In Magnetic resonance in medicine ; h5-index 66.0
PURPOSE : Rapid 2DRF pulse design with subject-specific inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented.
METHODS : The convolution neural network was trained on half a million single-channel transmit 2DRF pulses optimized with an optimal control method using artificial 2D targets, and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured and B0 maps from a high-resolution gradient echo sequence.
RESULTS : Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand-drawn regions of interest and the measured and B0 maps. Compensation of inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agree well with the simulations using the acquired and B0 maps, and the 2DRF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control.
CONCLUSION : The proposed convolutional neural network-based 2DRF pulse design method predicts 2DRF pulses with an excellent excitation pattern and compensated and B0 variations at 7 T. The rapid 2DRF pulse prediction (9 ms) enables subject-specific high-quality 2DRF pulses without the need to run lengthy optimizations.
Vinding Mads Sloth, Aigner Christoph Stefan, Schmitter Sebastian, Lund Torben Ellegaard
2DRF pulses, 7 T, artificial intelligence, deep learning, optimal control