Deep learning to differentiate parkinsonian disorders separately using single midsagittal MR imaging: a proof of concept study.

Journal: European radiology
PMID: 31264017

Abstract

OBJECTIVES: To evaluate the diagnostic performance of deep learning with the convolutional neural networks (CNN) to distinguish each representative parkinsonian disorder using MRI.

Authors

  • Shigeru Kiryu
    From the Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan 113-8655.
  • Koichiro Yasaka
    From the Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan 113-8655.
  • Hiroyuki Akai
    From the Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan 113-8655.
  • Yasuhiro Nakata
    Department of Neuroradiology, Tokyo Metropolitan Neurological Hospital, 2-6-1 Musashidai, Fuchu, Tokyo, 183-0042, Japan.
  • Yusuke Sugomori
    MICIN, Inc., Nihon Building 13F, 2-6-2 Otemachi, Chiyoda-ku, Tokyo, 100-0004, Japan.
  • Seigo Hara
    MICIN, Inc., Nihon Building 13F, 2-6-2 Otemachi, Chiyoda-ku, Tokyo, 100-0004, Japan.
  • Maria Seo
    MICIN, Inc., Nihon Building 13F, 2-6-2 Otemachi, Chiyoda-ku, Tokyo, 100-0004, Japan.
  • Osamu Abe
    From the Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan 113-8655.
  • Kuni Ohtomo

Keywords

External Resources

Popular Topics
Recent Journals