Predictive Analysis of Diabetic Retinopathy

摘要

Diabetic Retinopathy is human eye disease which causes damage to retina of eye and it may eventually lead to complete blindness. Detection of diabetic retinopathy in early stage is essential to avoid complete blindness. Many physical tests like visual acuity test, pupil dilation and optical coherence tomography can be used to detect diabetic retinopathy but are time consuming and affects patients as well. This project focuses on detecting the presence of diabetic retinopathy by performing different classifiers such as Artificial Neural Network (ANN), back propagation levenberg-marquardt, Support Vector Machine (SVM), Radial Basis Function Networks (RBFN) using features drawn from output of different retinal image processing features, like diameter of optic disk, lesion specific micro aneurysms, exudates etc. These data set consists of details about patients for Analysing if the patients have Diabetic retinopathy or not. The data set was obtained from University of California Irvine Machine Learning Repository and some real time data sets. The purpose of this project is to identify the efficient classifier in predicting the diabetic retinopathy. Depending upon the test result we evaluate the essential parameters like accuracy, specificity and Performance.