Fully automatic algorithm for the analysis of vessels in the angiographic image of the eye fundus

Abstract

BackgroundThe available scientific literature contains descriptions of manual, semi-automated and automated methods for analysing angiographic images. The presented algorithms segment vessels calculating their tortuosity or number in a given area. We describe a statistical analysis of the inclination of the vessels in the fundus as related to their distance from the center of the optic disc.MethodsThe paper presents an automated method for analysing vessels which are found in angiographic images of the eye using a Matlab implemented algorithm. It performs filtration and convolution operations with suggested masks. The result is an image containing information on the location of vessels and their inclination angle in relation to the center of the optic disc. This is a new approach to the analysis of vessels whose usefulness has been confirmed in the diagnosis of hypertension.ResultsThe proposed algorithm analyzed and processed the images of the eye fundus using a classifier in the form of decision trees. It enabled the proper classification of healthy patients and those with hypertension. The result is a very good separation of healthy subjects from the hypertensive ones: sensitivity - 83%, specificity - 100%, accuracy - 96%. This confirms a practical usefulness of the proposed method.ConclusionsThis paper presents an algorithm for the automatic analysis of morphological parameters of the fundus vessels. Such an analysis is performed during fluorescein angiography of the eye. The presented algorithm automatically calculates the global statistical features connected with both tortuosity of vessels and their total area or their number.

Three-dimensional reconstruction of blood vessels in the rabbit eye by X-ray phase contrast imaging

“…The detection of vessels in the retina has improved from manual, to semiautomated, to automated [13]. Nonlinear projections [14] and multiscale line operators [15] are familiar methods to analyze retinal blood vessels.…”

A fully automated tortuosity quantification system with application to corneal nerve fibres in confocal microscopy images

“…Further issues include the presence of non-target structures (clutter), low resolution, noise and non-uniform illumination. Fully automated tortuosity estimation frameworks have been proposed for retinal blood vessels, brain vasculature and corneal nerve fibres (Heneghan et al, 2002;Joshi et al, 2010;Scarpa et al, 2011;Koprowski et al, 2012). Typically, inaccuracies in the segmentation are the main source of inaccurate tortuosity estimates (e.g., Scarpa et al, 2011).…”

Implementation of Stochastic Approach for Vessel and Ridge Studies in Retinopathy of Prematurity Screening

“…Simple thresholding operation could be used to identify retinal vessels and ridges 11 . On the other hand, unsupervised algorithms have been combined with the automatic optimization of parameters which have been utilized to obtain faster results with new image types 18,19 . The manual detection of tortuosity, vessel and ridge width to screen the severity level of ROP is a time-consuming procedure and the ophthalmologist may get fatigue on scanning and analysing the ROP images 20 .…”