Rapid estimation of 2D relative -maps from localizers in the human heart at 7T using deep learning

Subject-tailored parallel transmission pulses for ultra-high fields body applications are typically calculated based on subject-specific $$ -maps of all transmit channels, which require lengthy adjustment times. This study investigates the feasibility of using deep learning to estimate complex, channel-wise, relative 2D $$ -maps from a single gradient echo localizer to overcome long calibration times.

126 channel-wise, complex, relative 2D $$ -maps of the human heart from 44 subjects were acquired at 7T using a Cartesian, cardiac gradient-echo sequence obtained under breath-hold to create a library for network training and cross-validation. The deep learning predicted maps were qualitatively compared to the ground truth. Phase-only $$ -shimming was subsequently performed on the estimated $$ -maps for a region of interest covering the heart. The proposed network was applied at 7T to 3 unseen test subjects.

The deep learning-based $$ -maps, derived in approximately 0.2 seconds, match the ground truth for the magnitude and phase. The static, phase-only pulse design performs best when maximizing the mean transmission efficiency. In-vivo application of the proposed network to unseen subjects demonstrates the feasibility of this approach: the network yields predicted $$ -maps comparable to the acquired ground truth and anatomical scans reflect the resulting $$ -pattern using the deep learning-based maps.

The feasibility of estimating 2D relative $$ -maps from initial localizer scans of the human heart at 7T using deep learning is successfully demonstrated. Because the technique requires only sub-seconds to derive channel-wise $$ -maps, it offers high potential for advancing clinical body imaging at ultra-high fields.