Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI.

Journal: European radiology
Published Date: Mar 24, 2022

Abstract

OBJECTIVES: To compare interobserver agreement and image quality of 3D T2-weighted fast spin echo (T2w-FSE) L-spine MRI images processed with a deep learning reconstruction (DLRecon) against standard-of-care (SOC) reconstruction, as well as against 2D T2w-FSE images. The hypothesis was that DLRecon 3D T2w-FSE would afford improved image quality and similar interobserver agreement compared to both SOC 3D and 2D T2w-FSE.

Authors

  • Simon Sun
  • Ek Tsoon Tan
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • Douglas N Mintz
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • Meghan Sahr
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • Yoshimi Endo
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • Joseph Nguyen
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • R Marc Lebel
    GE Healthcare, Calgary, Canada.
  • John A Carrino
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 East 70th Street, New York, NY, 10021, USA.
  • Darryl B Sneag
    Department of Radiology and Imaging, Hospital for Special Surgery, 535 E 70(th) Street, New York, NY 10021, United States of America. Electronic address: sneagd@hss.edu.

Keywords

External Resources

Popular Topics
Recent Journals