Using 3D Convolutional Neural Network and Corvis ST Corneal Dynamic Video for Detecting Forme Fruste Keratoconus.

Journal: Journal of refractive surgery (Thorofare, N.J. : 1995)
PMID:

Abstract

PURPOSE: To evaluate the performance of a three-dimensional convolutional neural network (3D CNN) in detecting forme fruste keratoconus (FFKC).

Authors

  • Hua Rong
    Department of Nursing, General Hospital of Taiyuan Iron & Steel Co.,Ltd., Taiyuan 030008, China.
  • Guihua Liu
    Reproductive Centre The Sixth Affiliated Hospital Sun Yat-sen University, Guangzhou 510655, P. R. China.
  • Yanling Wang
    Department of Neurology, The Fourth Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Jiamei Hu
  • Ziwen Sun
  • Nan Gao
    Department of Biological Sciences, Rutgers University, Newark, NJ, USA.
  • Chea-Su Kee
  • Bei Du
  • Ruihua Wei