Automatic Segmentation of Retinal Capillaries in Adaptive Optics Scanning Laser Ophthalmoscope Perfusion Images Using a Convolutional Neural Network.

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

Abstract

PURPOSE: Adaptive optics scanning laser ophthalmoscope (AOSLO) capillary perfusion images can possess large variations in contrast, intensity, and background signal, thereby limiting the use of global or adaptive thresholding techniques for automatic segmentation. We sought to develop an automated approach to segment perfused capillaries in AOSLO images.

Authors

  • Gwen Musial
    Department of Biomedical Engineering, University of Houston, Houston, TX, USA.
  • Hope M Queener
    College of Optometry, University of Houston, Houston, TX, USA.
  • Suman Adhikari
    College of Optometry, University of Houston, Houston, TX, USA.
  • Hanieh Mirhajianmoghadam
    College of Optometry, University of Houston, Houston, TX, USA.
  • Alexander W Schill
    Department of Biomedical Engineering, University of Houston, Houston, TX, USA.
  • Nimesh B Patel
    College of Optometry, University of Houston, Houston, TX, USA.
  • Jason Porter
    Department of Biomedical Engineering, University of Houston, Houston, TX, USA.

Keywords

External Resources

Popular Topics
Recent Journals