Bayesian detection of the fovea in eye fundus angiographies

This paper is concerned with the automatic detection of the avascular fovea l zone (fovea), in eye fundus angiographies. Fluorescein angiography is use d in ophthalmic practice to evaluate vascular retinopathies and choroidopat hies: sodium fluorescein is injected in the arm's cubital vein of the patie nt and its distribution along retinal vessels at certain times is observed. The proposed methodology is based on Bayesian statistical methods that all ow to incorporate the previous knowledge about the eye fundus in the model. The contour of the fovea is modeled by means of a unidimensional Markov ch ain and the observed intensities are assumed Gaussian and statistically ind ependent between pixels. Two approximations are used in order to estimate t he model's parameters: Empirical and Fully Bayesian. Two algorithms have be en used in order to estimate the fovea contour: Simulated Annealing (SA) an d Iterated Conditional Modes (ICM). This procedure is applied to different cases of diabetic retinopathy and vein occlusions. (C) 1999 Elsevier Scienc e B.V. All rights reserved.