Paper Title
Earlier Detection of Diabetic Retinopathy Using Crest Region Analysis

Diabetic Retinopathy is one of a complication of diabetes which can cause blindness. There are two levels of diabetic retinopathy which are non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). The presence of microaneurysms in the eye is one of the early signs of diabetic retinopathy. Automated detection of microaneurysms in digital color fundus photographs is developed to help opthalmologist to detect the emergence of its early symptoms and determine the next action step for the patient. Detection of microaneurysms in retinal fundus images involves the regional scanning on the crest region pixels centred on the pre-processed image. Inverted green channel is used to distinguish the blood vessels and the other anatomic structures. The crest region extraction in inverted green channel image involves the 8-pixel neighbourhood comparison. Cross-sectional scanning along the discrete line centred at local regional maximum pixels, from obtained cross-sectional profile intensity the maximum is fixed and the other properties are measured. The statistical parameters like mean standard deviation, co-efficient of variation of feature set are calculated. The microaneurysm candidates are estimated by comparison of distribution from the values of mean and standard deviation with the training set obtained from various datasets. The final result obtained is MA co-ordinates. Keywords- Biomedical image processing, image classification, medical decision-making