Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution
This addresses MRI image quality limitations for medical imaging applications by integrating physics-based sequence optimization with deep learning, representing a hybrid rather than purely incremental advance.
The researchers tackled MRI super-resolution by jointly optimizing MR sequence parameters and neural network parameters, rather than using fixed sequences as input to neural networks. Their physics-informed approach produced super-resolution images with higher correlation to time-consuming high-resolution reference scans compared to pure neural network methods.
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.