Model-informed unsupervised deep learning approaches to frequency and phase correction of MRS signals.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: A supervised deep learning (DL) approach for frequency and phase correction (FPC) of MRS data recently showed encouraging results, but obtaining transients with labels for supervised learning is challenging. This work investigates the feasibility and efficiency of unsupervised deep learning-based FPC.

Authors

  • Amirmohammad Shamaei
    Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic.
  • Jana Starcukova
    Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic.
  • Iveta Pavlova
    Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic.
  • Zenon Starcuk
    Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic.