Model-to-Data Approach for Deep Learning in Optical Coherence Tomography Intraretinal Fluid Segmentation.

Journal: JAMA ophthalmology
Published Date:

Abstract

IMPORTANCE: Amid an explosion of interest in deep learning in medicine, including within ophthalmology, concerns regarding data privacy, security, and sharing are of increasing importance. A model-to-data approach, in which the model itself is transferred rather than data, can circumvent many of these challenges but has not been previously demonstrated in ophthalmology.

Authors

  • Nihaal Mehta
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Cecilia S Lee
    Department of Ophthalmology, University of Washington, Seattle, Washington, USA.
  • Luísa S M Mendonça
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Khadija Raza
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Phillip X Braun
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Jay S Duker
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Nadia K Waheed
    New England Eye Center, Tufts Medical Center, Boston, Massachusetts.
  • Aaron Y Lee
    Department of Ophthalmology, University of Washington, Seattle, Washington.