English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Current MRI super-resolution (SR) methods only use existing contrastsacquired from typical clinical sequences as input for the neural network (NN).In turbo spin echo sequences (TSE) the sequence parameters can have a stronginfluence on the actual resolution of the acquired image and have consequentlya considera-ble impact on the performance of the NN. We propose aknown-operator learning approach to perform an end-to-end optimization of MRsequence and neural net-work parameters for SR-TSE. This MR-physics-informedtraining procedure jointly optimizes the radiofrequency pulse train of a protondensity- (PD-) and T2-weighted TSE and a subsequently applied convolutionalneural network to predict the corresponding PDw and T2w super-resolution TSEimages. The found radiofrequency pulse train designs generate an optimal signalfor the NN to perform the SR task. Our method generalizes from thesimulation-based optimi-zation to in vivo measurements and the acquiredphysics-informed SR images show higher correlation with a time-consumingsegmented high-resolution TSE sequence compared to a pure network trainingapproach.

Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution