Chapter 7 - FunNet: a deep learning network for the detection of age-related macular degeneration

Abstract

Age-related macular degeneration (AMD) is an eye disease affecting older adults. In the aged people, the prevalence of AMD is rising. Thus early identification is important to avoid vision loss in aged population. Developing a complete eye screening system for AMD diagnosis is difficult. This paper suggests FunNet: a deep Convolutional Neural Network structure for the detection of AMD from the fundus images. The proposed architecture’s performance is evaluated through ten-fold cross-validation methods using different classifiers like SVM, J48, and random forest. In terms of classification accuracy, the FunNet with J48 classifier provides the best results. The proposed method is tested on ARIA, STARE, and PRIVATE data sets and achieved an accuracy of 99.38%, 99.00%, 99.92%, respectively, with J48 classifier. Results demonstrating the efficacy of the suggested algorithm in AMD detection were contrasted with alternative approaches. The FunNet with J48 classifier can be used for the eye screening method in AMD detection task.