Detection of Mircoaneurysms in Diabetic Retinopathy Using Image Processing and Python

Abstract

Diabetic retinopathy (DR) is one of the most common reasons for blindness in the working-age population of the world. Diabetic Retinopathy is an eye disease, which occurs with long-standing untreated diabetes. Progression to vision impairment can be slowed down or stopped if DR is detected on time; In detection or screening of DR, automatic methods can play an important role. A microaneurysm is a tiny aneurysm, or swelling, in the side of a blood vessel. People with diabetes, microaneurysms are sometimes found in the retina of the eye. These miniature aneurysms can rupture and leak blood, hence the purpose of our project is to detect the microaneurysms which are the initial stage of Diabetic retinopathy so that we could prevent blindness. An algorithm is designed to detect microaneurysms and tested it on a publicly available DiaretDB1 database, which contains the ground truth for all images. For the detection of Micro aneurysms, the given steps are followed, image acquisition, green channel, and CLAHE, sequential filtering, blood vessel detection, BV extraction from the image, thresholding, and after the microaneurysms will be detected.