude Opus 4 in generating standardized CMR protocols"],"prefix":"10.1186","volume":"10","author":[{"given":"R\u0103zvan-Andrei","family":"Licu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4757-2420","authenticated-orcid":false,"given":"Giuseppe","family":"Muscogiuri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Casartelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anca","family":"Bac\u00e2rea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marian","family":"Pop","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andra-Maria","family":"Licu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Sferratore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Caruso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marianna","family":"Mirchuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Tarkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Byczkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandro","family":"Sironi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"671_CR1","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","volume":"18","author":"A Hosny","year":"2018","unstructured":"Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500\u2013510. https:\/\/doi.org\/10.1038\/s41568-018-0016-5","journal-title":"Nat Rev Cancer"},{"key":"671_CR2","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jmir.2019.09.005","volume":"50","author":"G Currie","year":"2019","unstructured":"Currie G, Hawk KE, Rohren E, Vial A, Klein R (2019) Machine learning and deep learning in medical imaging: intelligent imaging. J Med Imaging Radiat Sci 50:477\u2013487. https:\/\/doi.org\/10.1016\/j.jmir.2019.09.005","journal-title":"J Med Imaging Radiat Sci"},{"key":"671_CR3","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.ejrad.2018.03.019","volume":"102","author":"C Liew","year":"2018","unstructured":"Liew C (2018) The future of radiology augmented with artificial intelligence: a strategy for success. Eur J Radiol 102:152\u2013156. https:\/\/doi.org\/10.1016\/j.ejrad.2018.03.019","journal-title":"Eur J Radiol"},{"key":"671_CR4","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44\u201356. https:\/\/doi.org\/10.1038\/s41591-018-0300-7","journal-title":"Nat Med"},{"key":"671_CR5","doi-asserted-by":"publisher","first-page":"497","DOI":"10.3390\/diagnostics15040497","volume":"15","author":"P Leutz-Schmidt","year":"2025","unstructured":"Leutz-Schmidt P, Palm V, Mathy RM et al (2025) Performance of large language models ChatGPT and Gemini on workplace management questions in radiology. Diagnostics 15:497. https:\/\/doi.org\/10.3390\/diagnostics15040497","journal-title":"Diagnostics"},{"key":"671_CR6","doi-asserted-by":"publisher","first-page":"373","DOI":"10.2214\/AJR.23.29198","volume":"221","author":"AA Elkassem","year":"2023","unstructured":"Elkassem AA, Smith AD (2023) Potential use cases for ChatGPT in radiology reporting. AJR Am J Roentgenol 221:373\u2013376. https:\/\/doi.org\/10.2214\/AJR.23.29198","journal-title":"AJR Am J Roentgenol"},{"key":"671_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrai.2025.100024","volume":"3","author":"T Saliba","year":"2025","unstructured":"Saliba T, Ferrari J, Pozzessere C, Rotzinger D, Fahrni G (2025) Can advanced large language models support radiology training? A performance assessment of DeepSeek R1. Eur J Radiol Artif Intell 3:100024. https:\/\/doi.org\/10.1016\/j.ejrai.2025.100024","journal-title":"Eur J Radiol Artif Intell"},{"key":"671_CR8","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1007\/s11604-024-01634-z","volume":"42","author":"R Kurokawa","year":"2024","unstructured":"Kurokawa R, Ohizumi Y, Kanzawa J et al (2024) Diagnostic performances of Claude 3 Opus and Claude 3.5 Sonnet from patient history and key images in radiology\u2019s \u201cdiagnosis please\u201d cases. Jpn J Radiol 42:1399\u20131402. https:\/\/doi.org\/10.1007\/s11604-024-01634-z","journal-title":"Jpn J Radiol"},{"key":"671_CR9","doi-asserted-by":"publisher","first-page":"571","DOI":"10.3390\/jcm14020571","volume":"14","author":"M Koyun","year":"2025","unstructured":"Koyun M, Taskent I (2025) Evaluation of advanced artificial intelligence algorithms\u2019 diagnostic efficacy in acute ischemic stroke: a comparative analysis of ChatGPT-4o and Claude 3.5 Sonnet models. J Clin Med 14:571. https:\/\/doi.org\/10.3390\/jcm14020571","journal-title":"J Clin Med"},{"key":"671_CR10","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 et al (2024) Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o. Eur Radiol Exp 8:124. https:\/\/doi.org\/10.1186\/s41747-024-00526-1","journal-title":"Eur Radiol Exp"},{"key":"671_CR11","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s41747-024-00477-7","volume":"8","author":"H Assadi","year":"2024","unstructured":"Assadi H, Alabed S, Li R et al (2024) Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance. Eur Radiol Exp 8:77. https:\/\/doi.org\/10.1186\/s41747-024-00477-7","journal-title":"Eur Radiol Exp"},{"key":"671_CR12","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s41747-024-00423-7","volume":"8","author":"G Pambianchi","year":"2024","unstructured":"Pambianchi G, Marchitelli L, Cundari G (2024) Takotsubo syndrome: left atrial and ventricular myocardial strain impairment in the subacute and convalescent phases assessed by CMR. Eur Radiol Exp 8:34. https:\/\/doi.org\/10.1186\/s41747-024-00423-7","journal-title":"Eur Radiol Exp"},{"key":"671_CR13","doi-asserted-by":"publisher","first-page":"2866","DOI":"10.3390\/jcm11102866","volume":"11","author":"A Argentiero","year":"2022","unstructured":"Argentiero A, Muscogiuri G, Rabbat MG et al (2022) The applications of artificial intelligence in cardiovascular magnetic resonance\u2014a comprehensive review. J Clin Med 11:2866. https:\/\/doi.org\/10.3390\/jcm11102866","journal-title":"J Clin Med"},{"key":"671_CR14","doi-asserted-by":"publisher","first-page":"507","DOI":"10.3390\/life13020507","volume":"13","author":"LRM Lanzafame","year":"2023","unstructured":"Lanzafame LRM, Bucolo GM, Muscogiuri G et al (2023) Artificial intelligence in cardiovascular CT and MR imaging. Life 13:507. https:\/\/doi.org\/10.3390\/life13020507","journal-title":"Life"},{"key":"671_CR15","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1007\/s00330-024-10605-x","volume":"34","author":"T Emrich","year":"2024","unstructured":"Emrich T, Wintersperger BJ, Greco FD et al (2024) ESR Essentials: ten steps to cardiac MR-practice recommendations by ESCR. Eur Radiol 34:2140\u20132151. https:\/\/doi.org\/10.1007\/s00330-024-10605-x","journal-title":"Eur Radiol"},{"key":"671_CR16","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s12968-020-00607-1","volume":"22","author":"CM Kramer","year":"2020","unstructured":"Kramer CM, Barkhausen J, Bucciarelli-Ducci C, Flamm SD, Kim RJ, Nagel E (2020) Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J Cardiovasc Magn Reson 22:17. https:\/\/doi.org\/10.1186\/s12968-020-00607-1","journal-title":"J Cardiovasc Magn Reson"},{"key":"671_CR17","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s12968-023-00950-z","volume":"25","author":"F von Knobelsdorff-Brenkenhoff","year":"2023","unstructured":"von Knobelsdorff-Brenkenhoff F, Schulz-Menger J (2023) Cardiovascular magnetic resonance in the guidelines of the European Society of Cardiology: a comprehensive summary and update. J Cardiovasc Magn Reson 25:42. https:\/\/doi.org\/10.1186\/s12968-023-00950-z","journal-title":"J Cardiovasc Magn Reson"},{"key":"671_CR18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240516","volume":"314","author":"D Mastrodicasa","year":"2025","unstructured":"Mastrodicasa D, van Assen M, Huisman M et al (2025) Use of AI in cardiac CT and MRI: a scientific statement from the ESCR, EuSoMII, NASCI, SCCT, SCMR, SIIM, and RSNA. Radiology 314:e240516. https:\/\/doi.org\/10.1148\/radiol.240516","journal-title":"Radiology"},{"key":"671_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2025.112416","volume":"193","author":"Z Bendella","year":"2025","unstructured":"Bendella Z, Wichtmann BD, Clauberg R et al (2025) Chat GPT-4 shows high agreement in MRI protocol selection compared to board-certified neuroradiologists. Eur J Radiol 193:112416. https:\/\/doi.org\/10.1016\/j.ejrad.2025.112416","journal-title":"Eur J Radiol"},{"key":"671_CR20","doi-asserted-by":"publisher","first-page":"e2513921","DOI":"10.1001\/jamanetworkopen.2025.13921","volume":"8","author":"J Huang","year":"2025","unstructured":"Huang J, Wittbrodt MT, Teague CN et al (2025) Efficiency and quality of generative AI-assisted radiograph reporting. JAMA Netw Open 8:e2513921. https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.13921","journal-title":"JAMA Netw Open"},{"key":"671_CR21","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1007\/s00330-024-11032-8","volume":"35","author":"Y Mitsuyama","year":"2025","unstructured":"Mitsuyama Y, Tatekawa H, Takita H et al (2025) Comparative analysis of GPT-4-based ChatGPT\u2019s diagnostic performance with radiologists using real-world radiology reports of brain tumors. Eur Radiol 35:1938\u20131947. https:\/\/doi.org\/10.1007\/s00330-024-11032-8","journal-title":"Eur Radiol"},{"key":"671_CR22","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232133","volume":"311","author":"A Cozzi","year":"2024","unstructured":"Cozzi A, Pinker K, Hidber A et al (2024) BI-RADS category assignments by GPT-3.5, GPT-4, and Google Bard: a multilanguage study. Radiology 311:e232133. https:\/\/doi.org\/10.1148\/radiol.232133","journal-title":"Radiology"},{"key":"671_CR23","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1080\/14796678.2024.2348898","volume":"20","author":"YE Yavuz","year":"2024","unstructured":"Yavuz YE, Kahraman F (2024) Evaluation of the prediagnosis and management of ChatGPT-4.0 in clinical cases in cardiology. Future Cardiol 20:197\u2013207. https:\/\/doi.org\/10.1080\/14796678.2024.2348898","journal-title":"Future Cardiol"},{"key":"671_CR24","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1038\/s41591-024-03456-y","volume":"31","author":"E Goh","year":"2025","unstructured":"Goh E, Gallo RJ, Strong E et al (2025) GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial. Nat Med 31:1233\u20131238. https:\/\/doi.org\/10.1038\/s41591-024-03456-y","journal-title":"Nat Med"},{"key":"671_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52415-1","volume":"15","author":"CYK Williams","year":"2024","unstructured":"Williams CYK, Miao BY, Kornblith AE, Butte AJ (2024) Evaluating the use of large language models to provide clinical recommendations in the emergency department. Nat Commun 15:8236. https:\/\/doi.org\/10.1038\/s41467-024-52415-1","journal-title":"Nat Commun"},{"key":"671_CR26","doi-asserted-by":"publisher","first-page":"e2343689","DOI":"10.1001\/jamanetworkopen.2023.43689","volume":"6","author":"M Benary","year":"2023","unstructured":"Benary M, Wang XD, Schmidt M et al (2023) Leveraging large language models for decision support in personalized oncology. JAMA Netw Open 6:e2343689. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.43689","journal-title":"JAMA Netw Open"},{"key":"671_CR27","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.diii.2024.04.003","volume":"105","author":"P Keshavarz","year":"2024","unstructured":"Keshavarz P, Bagherieh S, Nabipoorashrafi SA et al (2024) ChatGPT in radiology: a systematic review of performance, pitfalls, and future perspectives. Diagn Interv Imaging 105:251\u2013265. https:\/\/doi.org\/10.1016\/j.diii.2024.04.003","journal-title":"Diagn Interv Imaging"},{"key":"671_CR28","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159\u2013174","journal-title":"Biometrics"},{"key":"671_CR29","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med 22:276\u2013282. https:\/\/doi.org\/10.11613\/BM.2012.031","journal-title":"Biochem Med"},{"key":"671_CR30","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.3390\/jcm12134189","volume":"12","author":"AF Darawsheh","year":"2023","unstructured":"Darawsheh AF, Kolarovszki B, Hong DH, Farkas N, Taheri S, Frank D (2023) Applicability of fractal analysis for quantitative evaluation of midpalatal suture maturation. J Clin Med 12:4189. https:\/\/doi.org\/10.3390\/jcm12134189","journal-title":"J Clin Med"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00671-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-025-00671-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00671-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T12:33:50Z","timestamp":1769430830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-025-00671-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["671"],"URL":"https:\/\/doi.org\/10.1186\/s41747-025-00671-1","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"GM is a member of the Advisory Editorial Board of\n                      European Radiology Experimental\n                      (European Society of Cardiovascular Radiology) and, as such, did not participate in the selection or review processes for this article. The remaining authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7"}}