Quantification and characterisation of arteries in retinal images

A computerised system is presented for the automatic quantification of bloo d vessel topography in retinal images. This system utilises digital image p rocessing techniques to provide more reliable and comprehensive information for the retinal vascular network. It applies strategies and algorithms for measuring vascular trees and includes methods for locating the centre of a bifurcation, detecting vessel branches, estimating vessel diameter, and ca lculating angular geometry at a bifurcation. The performance of the system is studied by comparison with manual measurements and by comparing measurem ents between red-free images and fluorescein images. In general an acceptab le degree of accuracy and precision was seen for all measurements, although the system had difficulty dealing with very noisy images and small or espe cially tortuous blood vessels. (C) 2000 Elsevier Science Ireland Ltd. All r ights reserved.