Segmentation of macular fluorescein angiographies. A statistical approach

This paper is concerned with the use of Bayesian methods in the segmentatio n of macular fluorescein angiographies. Fluorescein angiography is used ill ophthalmic practice to evaluate vascular retinopathies and choroidopathies : Sodium fluorescein is injected in the arm's cubital vein of the patient a nd its distribution is observed along retinal vessels at certain times. In this task a previous and essential step is the segmentation of the image in to its relevant components. In order to obtain this segmentation Bayesian m ethods can be used because a previous knowledge about the spatial structure of the scene to be segmented is available in this kind of images. The stoc hastic model assumed for the observed intensities is a simple model with a Gaussian noise process which is statiscally independent between pixels. The process of labels x is modelled as a Markov random field with a space-depe ndent external field expressing the anatomy of the ocular fundus and higher order interactions encouraging blood vessels to be thin and large. This pr ocedure is applied to different cases of diabetic retinophaty and vein occl usions. Two algorithms have been used to estimate x, simulated annealing an d iterated conditional modes. In order to evaluate the accuracy of the esti mation several error measures have been calculated. (C) 2001 Pattern Recogn ition Society. Published by Elsevier Science Ltd. All rights reserved.