A Deep Learning-Based Approach Towards Simultaneous Localization of Optic Disc and Fovea from Retinal Fundus Images

Stud Health Technol Inform. 2023 Jun 29:305:624-627. doi: 10.3233/SHTI230575.

Abstract

In this work, we propose a multi-task learning-based approach towards the localization of optic disc and fovea from human retinal fundus images using a deep learning-based approach. Formulating the task as an image-based regression problem, we propose a Densenet121-based architecture through an extensive set of experiments with a variety of CNN architectures. Our proposed approach achieved an average mean absolute error of only 13pixels (0.04%), mean squared error of 11 pixels (0.005%), and a root mean square error of only 0.02 (13%) on the IDRiD dataset.

Keywords: Fovea; Optic Disc; Qatar Biobank; Retina.

MeSH terms

  • Deep Learning*
  • Fundus Oculi
  • Humans
  • Optic Disk* / diagnostic imaging