An Ensemble Classifier Based on Individual Features for Detecting Microaneurysms in Diabetic Retinopathy

Individuals with diabetes are more likely to develop Diabetic Retinopathy (DR), a chronic ailment that can lead blindness if left undiagnosed. Early-stage (DR) is characterized by Microaneurysms (MA), which appear as tiny red lesions on the retina. This paper investigates unique approach for automated early identification of microaneurysms in eye images. A ensemble classifier technique suggested this work. Classifiers like SVM, KNN, Decision Tree, and Naïve Bayes chosen study building an model. After preprocessing image , certain common characteristics such shape intensity features were retrieved from candidate. The mean absolute difference each feature computed. Based ranges would give improved classification results, expert trained. outputs classifiers integrated distinct characteristics, number categories have been most frequently repeated utilized reach final decision. process has comprehensively validated using two available open datasets, e-ophtha DIARETDB1. On DIARETDB1 model achieved AUC 0.928 0.873, Sensitivity 90.7% 85%, Specificity 90% 91% respectively.