A review on supervised learning methodologies for detection of exudates in diabetic retinopathy

Diabetic retinopathy has become one of the major reasons for blindness in world. Early and precise diagnosis disease may save one’s eyesight from irreversible damage. Manual detection lesions is time consuming not be as accurate desirable. Many automated systems have been developed recently to help ophthalmologists their endeavors. Exudates are early signs manifestation diabetic retinopathy. In this paper, methodologies detecting exudates retinal fundus images were reviewed. These methods categorized into deep learning, machine learning primarily focusing on image processing techniques. The comprehensive view performances was given. Several datasets described briefly. Most researchers preferred combination multiple publically available databases. Also, potential areas research discussed. It found that sensitivity which identifies abnormal correctly, most widely used performance measure. study will helpful wanting explore more field.