Automatic screening of Diabetic Retinopathy

Abstract

Diabetic Retinopathy (DR) is a disorder of the retinal vasculature. It develops to some degree in nearly all patients with long-standing diabetes mellitus and can result in blindness. Screening of DR is essential for both early detection and early treatment. The presented diabetic retinopathy research involves three development stages. This thesis aims to investigate automatic methods for diabetic retinopathy detection and subsequently develop an effective system for the detection and screening of diabetic retinopathy. Firstly, the thesis presents the development of a preliminary classification and screening system for diabetic retinopathy using eye fundus images. The research will then focus on the detection of the earliest signs of diabetic retinopathy in the change of retinal blood vessels and how the detection enhancement and extract of retinal vessel using 2D Gaussian matched filter. The research proposes the image processing techniques combination for the general diabetic retinopathy detection .In addition, the research proposed GLCM as extracted feature tool to extract 22 feature , in additional we use t-test as feature selection method for accurately automated blood vessels Furthermore, the research presents a medium tree as classifier with 97.7% accuracy for retinopathy diagnosis . We development of a friendly GUI for doctors by using mat lab software GUI for doctors by mat lab software. An accurate retinal screening, therefore, is required to assist the retinal screeners to classify the retinal images effectively. Highly efficient and accurate image processing techniques must thus be used in order to produce an effective screening of diabetic retinopathy.