Segmentation of exudates to assess diabetic retinopathy by reni's entropy based thresholding

Abstract

Objective: Diabetic retinopathy is a critical pathological disease condition which affects the lives of millions of people everyday. Exudates found in the eye are one of the important signs of Diabetic retinopathy. This work aims to segment exudates for faster detection and treatment of Diabetic retinopathy.Methods: This paper proposes a robust and efficient method to segment exu-dates. Initial pre-processing work applies adaptive unsharp masking which sharps the areas based on the level of smoothness in the image preventing accentuation of noise. Optic disc is removed by active contour model. The exudates are then segmented by Renyi's Entropy based thresholding which choses the optimal threshold for segmentation, exploiting Renyi's entropy da-ta.Results: The performance of the proposed system was evaluated and found better than state of art results giving accuracy, sensitivity and specificity 94.5%, 95.1% and 96.2% respectively.Con-clusion: Effective computer aided system is essential for accurate exudates detection. The proposed algorithm utilises the advantages of adaptive unsharp masking in medical image pro-cessing along with Renyi's entropy based thresholding to detect Exudates, which performs better than traditional thresholding techniques.