Evaluation of a Deep Learning System For Identifying Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

Journal: Journal of glaucoma
Published Date: Dec 1, 2019

Abstract

PRECIS: Pegasus outperformed 5 of the 6 ophthalmologists in terms of diagnostic performance, and there was no statistically significant difference between the deep learning system and the "best case" consensus between the ophthalmologists. The agreement between Pegasus and gold standard was 0.715, whereas the highest ophthalmologist agreement with the gold standard was 0.613. Furthermore, the high sensitivity of Pegasus makes it a valuable tool for screening patients with glaucomatous optic neuropathy.

Authors

  • Lama A Al-Aswad
    Columbia University Medical Center, Harkness Eye Institute, New York, New York, USA. Electronic address: laa2003@cumc.columbia.edu.
  • Rahul Kapoor
    Columbia University Medical Center, Harkness Eye Institute, New York, New York, USA.
  • Chia Kai Chu
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.
  • Stephen Walters
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.
  • Dan Gong
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.
  • Aakriti Garg
    Wilmer Eye Institute.
  • Kalashree Gopal
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.
  • Vipul Patel
    Global Robotics Institute, Florida Hospital Celebration Health, Celebration, FL, USA.
  • Trikha Sameer
    Visulytix Ltd.
  • Thomas W Rogers
    Department of Computer Science, University College London, London, UK.
  • Jaccard Nicolas
    Visulytix Ltd.
  • Gustavo C De Moraes
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.
  • Golnaz Moazami
    Columbia University Medical Center, Harkness Eye Institute, New York, NY.

Keywords

External Resources

Popular Topics
Recent Journals