Deep Learning-Generated Synthetic MR Imaging STIR Spine Images Are Superior in Image Quality and Diagnostically Equivalent to Conventional STIR: A Multicenter, Multireader Trial.

Journal: AJNR. American journal of neuroradiology
Published Date: Jul 6, 2023

Abstract

BACKGROUND AND PURPOSE: Deep learning image reconstruction allows faster MR imaging acquisitions while matching or exceeding the standard of care and can create synthetic images from existing data sets. This multicenter, multireader spine study evaluated the performance of synthetically created STIR compared with acquired STIR.

Authors

  • L N Tanenbaum
    RadNet-San Fernando Interventional Radiology, 1510 Cotner Ave., 90025, Los Angeles, CA, USA. nuromri@gmail.com.
  • S C Bash
    From RadNet (L.N.T., S.C.B.), New York, New York.
  • G Zaharchuk
    From the Departments of Radiology (G.Z., M.W., D.R., C.P.L.) gregz@stanford.edu.
  • A Shankaranarayanan
    Subtle Medical, 883 Santa Cruz Ave, 94025, Menlo Park, CA, USA.
  • R Chamberlain
    Subtle Medical (A.S., R.C., L.W.), Menlo Park, California.
  • M Wintermark
    From the Departments of Radiology (G.Z., M.W., D.R., C.P.L.).
  • C Beaulieu
    Stanford University Medical Center (G.Z., C.B.), Stanford, California.
  • M Novick
    All-American Teleradiology (M.N.), Bay Village, Ohio.
  • L Wang
    Institute of Organ Transplantation, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Key Laboratory of Ministry of Health, Key Laboratory of Ministry of Education, Wuhan, China.

Keywords

External Resources

Popular Topics
Recent Journals