Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN). In turbo spin echo sequences (TSE) the sequence parameters can have a strong influence on the actual resolution of the acquired image and have consequently a considera-ble impact on the performance of the NN. We propose a known-operator learning approach to perform an end-to-end optimization of MR sequence and neural net-work parameters for SR-TSE. This MR-physics-informed training procedure jointly optimizes the radiofrequency pulse train of a proton density- (PD-) and T2-weighted TSE and a subsequently applied convolutional neural network to predict the corresponding PDw and T2w super-resolution TSE images. The found radiofrequency pulse train designs generate an optimal signal for the NN to perform the SR task. Our method generalizes from the simulation-based optimi-zation to in vivo measurements and the acquired physics-informed SR images show higher correlation with a time-consuming segmented high-resolution TSE sequence compared to a pure network training approach.
@article{arxiv.2305.07524,
title = {Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution},
author = {Hoai Nam Dang and Vladimir Golkov and Thomas Wimmer and Daniel Cremers and Andreas Maier and Moritz Zaiss},
journal= {arXiv preprint arXiv:2305.07524},
year = {2023}
}
Comments
13 pages, 4 figures, 3 tables, submitted to MICCAI 2023 for review