Effect of color information on the diagnostic performance of glaucoma in deep learning using few fundus images.

Journal: International ophthalmology
Published Date: Jun 27, 2020

Abstract

PURPOSE: The purpose of this study was to evaluate the accuracy of the convolutional neural network (CNN) model in glaucoma identification with three primary colors (red, green, blue; RGB) and split color channels using fundus photographs with a small sample size.

Authors

  • Masakazu Hirota
    Department of Orthoptics, Faculty of Medical Technology, Teikyo University, Itabashi, Tokyo, Japan. hirota.ortho@med.teikyo-u.ac.jp.
  • Atsushi Mizota
    Department of Ophthalmology, Teikyo University School of Medicine, Tokyo, Japan.
  • Tatsuya Mimura
    Department of Ophthalmology, Teikyo University School of Medicine, Tokyo, Japan.
  • Takao Hayashi
    Department of Orthoptics, Faculty of Medical Technology, Teikyo University, Itabashi, Tokyo, Japan.
  • Junichi Kotoku
    Division of Clinical Radiology, Graduate School of Medical Care and Technology, Teikyo University, Itabashi, Tokyo, Japan.
  • Tomohiro Sawa
    Medical Information Systems Research Center, Teikyo University, Itabashi, Tokyo, Japan.
  • Kenji Inoue
    Inouye Eye Hospital, Tokyo, Japan.

Keywords

External Resources

Popular Topics
Recent Journals