Motivation: Chemical exchange saturation transfer (CEST) MRI provides metabolic information in vivo with high spatial specificity. However, acquisition of the canonical Z-spectrum and multiple contrasts is time-consuming and thus hinders rapid clinical translation. Goal(s): Develop a novel method using a deep neural network to accelerate CEST acquisitions across offsets and saturation powers. Approach: A state-of-the-art transformer-based network is used to recover densely sampled Z-spectra from sparsely sampled offsets across multiple saturation powers, allowing for an accelerated multi-B1 CEST acquisition. Results: The neural network performs well in recovering sparsely sampled Z-spectra across multiple B1s, with low RMSE ad high image fidelity. Impact: A state-of-the-art transformer-based network, SAITS, successfully recovers sparsely sampled Z-spectrum offsets and B1s, allowing for multi-contrast CEST MRI and B1 inhomogeneity correction. Given low reconstruction error and high image fidelity, this method facilitates rapid clinical translation of Z-spectrum acquisitions.
Swain et al. (Tue,) studied this question.