Cardiac MR Fingerprinting at 0.55T Using a Deep Image Prior for Joint T 1 , T 2 , and M 0 Mapping

ABSTRACT Background 0.55T systems offer unique advantages and may support expanded access to cardiac MRI. Purpose To assess the feasibility of 0.55T cardiac MR Fingerprinting (MRF), leveraging a deep image prior reconstruction to mitigate noise. Study Type Phantom and prospective in vivo assessment. Population ISMRM/NIST MRI system phantom and 18 healthy subjects (11 female; ages 28 ± 8 years). Field Strength and Sequences MRF, modified Look‐Locker inversion recovery (MOLLI), and T 2 ‐prepared balanced steady state free precession (T 2 ‐bSSFP) at 0.55T. Assessment MRF T 1 and T 2 maps were reconstructed using (1) a low‐rank technique with sparse and locally low‐rank regularization (SLLR‐MRF) and (2) a deep image prior (DIP‐MRF). Accuracy and precision of MRF and conventional sequences were evaluated in a phantom. In vivo performance of MRF was evaluated in the 18 healthy subjects, with 7 subjects also undergoing conventional mapping. Myocardial T 1 and T 2 values were compared among methods and image quality scored by three readers (2, 3, and 4 years of experience) on a 5‐point scale. Statistical Tests Linear regression, Bland–Altman, intraclass correlation coefficient, and one‐way ANOVA with p 0.99). Standard deviations within the myocardium were significantly lower with DIP‐MRF compared to SLLR‐MRF (39 vs. 147 ms for T 1 and 4.5 vs. 12.7 ms for T 2 ). Overall image quality ratings were significantly lower for SLLR‐MRF (T 1 : 2.3, T 2 : 2.9), which were significantly lower compared to conventional mapping methods (T 1 : 3.4, T 2 : 3.9), and DIP‐MRF (T 1 : 3.8, T 2 : 4.1) received higher scores. Data Conclusion This study demonstrated the feasibility of cardiac MRF on a commercial 0.55T system, enabled by a deep image prior reconstruction for denoising. Evidence Level 2. Stage of Technical Efficacy 1.