A Critical Review of Expert Systems for Detection and Diagnosis of Diabetic Retinopathy

Abstract

Diabetic Retinopathy is considered as a root cause of vision loss for diabetic patients. Due to this health threat, lots of research work has been carried out on retinal images using computer science to assists medical professionals. Ten papers which use different techniques for diagnosis and detection of DR are reviewed here. Various methods such as high gray level variation, area threshold, Hough transform, back tracking technique, morphological filtering techniques, watershed transformation, principal component analysis and point distribution model have been reported for the detection and extraction of Optic Disk(OD). Various methods such as shade correction, contrast enhancement, sharpening, combination of local and global thresholding, color normalization, fuzzy C-means clustering and neural networks has been reported for the detection and classification of exudates.