Retinal Microaneurysm Detection on Optic Disc through Cross-Section Profile Analysis

M Dorothy; E Yuvarani

M Dorothy Assistant Professor, Department of Information Technology, SNS College of Engineering, Coimbatore
E Yuvarani Assistant Professor, Department of Master of Computer Applications, SNS Collegeof Engineering, Coimbatore

Keywords: Image Processing, Diabetic Retinopathy, microaneurysms, Bio-Imaging, naïve Bayes Classification

Abstract

Diabetic Retinopathy (DR) is a most popular diabetic eye disease that develops in most of the patients caused by changes in retina with long-standing illness. Diagnosis of DR is performed by the evaluation of retinal images. The presence of microaneurysms (MAs) on the retina is the primary factor and main characteristic symptom of this disease. MA-like structures do appear on the optic disc. Optic disc (OD) detection is an important step while developing automated screening systems for Diabetic Retinopathy.A method to automatically detect the position of the OD in digital retinal fundus images starts by normalizing luminosity and contrast throughout the image using illumination equalization and adaptive histogram equalization methods respectively. The MA detection is applied through the finding of directional cross-section samples and peak detection is applied on each sample and a set of attributes regarding the size, height and shape of the peak are calculated consequently. The naïve Bayes (NB) classification is used in the feature set to exclude the spurious candidates. Finally, the MA score is calculated for the remaining candidates and the points with non-maximal score in a candidate region are not considered.