Automated Recognition of Retinal Pigment Epithelium Cells on Limited Training Samples Using Neural Networks.

Journal: Translational vision science & technology
Published Date: Jun 1, 2020

Abstract

PURPOSE: To develop a neural network (NN)-based approach, with limited training resources, that identifies and counts the number of retinal pigment epithelium (RPE) cells in confocal microscopy images obtained from cell culture or mice RPE/choroid flat-mounts.

Authors

  • Qitong Gao
    Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA.
  • Ying Xu
    School of Biological and Food Engineering Changzhou University Changzhou Jiangsu China.
  • Joshua Amason
    Department of Ophthalmology, Duke University, Durham, NC, USA.
  • Anna Loksztejn
    Department of Ophthalmology, Duke University, Durham, NC, USA.
  • Scott Cousins
    Department of Ophthalmology, Duke University, Durham, NC, USA.
  • Miroslav Pajic
    Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA.
  • Majda Hadziahmetovic
    Department of Ophthalmology, Duke University, Durham, NC, USA.

Keywords

External Resources

Popular Topics
Recent Journals