Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias.

Journal: Magnetic resonance in medicine
Published Date: Dec 19, 2022

Abstract

PURPOSE: The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution.

Authors

  • Rudy Rizzo
    MR Methodology, Department for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland.
  • Martyna Dziadosz
    MR Methodology, Department for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland.
  • Sreenath P Kyathanahally
    Departments of Radiology and Clinical Research, University of Bern, Bern, Switzerland.
  • Amirmohammad Shamaei
    Institute of Scientific Instruments of the Czech Academy of Sciences, Brno, Czech Republic.
  • Roland Kreis
    Departments of Radiology and Clinical Research, University of Bern, Bern, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals