Use of a Convolutional Neural Network to Predict the Response of Diabetic Macular Edema to Intravitreal Anti-VEGF Treatment: A Pilot Study.

Journal: American journal of ophthalmology
PMID:

Abstract

PURPOSE: To utilize a convolutional neural network (CNN) to predict the response of treatment-naïve diabetic macular edema (DME) to a single injection of anti-vascular endothelial growth factor (anti-VEGF) with data from optical coherence tomography (OCT).

Authors

  • George Magrath
    From the Department of Ophthalmology (G.M., J.L., E.S., J.B., A.L.), Storm Eye Institute, Medical University of South Carolina, Charleston, South Carolina; Opus Genetics (G.M., A.J., S.T.), Durham, North Carolina. Electronic address: magrath@musc.edu.
  • Joseph Luvisi
    From the Department of Ophthalmology (G.M., J.L., E.S., J.B., A.L.), Storm Eye Institute, Medical University of South Carolina, Charleston, South Carolina.
  • Daniel Russakoff
    Voxeleron LLC, Pleasanton, California, United States of America.
  • Jonathan Oakley
    Voxeleron LLC, Pleasanton, California, United States of America.
  • Emil Anthony Say
    From the Department of Ophthalmology (G.M., J.L., E.S., J.B., A.L.), Storm Eye Institute, Medical University of South Carolina, Charleston, South Carolina.
  • Jeffrey Blice
    From the Department of Ophthalmology (G.M., J.L., E.S., J.B., A.L.), Storm Eye Institute, Medical University of South Carolina, Charleston, South Carolina.
  • Ashwath Jayagopal
    Opus Genetics (G.M., A.J., S.T.), Durham, North Carolina.
  • Sally Tucker
    Emblem Consultancy Limited (S.T.), Harpenden, United Kingdom.
  • Alex Loayza
    From the Department of Ophthalmology (G.M., J.L., E.S., J.B., A.L.), Storm Eye Institute, Medical University of South Carolina, Charleston, South Carolina.
  • George Hamilton Baker
    Department of Pediatric Cardiology, Medical University of South Carolina, Charleston, SC 29425, United States.
  • Jihad S Obeid
    Biomedical Informatics Center, Medical University of South Carolina, Charleston, SC 29425, United States.