Feature Extraction for Retinal Vascular Network Classification

Montoro, Ana ;   Morales, Sandra ;   Naranjo, Valery ;   López, Fernando ;   Alcañiz, Mariano

The analysis of retinal blood vessels provides useful information for medical diagnosis of several diseases such as cardiovascular risk or diabetic and hypertensive retinopathy. These diseases affect retinal vessels so that an abnormal calibre of veins or arteries could indicate the presence of some of them. So, before analysing vessel calibres, it is interesting to distinguish between vein and artery. This paper is focused on studying the appearance of the retinal vascular network in different color spaces (RGB and HSV) to extract the most discriminant vessel features and classify the retinal vascular network as venous or arterial. The method for vessel classification has been evaluated on a public image database which facilitates further comparison with other state-of-the-art algorithms. The classification results are promising: 0.861 and 0.862 of sensitivity for vein and artery discrimination, respectively, which improve previous results of the literature. Once the vascular network has been classified, it would be possible to obtain different measures as the arteriovenous ratio (AVR), an essential parameter in the diagnosis of many diseases.