Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning

Gómez Valverde, Juan José ORCID: https://orcid.org/0000-0002-5073-5908, Antón López, Alfonso, Fatti, Gianluca, Liefers, Bart, Herranz Cabarcos, Alejandra, Santos Lleo, Andres de ORCID: https://orcid.org/0000-0001-7423-9135, Sánchez, Clara, I and Ledesma Carbayo, María Jesús ORCID: https://orcid.org/0000-0001-6846-3923 (2019). Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. "Biomedical Optics Express", v. 10 (n. 2); pp. 892-913. ISSN 2156-7085. https://doi.org/10.1364/BOE.10.000892.

Description

Title: Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning
Author/s:
Item Type: Article
Título de Revista/Publicación: Biomedical Optics Express
Date: 25 January 2019
ISSN: 2156-7085
Volume: 10
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[thumbnail of INVE_MEM_2019_325141.pdf]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (713kB) | Preview

Abstract

Glaucoma detection in color fundus images is a challenging task that requires expertise and years of practice. In this study we exploited the application of different Convolutional Neural Networks (CNN) schemes to show the influence in the performance of relevant factors like the data set size, the architecture and the use of transfer learning vs newly defined architectures. We also compared the performance of the CNN based system with respect to human evaluators and explored the influence of the integration of images and data collected from the clinical history of the patients. We accomplished the best performance using a transfer learning scheme with VGG19 achieving an AUC of 0.94 with sensitivity and specificity ratios similar to the expert evaluators of the study. The experimental results using three different data sets with 2313 images indicate that this solution can be a valuable option for the design of a computer aid system for the detection of glaucoma in large-scale screening programs.

Funding Projects

Type
Code
Acronym
Leader
Title
Government of Spain
TEC2015-66978-R
Unspecified
Unspecified
Tecnología óptica para elastografía del tejido

More information

Item ID: 64271
DC Identifier: https://oa.upm.es/64271/
OAI Identifier: oai:oa.upm.es:64271
DOI: 10.1364/BOE.10.000892
Official URL: https://www.osapublishing.org/boe/abstract.cfm?uri...
Deposited by: Memoria Investigacion
Deposited on: 07 Oct 2020 14:37
Last Modified: 07 Oct 2020 14:37
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM