Human Versus Machine: Comparing a Deep Learning Algorithm to Human Gradings for Detecting Glaucoma on Fundus Photographs.

Journal: American journal of ophthalmology
Published Date: Mar 1, 2020

Abstract

PURPOSE: To compare the diagnostic performance of human gradings vs predictions provided by a machine-to-machine (M2M) deep learning (DL) algorithm trained to quantify retinal nerve fiber layer (RNFL) damage on fundus photographs.

Authors

  • Alessandro A Jammal
    Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina.
  • Atalie C Thompson
    Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina.
  • Eduardo B Mariottoni
    Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA.
  • Samuel I Berchuck
    Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA; Department of Statistical Science and Forge, Duke University, Durham, North Carolina, USA.
  • Carla N Urata
    Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA.
  • Tais Estrela
    Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA.
  • Susan M Wakil
    Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA.
  • Vital P Costa
    Department of Ophthalmology, State University of Campinas, Campinas, Brazil.
  • Felipe A Medeiros
    Duke Eye Center, Department of Ophthalmology, Duke University, Durham, North Carolina, United States.

Keywords

External Resources

Popular Topics
Recent Journals