Journal de recherche et développement
Libre accès

Abstrait

Diagnosis of Diabetic Retinopathy using Machine Learning

Swati Gupta and Karandikar AM

Diabetic retinopathy is the most common diabetic eye disease and a leading cause of blindness. Regular screening for early disease detection has been a highly labor and resource intensive task. Hence automatic detection of these diseases through computational techniques would be a great remedy. There are many features present in retina like exudates and micro aneurysm feature. The presence of micro aneurysms (MAs) is usually an early sign of diabetic retinopathy and their automatic detection from color retinal images somewhat tough job, so for that we are using green Chanel images. The objective of project is to detect retinal micro-aneurysms and exudates for automatic screening of DR using classifier. To develop an automated DR screening system detection of dark lesions and bright lesions in digital funds photographs is needed. To detect retinal micro- aneurysms and exudates retinal funds images are taken from Messidor dataset. After pre-processing, morphological operations are performed to find the feature and then features are get extracted such as GLCM and Splat for classification. In this we are achieve the sensitivity and specificity of 87% and 100% respectively with accuracy of 86%.