Generalisability and performance of an OCT-based deep learning classifier for community-based and hospital-based detection of gonioscopic angle closure.

Journal: The British journal of ophthalmology
PMID:

Abstract

PURPOSE: To assess the generalisability and performance of a deep learning classifier for automated detection of gonioscopic angle closure in anterior segment optical coherence tomography (AS-OCT) images.

Authors

  • Jasmeen Randhawa
    Keck School of Medicine at the University of Southern California, Los Angeles, California, USA.
  • Michael Chiang
    Sol Price School of Public Policy, University of Southern California, Los Angeles, California, USA.
  • Natalia Porporato
    Singapore Eye Research Institute/Singapore National Eye Centre, Singapore.
  • Anmol A Pardeshi
    Roski Eye Institute, Department of Ophthalmology, Keck School of Medicine at the University of Southern California, Los Angeles, California, USA.
  • Justin Dredge
    Roski Eye Institute, Department of Ophthalmology, Keck School of Medicine at the University of Southern, California.
  • Galo Apolo Aroca
    Roski Eye Institute, Keck School of Medicine of the University of Southern California, Los Angeles, California, USA.
  • Tin A Tun
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
  • Joanne HuiMin Quah
    Outram Polyclinic, SingHealth Polyclinics, Singapore.
  • Marcus Tan
    Ophthalmology, National University of Singapore, Singapore.
  • Risa Higashita
    Tomey Corporation, Nagoya, Japan; Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China.
  • Tin Aung
    Singapore Eye Research Institute, Singapore National Eye Center, Singapore.
  • Rohit Varma
    University of Southern California Gayle and Edward Roski Eye Institute, Los Angeles, California.
  • Benjamin Y Xu
    Roski Eye Institute, Department of Ophthalmology, Keck School of Medicine at the University of Southern California, Los Angeles, California, USA. Electronic address: benjamin.xu@med.usc.edu.