The retinal vasculature is the only part of the body's circulatory system that can be observed non-invasively. A large variety of diseases affect the vasculature, in ways that may cause geometrical and functional changes. Retinal images are therefore not only suitable for investigation of ocular diseases such as glaucoma and age-related macular degeneration (AMD), but also for systemic diseases such as diabetes, hypertension and arteriosclerosis. This paper presents a novel method for retinal vasculature extraction, using a vessel tracking method based on multi-orientation analysis. We apply multi-orientation analysis via so-called invertible orientation scores, modeling the cortical columns in the visual system of higher mammals. This allows us to successfully deal with the many complex problems inherent to vasculature tracking, such as tracking over crossings, bifurcations, parallel tracks and tracks of varying widths. The method runs fully automatically and provides a detailed model of the retinal vasculature, which is crucial as a sound basis for further quantitative analysis of the retina, especially in screening applications.
|Number of pages
|Published - 2012