A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis

Abstract 

We present an automatic image processing algorithm to detect hard exudates. Automatic detection of hard exudates from retinal images is an important problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Fisher's linear discriminant analysis and makes use of colour information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 58 retinal images with variable colour, brightness, and quality. Our proposed algorithm obtained a sensitivity of 88% with a mean number of 4.83±4.64 false positives per image using the lesion-based performance evaluation criterion, and achieved an image-based classification accuracy of 100% (sensitivity of 100% and specificity of 100%).

Keywords: Diabetic retinopathy, Hard exudates, Image processing, Retinal images