{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T02:50:56Z","timestamp":1791168656767,"version":"4.1.0"},"reference-count":34,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T00:00:00Z","timestamp":1791072000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T00:00:00Z","timestamp":1791072000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n Cine cardiac magnetic resonance imaging (MRI) protocols are typically based on static templates, which may not optimally address individual patient limitations such as arrhythmia or limited breath\u2010hold capacity.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n To test whether an artificial intelligence (AI) framework using a large language model with retrieval\u2010augmented generation (LLM\u2010RAG) can provide cine cardiac MRI protocols that are equivalent or noninferior to those of technologist\u2010optimized protocols.<\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Prospective, intra\u2010individual comparative, nonrandomized.<\/jats:p>\n <\/jats:sec>\n \n Population\/Subjects<\/jats:title>\n Sixty\u2010eight patients (mean age 46\u2009\u00b1\u200918\u2009years; 39 women) referred for clinical cardiac MRI, including patients with normal function as well as those with arrhythmia, implants, or limited breath\u2010hold capacity.<\/jats:p>\n <\/jats:sec>\n \n Field Strength\/Sequence<\/jats:title>\n 1.5\u2009T, cine cardiac MRI.<\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n Each participant underwent cine cardiac MRI twice in one session. First with a technologist\u2010optimized protocol, then with an AI\u2010optimized protocol (fixed order). Image quality and artifact suppression were assessed using four\u2010point Likert scales by two blinded readers. Left ventricular (LV) functional parameters and repeat acquisitions were recorded.<\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n \n Wilcoxon signed\u2010rank test, McNemar's test, paired\n t<\/jats:italic>\n \u2010tests, and Bland\u2013Altman analysis. Significance set at\n p<\/jats:italic>\n \u2009<\u20090.05.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Compared to technologist\u2010, AI\u2010optimized cine protocols demonstrated significantly higher image quality (3.69\u2009\u00b1\u20090.47 vs. 3.00\u2009\u00b1\u20090.49,\n p<\/jats:italic>\n \u2009<\u20090.001) and artifact suppression (3.19\u2009\u00b1\u20090.35 vs. 2.17\u2009\u00b1\u20090.45,\n p<\/jats:italic>\n \u2009<\u20090.001). The AI\u2010optimized protocol reduced repeat acquisitions by 68% (6 vs. 19 repeats,\n p<\/jats:italic>\n \u2009=\u20090.028). No significant differences were observed in LV functional parameters between both protocols (all\n p<\/jats:italic>\n \u2009>\u20090.05). Bland\u2013Altman analysis showed minimal bias for all LV functional parameters.\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n In this nonrandomized study, a LLM\u2010RAG framework generated cine cardiac MRI protocols that were noninferior to technologist\u2010optimized protocols for image quality and demonstrated high agreement for LV functional measurements with fewer repeat acquisitions. These findings demonstrated the feasibility of AI\u2010guided patient\u2010adaptive protocoling. Randomized trials are warranted.<\/jats:p>\n <\/jats:sec>\n \n Evidence Level<\/jats:title>\n 2.<\/jats:p>\n <\/jats:sec>\n \n Technical Efficacy<\/jats:title>\n Stage 2.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.70566","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T01:51:36Z","timestamp":1791165096000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Personalized Cine Cardiac\n MRI<\/scp>\n Protocol Optimization Using a Retrieval\u2010Augmented Large Language Model: A Prospective Comparison With Technologist\u2010Optimized Protocol"],"prefix":"10.1002","author":[{"given":"Sadegh","family":"Dehghani","sequence":"first","affiliation":[{"name":"Radiation Sciences Department, School of Allied Medical Sciences Tehran University of Medical Sciences Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4332-7667","authenticated-orcid":false,"given":"Ali","family":"Farashahi","sequence":"additional","affiliation":[{"name":"Tehran Heart Center Tehran University of Medical Sciences Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9417-4392","authenticated-orcid":false,"given":"Ibtihal Raheem","family":"Hammood","sequence":"additional","affiliation":[{"name":"Ibn Al\u2010Baladi for Children and Women Hospital Baghdad Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,4]]},"reference":[{"issue":"4","key":"e_1_2_8_2_1","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.3390\/jcm14041112","article-title":"Feasibility and Role of Cardiac Magnetic Resonance in Intensive and Acute Cardiovascular Care","volume":"14","author":"Leo I.","year":"2025","journal-title":"Journal of Clinical Medicine"},{"issue":"1","key":"e_1_2_8_3_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocmr.2024.100995","article-title":"SCMR Expert Consensus Statement for Cardiovascular Magnetic Resonance of Patients With a Cardiac Implantable Electronic Device","volume":"26","author":"Kim D.","year":"2024","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"5","key":"e_1_2_8_4_1","first-page":"1753","article-title":"Cardiac MR Fingerprinting: Overview, Technical Developments, and Applications","volume":"60","author":"Rashid I.","year":"2024","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"1","key":"e_1_2_8_5_1","doi-asserted-by":"crossref","DOI":"10.1093\/ehjimp\/qyaf046","article-title":"Current Trends and Challenges in the Clinical Use of Cardiovascular Magnetic Resonance: A Survey From the Italian Society of Cardiology","volume":"3","author":"Monti L.","year":"2025","journal-title":"European Heart Journal \u2010 Imaging Methods and Practice"},{"issue":"2","key":"e_1_2_8_6_1","doi-asserted-by":"crossref","DOI":"10.2214\/AJR.25.33759","article-title":"Artificial Intelligence for CT and MRI Protocoling: A Meta\u2010Analysis of Traditional Machine Learning, BERT, and Large Language Models","volume":"226","author":"Sacoransky E.","year":"2026","journal-title":"AJR, American Journal of Roentgenology"},{"issue":"2","key":"e_1_2_8_7_1","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1007\/s00330-025-11888-4","article-title":"GPT\u20104 for Automated Sequence\u2010Level Determination of MRI Protocols Based on Radiology Request Forms From Clinical Routine","volume":"36","author":"Terzis R.","year":"2026","journal-title":"European Radiology"},{"issue":"4","key":"e_1_2_8_8_1","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1002\/jmri.70034","article-title":"Potential Time and Recall Benefits for Adaptive AI\u2010Based Breast Cancer MRI Screening","volume":"62","author":"Balkenende L.","year":"2025","journal-title":"Journal of Magnetic Resonance Imaging"},{"key":"e_1_2_8_9_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejrad.2024.111470","article-title":"Using Deep Learning to Optimize the Prostate MRI Protocol by Assessing the Diagnostic Efficacy of MRI Sequences","volume":"175","author":"Fransen S. J.","year":"2024","journal-title":"European Journal of Radiology"},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","DOI":"10.3389\/fnimg.2023.1090054","article-title":"AI\u2010Driven and Automated MRI Sequence Optimization in Scanner\u2010Independent MRI Sequences Formulated by a Domain\u2010Specific Language","volume":"2","author":"Hoinkiss D. C.","year":"2023","journal-title":"Frontiers in Neuroimaging"},{"issue":"2","key":"e_1_2_8_11_1","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1002\/jmri.22626","article-title":"Fully Automatic Geometry Planning for Cardiac MR Imaging and Reproducibility of Functional Cardiac Parameters","volume":"34","author":"Frick M.","year":"2011","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"1","key":"e_1_2_8_12_1","doi-asserted-by":"crossref","DOI":"10.1186\/1532-429X-15-S1-O54","article-title":"Fully Automatic Planning of the Long\u2010Axis Views of the Heart","volume":"15","author":"Hayes C.","year":"2013","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"key":"e_1_2_8_13_1","unstructured":"J.Goldfarb J.Cheng andJ.Cao \u201cAutomatic Optimal Frequency Adjustment for High Field Cardiac MR Imaging via Deep Learning\u201d(2018) CMR 2018\u2014A Joint EuroCMR\/SCMR Meeting Abstract Supplement."},{"issue":"1","key":"e_1_2_8_14_1","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s12968-019-0575-y","article-title":"Machine Learning in Cardiovascular Magnetic Resonance: Basic Concepts and Applications","volume":"21","author":"Leiner T.","year":"2019","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"5","key":"e_1_2_8_15_1","doi-asserted-by":"crossref","first-page":"328","DOI":"10.36347\/sjet.2025.v13i05.003","article-title":"Retrieval\u2010Augmented Generation and Hallucination in Large Language Models: A Scholarly Overview","volume":"13","author":"Gupta S.","year":"2025","journal-title":"Scholars Journal of Engineering and Technology"},{"issue":"12","key":"e_1_2_8_16_1","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.3390\/bioengineering12121303","article-title":"Agentic AI and Large Language Models in Radiology: Opportunities and Hallucination Challenges","volume":"12","author":"Salehi S.","year":"2025","journal-title":"Bioengineering"},{"key":"e_1_2_8_17_1","first-page":"9459","article-title":"Retrieval\u2010Augmented Generation for Knowledge\u2010Intensive Nlp Tasks","volume":"33","author":"Lewis P.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"e_1_2_8_18_1","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300068","article-title":"Almanac \u2010 Retrieval\u2010Augmented Language Models for Clinical Medicine","volume":"1","author":"Zakka C.","year":"2024","journal-title":"NEJM Ai"},{"issue":"1","key":"e_1_2_8_19_1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1002\/jmri.70310","article-title":"Optimizing Cine Cardiac MRI: Technical Advances and Clinical Applications","volume":"64","author":"Dehghani S.","year":"2026","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"1","key":"e_1_2_8_20_1","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s12968-023-00961-w","article-title":"Highly Accelerated Free\u2010Breathing Real\u2010Time Myocardial Tagging for Exercise Cardiovascular Magnetic Resonance","volume":"25","author":"Morales M. A.","year":"2023","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"1","key":"e_1_2_8_21_1","article-title":"Enhanced Myocardial Tissue Visualization: A Comparative Cardiovascular Magnetic Resonance Study of Gradient\u2010Spin Echo\u2010STIR and Conventional STIR Imaging","volume":"2024","author":"Dehghani S.","year":"2024","journal-title":"International Journal of Biomedical Imaging"},{"issue":"2","key":"e_1_2_8_22_1","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1002\/jmri.20969","article-title":"Measurement of Signal\u2010To\u2010Noise Ratios in MR Images: Influence of Multichannel Coils, Parallel Imaging, and Reconstruction Filters","volume":"26","author":"Dietrich O.","year":"2007","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"4","key":"e_1_2_8_23_1","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1002\/mrm.21728","article-title":"Comprehensive Quantification of Signal\u2010To\u2010Noise Ratio and g\u2010Factor for Image\u2010Based and k\u2010Space\u2010Based Parallel Imaging Reconstructions","volume":"60","author":"Robson P. M.","year":"2008","journal-title":"Magnetic Resonance in Medicine"},{"issue":"1","key":"e_1_2_8_24_1","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/s12968-020-00683-3","article-title":"Reference Ranges (\u201cNormal Values\u201d) for Cardiovascular Magnetic Resonance (CMR) in Adults and Children: 2020 Update","volume":"22","author":"Kawel\u2010Boehm N.","year":"2020","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"1","key":"e_1_2_8_25_1","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An Overview of Clinical Decision Support Systems: Benefits, Risks, and Strategies for Success","volume":"3","author":"Sutton R. T.","year":"2020","journal-title":"Npj Digital Medicine"},{"issue":"21","key":"e_1_2_8_26_1","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2018.17163","article-title":"Clinical Decision Support in the Era of Artificial Intelligence","volume":"320","author":"Shortliffe E. H.","year":"2018","journal-title":"Journal of the American Medical Association"},{"issue":"1","key":"e_1_2_8_27_1","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12968-020-00607-1","article-title":"Standardized Cardiovascular Magnetic Resonance Imaging (CMR) Protocols: 2020 Update","volume":"22","author":"Kramer C. M.","year":"2020","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"9","key":"e_1_2_8_28_1","first-page":"1755","article-title":"Are We There Yet? The Road to Routine Rapid CMR Imaging","volume":"14","author":"Plein S.","year":"2021","journal-title":"JACC: Cardiovascular Imaging"},{"issue":"1","key":"e_1_2_8_29_1","doi-asserted-by":"crossref","DOI":"10.1186\/1532-429X-10-35","article-title":"Standardized Cardiovascular Magnetic Resonance Imaging (CMR) Protocols, Society for Cardiovascular Magnetic Resonance: Board of Trustees Task Force on Standardized Protocols","volume":"10","author":"Kramer C. M.","year":"2008","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","DOI":"10.3389\/fcvm.2021.742640","article-title":"Deep Learning for Classification and Selection of Cine CMR Images to Achieve Fully Automated Quality\u2010Controlled CMR Analysis From Scanner to Report","volume":"8","author":"Vergani V.","year":"2021","journal-title":"Frontiers in Cardiovascular Medicine"},{"issue":"15","key":"e_1_2_8_31_1","doi-asserted-by":"crossref","first-page":"3274","DOI":"10.3390\/jcm10153274","article-title":"Compressed Sensing Real\u2010Time Cine Reduces CMR Arrhythmia\u2010Related Artifacts","volume":"10","author":"Long\u00e8re B.","year":"2021","journal-title":"Journal of Clinical Medicine"},{"issue":"1","key":"e_1_2_8_32_1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s12968-016-0271-0","article-title":"Compressed Sensing Real\u2010Time Cine Cardiovascular Magnetic Resonance: Accurate Assessment of Left Ventricular Function in a Single\u2010Breath\u2010Hold","volume":"18","author":"Kido T.","year":"2016","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"10","key":"e_1_2_8_33_1","doi-asserted-by":"crossref","first-page":"924","DOI":"10.3348\/kjr.2025.0440","article-title":"Deep Learning\u2010Based Breath\u2010Hold and Free\u2010Breathing Cine MRI for Comprehensive Cardiac Evaluation","volume":"26","author":"Wu Y.","year":"2025","journal-title":"Korean Journal of Radiology"},{"issue":"5","key":"e_1_2_8_34_1","doi-asserted-by":"crossref","first-page":"e2330272","DOI":"10.2214\/AJR.23.30272","article-title":"Prospective Comparison of Free\u2010Breathing Accelerated Cine Deep Learning Reconstruction Versus Standard Breath\u2010Hold Cardiac MRI Sequences in Patients With Ischemic Heart Disease","volume":"222","author":"Monteuuis D.","year":"2024","journal-title":"AJR. American Journal of Roentgenology"},{"issue":"1","key":"e_1_2_8_35_1","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/S0002-9149(02)02381-0","article-title":"Comparison of Interstudy Reproducibility of Cardiovascular Magnetic Resonance With Two\u2010Dimensional Echocardiography in Normal Subjects and in Patients With Heart Failure or Left Ventricular Hypertrophy","volume":"90","author":"Grothues F.","year":"2002","journal-title":"American Journal of Cardiology"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70566","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.70566","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T01:51:41Z","timestamp":1791165101000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,4]]},"references-count":34,"alternative-id":["10.1002\/jmri.70566"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70566","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,4]]},"assertion":[{"value":"2026-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"jmri.70566"}}