MRzero - Automated discovery of MRI sequences using supervised learning.

Journal: Magnetic resonance in medicine
Published Date: Mar 23, 2021

Abstract

PURPOSE: A supervised learning framework is proposed to automatically generate MR sequences and corresponding reconstruction based on the target contrast of interest. Combined with a flexible, task-driven cost function this allows for an efficient exploration of novel MR sequence strategies.

Authors

  • A Loktyushin
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.
  • K Herz
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.
  • N Dang
    Friedrich-Alexander Universität Erlangen-Nürnberg (FAU), Neuroradiology, University Clinic Erlangen, Erlangen, Germany.
  • F Glang
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.
  • A Deshmane
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.
  • S Weinmüller
    Friedrich-Alexander Universität Erlangen-Nürnberg (FAU), Neuroradiology, University Clinic Erlangen, Erlangen, Germany.
  • A Doerfler
    Friedrich-Alexander Universität Erlangen-Nürnberg (FAU), Neuroradiology, University Clinic Erlangen, Erlangen, Germany.
  • B Schölkopf
    Empirical Inference, Max-Planck Institute for Intelligent Systems, Tübingen, Germany.
  • K Scheffler
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.
  • M Zaiss
    Magnetic Resonance Center, Max-Planck Institute for Biological Cybernetics, Tübingen, Germany.

Keywords

External Resources

Popular Topics
Recent Journals