Answers are grounded in this paper and cite their sources.
Deep learning evaluation demonstrates robust cardiac T1 and T2 estimation across standard mapping sequences, suggesting simplified cardiovascular magnetic resonance workflows.
The most used curve-fitting method for map reconstruction of the cardiovascular magnetic resonance mapping is sensitive to the initial conditions, time-consuming, and prone to fitting error. In this study, we sought to develop a deep-learning approach (DeepFittingNet) to perform T1 and T2 calculations for the most clinically used cardiac parametric mappings, to simplify the clinical workflow of cardiac T1/T2 measurements and improve the robustness. In testing, DeepFittingNet could perform T1/T2 estimation tasks for MOLLI, SASHA, and T2-prep bSSFP. Compared to the curve-fitting algorithm, DeepFittingNet could improve the robustness for inversion-recovery T1 estimation and have comparable accuracy and precision.
No takes yet. Share an insight, caveat, or question.
Guo et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: