Automated detection of Cotton Wool Spots for the diagnosis of Hypertensive Retinopathy

摘要

The development of automated systems for the detection and diagnosis of different diseases are quite popular now-a-days. Hypertensive Retinopathy (HR) is an eye disease caused by high blood pressure. Formation of Cotton Wool Spots (CWS) is one of the important clinical signs that are seen at advanced stages in HR. An automated system is presented in this paper for the detection of Cotton Wool Spots in digital retinal images. The system first enhances candidate regions using Gabor filter bank, then binarize those regions using Global thresholding. The proposed system is tested on a locally gather fundus image dataset, and achieved 82.21% and 82.38% sensitivity and PPV, respectively.