Format

Send to

Choose Destination
Biomed Opt Express. 2019 Jan 25;10(2):892-913. doi: 10.1364/BOE.10.000892. eCollection 2019 Feb 1.

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

Author information

1
Biomedical Image Technologies Laboratory (BIT), ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, Spain.
2
Biomedical Research Center in Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Spain.
3
Parc de Salut Mar, Barcelona, Spain.
4
Universitat Internacional de Catalunya, Barcelona, Spain.
5
Institut Catala de Retina, Barcelona, Spain.
6
Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands.

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.

Conflict of interest statement

The authors declare that there are no conflicts of interest related to this article.

Supplemental Content

Full text links

Icon for PubMed Central
Loading ...
Support Center