Simultaneous NODDI and GFA parameter map generation from subsampled q-space imaging using deep learning.

Journal: Magnetic resonance in medicine
PMID: 30426558

Abstract

PURPOSE: To develop a robust multidimensional deep-learning based method to simultaneously generate accurate neurite orientation dispersion and density imaging (NODDI) and generalized fractional anisotropy (GFA) parameter maps from undersampled q-space datasets for use in stroke imaging.

Authors

  • Eric K Gibbons
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah.
  • Kyler K Hodgson
    Department of Bioengineering, University of Utah, Salt Lake City, Utah.
  • Akshay S Chaudhari
    Department of Radiology, Stanford University, Stanford, California.
  • Lorie G Richards
    Department of Occupational and Recreational Therapies, University of Utah, Salt Lake City, Utah.
  • Jennifer J Majersik
    Department of Neurology, University of Utah, Salt Lake City, Utah.
  • Ganesh Adluru
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah.
  • Edward V R DiBella
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah.

Keywords

External Resources

Popular Topics
Recent Journals