An analytical method for the detection of exudates in retinal images using invertible orientation scores

Diabetic retinopathy is an eye related complication of diabetes mellitus caused due to damage to the retinal blood vessels, resulting in micro-aneurysms, hemorrhages and exudates. DR is asymptomatic, necessitating the development of an automated screening system. Exudates appear in the later stages of diabetic retinopathy and their presence would classify the disease as moderate or severe. In developing countries, where access to training data is limited, there is a greater need for analytical methods than machine learning techniques. The proposed method uses the orientation scores of the retinal image to detect exudates. The 2D orientation score framework, proposed by Duits et al., inspired by the visual system of mammals, is a mapping which assigns the position and orientation angle of each pixel to a complex scalar and has been so far used to detect vasculature tree on the retina. This paper proposes the use of orientation scores to form an orientation enhanced image, from which a binary mask of exudates can be obtained by intensity thresholding. It achieves a sensitivity of 86.2% and a specificity of 85% on images of DIARETDB1 database.