A New Method for Automatic Detection and Diagnosis of Retinopathy Diseases in Colour Fundus Images Based on Morphology

摘要

Automatic detection of lesions in retinal images can assist in early diagnosis and screening of retinopathy diseases. In this paper, the detection of five types of lesions and optic disc has been studied. These lesions include: Hard exudates, Soft exudates, Drusen, Microaneurysm and Hemorrhage, each of which is a sign of one or more types of disease. Our algorithm also effectively diagnoses Glaucoma and other diseases which cause changes to the optic disc. In our method, first the retina images are pre-processed. Then, our algorithm detects OD, fovea and lesions in the image and determines the type of each lesion based on Morphology. Later, the system finds the Characteristics of the Optic Disc for diagnosis of Glaucoma. It is shown that the performance of the proposed method is high. We have achieved a sensitivity of 92.5% and a specificity of 81.4%.