An Improved Method for Automated Identification of Hard Exudates in Diabetic Retinopathy Disease

Abstract

The presence of Hard Exudates in retinal images is one of the significant indications of Diabetic Retinopathy disease. Early detection of Hard Exudates obviously prevents the vision loss very effectively. Today, the development of appropriate Pre-processing stages for Hard Exudate identification through automated screening is an open issue. In this research article, a mathematical morphology based image processing technique is presented for the identification of Hard Exudates in retinal images. The analysis of noisy and low-contrast retinal images shows the importance of this method. In this research work, 570 input images collected from Hospital are examined by the k-fold cross-validation technique. The sensitivity and specificity, two important parameters for performance analysis of Hard Exudate screening, are 97.36% and 99.31%, respectively. In Receiver Operating Characteristics the Area Under Curve (AUC) is 0.93 (average for k folds). Public datasets e_Ophtha_EX and DIARETDB1 are used here to compare the screening performance with existing algorithms and AUC is 0.97 and 0.98, respectively. Thus, the screening result on both Hospital dataset and Public dataset reflects the effectiveness of the proposed method.