Deep learning-based relative B₁⁺-mapping in the human body at 7T

Synopsis

In this work, we estimate relative 2D B₁⁺-maps from initial localizer scans using deep learning at 7T. We investigate 7 UNets and MultiResUNets architectures to estimate complex, channel-wise, relative 2D B₁⁺-maps of 8 transmit channels from a single gradient echo localizer obtained with 32 receive channels. The networks are evaluated in 5 unseen volunteers not included in the training library by comparing the prediction with the acquired relative B₁⁺-maps using different evaluation metrics for homogeneous B₁⁺ phase shimming. Our approach saves additional B₁⁺-mapping scans, and, hence, overcomes long calibration times in the human body at 7T.