Age-Related Macular Degeneration Using Deep Neural Network Technique and PSO: A Methodology Approach

Abstract

Age-Related Macular Degeneration (AMD), is an eye issue, that can cause central vision to blur. It happens when the macula, the part of the eye that controls accurate, straight-ahead vision, sustains degradation with ageing. The macula is a component of the retinal (the light-sensitive tissue at the back of the eye). Additionally, it is the main reason why older people lose their vision. Curing this issue as early as possible is one of the most tedious tasks for medical experts. In this research, AMD is effectively detected using a deep learning model, and the phases are as follows: a) Participants between the ages of 55 and 80 are included in the data collection from the Age-Related Eye Disease Study (AREDS) repository b) Preprocessing employing a median filter to increase the contrast, c) Extracting Biologically Inspired Features (BIF) using focal region extraction, d) feature selection for dimensionality reduction and finally e) detection of AMD using Alexnet network. Experimental evaluation is conducted over various state-of-art models under various measures in which proposed network outperforms (accuracy: 0.96, detection rate: 0.94, sensitivity: 0.97, specificity: 0.97).