A Model Based Approach for Vessel Caliber Measurement in Retinal Images

The diagnostic signature of many microvasculature diseases like diabetes mellitus, hypertension and arteriosclerosis includes the changes incurred in the diameter of retinal blood vessels. Therefore estimation of precise vascular widths is a critical and demanding process in automated retinal image analysis. This paper proposes an automated system to measure the vessel caliber in the retinal images of multi-ethnic school children. The diameter measurement is based on the detection of the centerline pixels from a vessel probability map image, determining the vessel orientation at these pixels, extracting the vessel segments and later using a two dimensional model, which is optimized to fit various types of intensity profiles of vessel segments. The width is then estimated from parameters of the optimized model. The method is also used to explore the relationship between the average vessel width and the background pigmentation of the retinal image by analyzing monochromatic representations of different color spaces.