Motivation: Saturation transfer MR fingerprinting (ST-MRF) is a novel quantitative molecular MRI method that enables estimation of free water, solute, and semisolid macromolecule parameters. However, the quantification accuracy is highly dependent on acquisition schedule. Goal(s): To find an optimal acquisition schedule that improves scan efficiency and quantification accuracy Approach: We develop a learning-based optimization framework for ST-MRF incorporated with two neural networks for ultrafast signal synthesis and tissue quantification. Additionally, correction for B0 and B1 inhomogeneities were implemented. Results: Our results showed that the optimal ST-MRF schedule significantly outperformed other MRF acquisition schedules in terms of quantification accuracy, even with the severe field inhomogeneity. Impact: The proposed optimal ST-MRF approach could provide accurate and reliable multi-tissue parameter maps from a single scan within clinical acceptable time, even in the presence of the severe B0 and B1 field inhomogeneities.
Kang et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: