AUTOMATIC RETINAL VESSEL TORTUOSITY MEASUREMENT

Abstract

Retinal vascular vessels have the role to indicate the retinal diseases and for systematic diseases when there are any abnormalities in retinal vascular pattern. A characteristic of the vascular pattern that is appreciated by clinicians is vascular tortuosity, i.e., how curved or kinked a blood vessel, either vein or artery, appears along its course. In this study we suggest a novel mask filter to track the blood vessel along its course and measuring the blood vessels tortuosity over the entire human retinal vessel network in fundus eye image, by using the arc to chord ratio. The suggested algorithm tested with straight and curve hand drawing lines and gives high accurate results.