Diagnosis of corneal pathologies using deep learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Corneal pathologies are leading causes of blindness and represent a world health problem according to the world health organization. Early detection of corneal diseases is necessary to prevent blindness. In this paper, we use transfer learning with pretrained deep learning networks to diagnose three common corneal diseases, namely, dry eye, Fuchs' endothelial dystrophy, and keratoconus as well as healthy eyes using only optical coherence tomography (OCT) images. Corneal OCT scans were obtained from 413 eyes of 269 patients and used to train, validate, and test the networks. All networks achieved all-category accuracy values > 99%, categorical area under curve values > 0:99, categorical specificity values > 99%, and categorical sensitivity values > 99% on the training, validation, and testing, respectively. The work in this paper has clinical significance and can potentially be applied in clinical practice to potentially solve a significant world health problem.

Original languageEnglish (US)
Title of host publicationOphthalmic Technologies XXX
EditorsFabrice Manns, Arthur Ho, Per G. Soderberg
PublisherSPIE
ISBN (Electronic)9781510631991
DOIs
StatePublished - 2020
Event30th Conference on Ophthalmic Technologies - San Francisco, United States
Duration: Feb 1 2020Feb 2 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11218
ISSN (Print)1605-7422

Conference

Conference30th Conference on Ophthalmic Technologies
CountryUnited States
CitySan Francisco
Period2/1/202/2/20

Keywords

  • Corneal Pathologies
  • Deep Learning
  • Optical Coherence Tomography (OCT)

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Diagnosis of corneal pathologies using deep learning'. Together they form a unique fingerprint.

Cite this