Split-slice training and hyperparameter tuning of RAKI networks for simultaneous multi-slice reconstruction.

Journal: Magnetic resonance in medicine
Published Date: Dec 16, 2020

Abstract

PURPOSE: Simultaneous multi-slice acquisitions are essential for modern neuroimaging research, enabling high temporal resolution functional and high-resolution q-space sampling diffusion acquisitions. Recently, deep learning reconstruction techniques have been introduced for unaliasing these accelerated acquisitions, and robust artificial-neural-networks for k-space interpolation (RAKI) have shown promising capabilities. This study systematically examines the impacts of hyperparameter selections for RAKI networks, and introduces a novel technique for training data generation which is analogous to the split-slice formalism used in slice-GRAPPA.

Authors

  • Andrew S Nencka
    Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
  • Volkan E Arpinar
    Center for Imaging Research, Medical College of Wisconsin, Milwaukee, WI, USA.
  • Sampada Bhave
    Canon Medical Research USA, Cleveland, OH, USA.
  • Baolian Yang
    GE Healthcare, Waukesha, WI, USA.
  • Suchandrima Banerjee
    GE Healthcare, Waukesha, WI, USA.
  • Michael McCrea
    Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA.
  • Nikolai J Mickevicius
    Department of Radiation Oncology, Medical College of Wisconsin, Milwaukee, WI, USA.
  • L Tugan Muftuler
    Center for Imaging Research, Medical College of Wisconsin, Milwaukee, WI, USA.
  • Kevin M Koch
    Department of Radiology, Medical College of Wisconsin, Milwaukee, WI, USA.

Keywords

External Resources

Popular Topics
Recent Journals