Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data.

Journal: Magnetic resonance in medicine
Published Date: Jul 2, 2020

Abstract

PURPOSE: To develop a strategy for training a physics-guided MRI reconstruction neural network without a database of fully sampled data sets.

Authors

  • Burhaneddin Yaman
  • Seyed Amir Hossein Hosseini
    Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America.
  • Steen Moeller
    Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota.
  • Jutta Ellermann
    Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota, USA.
  • Kâmil Uğurbil
    Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, Minnesota.
  • Mehmet Akçakaya
    Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, Minnesota.

Keywords

External Resources

Popular Topics
Recent Journals