An Automatic Method for Assessing Retinal Vessel Width Changes

Abstract

The Arteriolar-to-Venular Ratio (AVR) is commonly used in studies for the diagnosis of diseases such as diabetes, hypertension or cardio-vascular pathologies. This paper presents an automatic approach for the estimation of the Arteriolar-to-Venular Ratio (AVR) in retinal images. The proposed method includes vessel segmentation, vessel caliber estimation, optic disc detection, region of interest determination, artery/vein classification and AVR calculation. The method was assessed using the images of the INSPIRE-AVR database. A mean error of 0.05 was obtained when the methods results were compared with reference AVR values provided with this dataset, thus demonstrating the adequacy of the proposed solution for AVR estimation.