Affordable Access

deepdyve-link
Publisher Website

Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration.

Authors
  • González-Gonzalo, Cristina1, 2, 3, 4
  • Sánchez-Gutiérrez, Verónica5
  • Hernández-Martínez, Paula5
  • Contreras, Inés5, 6
  • Lechanteur, Yara T4
  • Domanian, Artin4
  • van Ginneken, Bram2
  • Sánchez, Clara I1, 2, 3, 4
  • 1 A-eye Research Group, Radboud University Medical Center, Nijmegen, The Netherlands. , (Netherlands)
  • 2 Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands. , (Netherlands)
  • 3 Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands. , (Netherlands)
  • 4 Department of Ophthalmology, Radboud University Medical Center, Nijmegen, The Netherlands. , (Netherlands)
  • 5 Department of Ophthalmology, University Hospital Ramón y Cajal, Ramón y Cajal Health Research Institute (IRYCIS), Madrid, Spain. , (Spain)
  • 6 Clínica Rementería, Madrid, Spain. , (Spain)
Type
Published Article
Journal
Acta ophthalmologica
Publication Date
Jun 01, 2020
Volume
98
Issue
4
Pages
368–377
Identifiers
DOI: 10.1111/aos.14306
PMID: 31773912
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

To validate the performance of a commercially available, CE-certified deep learning (DL) system, RetCAD v.1.3.0 (Thirona, Nijmegen, The Netherlands), for the joint automatic detection of diabetic retinopathy (DR) and age-related macular degeneration (AMD) in colour fundus (CF) images on a dataset with mixed presence of eye diseases. Evaluation of joint detection of referable DR and AMD was performed on a DR-AMD dataset with 600 images acquired during routine clinical practice, containing referable and non-referable cases of both diseases. Each image was graded for DR and AMD by an experienced ophthalmologist to establish the reference standard (RS), and by four independent observers for comparison with human performance. Validation was furtherly assessed on Messidor (1200 images) for individual identification of referable DR, and the Age-Related Eye Disease Study (AREDS) dataset (133 821 images) for referable AMD, against the corresponding RS. Regarding joint validation on the DR-AMD dataset, the system achieved an area under the ROC curve (AUC) of 95.1% for detection of referable DR (SE = 90.1%, SP = 90.6%). For referable AMD, the AUC was 94.9% (SE = 91.8%, SP = 87.5%). Average human performance for DR was SE = 61.5% and SP = 97.8%; for AMD, SE = 76.5% and SP = 96.1%. Regarding detection of referable DR in Messidor, AUC was 97.5% (SE = 92.0%, SP = 92.1%); for referable AMD in AREDS, AUC was 92.7% (SE = 85.8%, SP = 86.0%). The validated system performs comparably to human experts at simultaneous detection of DR and AMD. This shows that DL systems can facilitate access to joint screening of eye diseases and become a quick and reliable support for ophthalmological experts. © 2019 The Authors. Acta Ophthalmologica published by John Wiley & Sons Ltd on behalf of Acta Ophthalmologica Scandinavica Foundation.

Report this publication

Statistics

Seen <100 times