Detect microaneurysm by image processing for early diagnosis of diabetic retinopathy

Diabetes is a chronic disease that results in the body unable to secrete enough insulin hormone from the body of the pancreas. One of the side effects of this disease is diabetic eye diseases that develop over time. Diabetic eye disease refers to a group of eye disorders that can cause severe vision loss and even blindness. Diabetic retinopathy is the most common diabetic eye disease. It is also the most important cause of blindness in adults aged 16-85 years. With diabetes, the likelihood of the occurrence of diabetic retinopathy and severe retinal problems that may lead to visual loss is increasing. Correct analysis of vascular structures and retinal images in diabetic retinopathy plays an important role in the early diagnosis of the disease. In this study, an android based algorithm was developed using OpenCV library with dataset consisting from fundus camera images collected from diabetic retinopathy patients. With this algorithm, it is aimed to detect lesions and leaks in microaneurysm images by Hough Transformation and to help early diagnosis of the disease.