A Universal Retinal Image Template for Automated Screening of Diabetic Retinopathy

Diabetic retinopathy (DR) frequently appears in diabetic patients. It is initially asymptomatic, but can progress to blindness. Screening studies for its diagnosis are performed in many countries by means of photographing the eye retina with special fundus-cameras. These studies are aimed at revealing the presence of microaneurysms (MAs) on the retina, which are the primary signs of DR. The wide variety of cameras, peculiarities of retina illumination, FOV angles, and sizes of digital images has complicated the development of a reliable and universal approach to analyzing retina images by machine-learning methods. In this paper, we consider the problem of choosing the size and shape of a unified template for representing the data of an arbitrary retinal image for subsequent automated DR screening. It is experimentally proved that it is possible to extract a square inscribed in the FOV region from each retinal image and compress it to the size of 512 × 512 pixels. This is the minimum allowable size of the template. It preserves the required number of MAs for DR screening by machine-learning methods.