Back to Journals » Clinical Ophthalmology » Volume 14

Artificial Intelligence to Identify Retinal Fundus Images, Quality Validation, Laterality Evaluation, Macular Degeneration, and Suspected Glaucoma

Authors Zapata MA, Royo-Fibla D, Font O, Vela JI, Marcantonio I, Moya-Sánchez EU, Sánchez-Pérez A, Garcia-Gasulla D, Cortés U, Ayguadé E, Labarta J

Received 23 October 2019

Accepted for publication 22 January 2020

Published 13 February 2020 Volume 2020:14 Pages 419—429


Checked for plagiarism Yes

Review by Single anonymous peer review

Peer reviewer comments 4

Editor who approved publication: Dr Scott Fraser

Miguel Angel Zapata,1 Dídac Royo-Fibla,1 Octavi Font,1 José Ignacio Vela,2,3 Ivanna Marcantonio,2,3 Eduardo Ulises Moya-Sánchez,4,5 Abraham Sánchez-Pérez,5 Darío Garcia-Gasulla,4 Ulises Cortés,4,6 Eduard Ayguadé,4,6 Jesus Labarta4,6

1Optretina, Barcelona, Spain; 2Ophthalmology Department, Hospital de la Santa Creu I de Sant Pau, Barcelona 08041, Spain; 3Universitat Autònoma de Barcelona (UAB), Campus de la UAB, Barcelona, Spain; 4Barcelona Supercomputing Center (BSC), Barcelona, Spain; 5Universidad Autónoma de Guadalajara - Postgrado en Ciencias Computacionales, Guadalajara, Mexico; 6Universitat Politècnica de Catalunya - BarcelonaTECH, Campus Nord, Barcelona, Spain

Correspondence: Miguel Angel Zapata
Optretina, C/ Las Palmas 11, 08195 Sant Cugat del Vallès, Barcelona, Spain
Tel +34 655809682

Purpose: To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON).
Patients and Methods: Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina’s tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity.
Results: Determination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%).
Conclusion: Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.

Keywords: artificial intelligence, retinal diseases, screening, retinal fundus image

Creative Commons License This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.

Download Article [PDF]  View Full Text [HTML][Machine readable]