Personalized Cine Cardiac MRI Protocol Optimization Using a Retrieval‐Augmented Large Language Model: A Prospective Comparison With Technologist‐Optimized Protocol

ABSTRACT Background 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‐hold capacity. Purpose To test whether an artificial intelligence (AI) framework using a large language model with retrieval‐augmented generation (LLM‐RAG) can provide cine cardiac MRI protocols that are equivalent or noninferior to those of technologist‐optimized protocols. Study Type Prospective, intra‐individual comparative, nonrandomized. Population/Subjects Sixty‐eight patients (mean age 46 ± 18 years; 39 women) referred for clinical cardiac MRI, including patients with normal function as well as those with arrhythmia, implants, or limited breath‐hold capacity. Field Strength/Sequence 1.5 T, cine cardiac MRI. Assessment Each participant underwent cine cardiac MRI twice in one session. First with a technologist‐optimized protocol, then with an AI‐optimized protocol (fixed order). Image quality and artifact suppression were assessed using four‐point Likert scales by two blinded readers. Left ventricular (LV) functional parameters and repeat acquisitions were recorded. Statistical Tests Wilcoxon signed‐rank test, McNemar's test, paired t ‐tests, and Bland–Altman analysis. Significance set at p   Results Compared to technologist‐, AI‐optimized cine protocols demonstrated significantly higher image quality (3.69 ± 0.47 vs. 3.00 ± 0.49, p  p  p  = 0.028). No significant differences were observed in LV functional parameters between both protocols (all p  > 0.05). Bland–Altman analysis showed minimal bias for all LV functional parameters. Data Conclusion In this nonrandomized study, a LLM‐RAG framework generated cine cardiac MRI protocols that were noninferior to technologist‐optimized protocols for image quality and demonstrated high agreement for LV functional measurements with fewer repeat acquisitions. These findings demonstrated the feasibility of AI‐guided patient‐adaptive protocoling. Randomized trials are warranted. Evidence Level 2. Technical Efficacy Stage 2.