Retinal Vascular Network Model - An Automatic Approach

In this paper, we propose a retinal vascular network model, which is an automatic process of generating a graph representation (i.e., a tree) of the retinal blood vessels and includes vessel geometrical features. It maps the retinal blood vessels and can facilitate vascular features such as the vessel width, bifurcation angle, among others to predict or earlier diagnose cardiovascular and related diseases. The proposed tree-model is based on vessel’s centerline, cross-sectional width, and bifurcation, branching and crossover points. The optic disc center is computed using the Hough transformation and vessel centerlines are tracked from out side its radius. Blood vessels are fragmented as vessel-segments based on the bifurcation, branching and crossover points. For each blood vessel we construct a binary tree which is linked in the root of the tree-model. Our automated method achieves an accuracy of 91.23% in extracting the vessel-segments.