A convolutional neural network to filter artifacts in spectroscopic MRI.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information.

Authors

  • Saumya S Gurbani
    Department of Radiation Oncology, Emory University, Atlanta, Georgia.
  • Eduard Schreibmann
    Department of Radiation Oncology, Winship Cancer Institute of Emory University, 1365-C Clifton Road NE, Atlanta, Georgia 30322.
  • Andrew A Maudsley
    Department of Radiology, University of Miami Miller School of Medicine, Miami, Florida.
  • James Scott Cordova
    Department of Radiation Oncology, Emory University, Atlanta, Georgia.
  • Brian J Soher
    Department of Radiology, Duke University School of Medicine, Durham, North Carolina.
  • Harish Poptani
    Institute of Translational Medicine, University of Liverpool, Liverpool, United Kingdom.
  • Gaurav Verma
    Department of Chemistry, University of South Florida, 4202 East Fowler Avenue, Tampa, Florida 33620, United States.
  • Peter B Barker
    Department of Radiology and Radiological Science, The Johns Hopkins University, Baltimore, Maryland.
  • Hyunsuk Shim
    Department of Radiation Oncology, Emory University, Atlanta, Georgia.
  • Lee A D Cooper
    Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, 30322, USA. lee.cooper@emory.edu.