eduzhai > Applied Sciences > Engineering >

Fast and Accurate Modeling of Transient-State Gradient-Spoiled Sequences by Recurrent Neural Networks

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 36 pages

Abstract: Fast and accurate modeling of MR signal responses are typically required forvarious quantitative MRI applications, such as MR Fingerprinting and MR-STAT.This work uses a new EPG-Bloch model for accurate simulation of transient-stategradient-spoiled MR sequences, and proposes a Recurrent Neural Network (RNN) asa fast surrogate of the EPG-Bloch model for computing large-scale MR signalsand derivatives. The computational efficiency of the RNN model is demonstratedby comparing with other existing models, showing one to three orders ofacceleration comparing to the latest GPU-accelerated open-source EPG package.By using numerical and in-vivo brain data, two use cases, namely MRF dictionarygeneration and optimal experimental design, are also provided. Results showthat the RNN surrogate model can be efficiently used for computing large-scaledictionaries of transient-states signals and derivatives within tens ofseconds, resulting in several orders of magnitude acceleration with respect tostate-of-the-art implementations. The practical application of transient-statesquantitative techniques can therefore be substantially facilitated.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×