ABSTRACT
Drusens are indicators of macular degeneration, a disease characterized by accumulations of extra cellular materials under retina. The automatic study of the quantitative evolution of Drusen spots throughout a medical treatment constitutes a useful tool for ophthalmologists. Until now, drusen evaluation was done manually, based only on qualitative aspects. Also the analyses depended on the ophthalmologist and were not ease to reproduce.
Another important issue is that retina is not a plane surface and therefore light doesn’t have a uniform distribution, producing images with non-uniform illumination and consequently with different contrast areas.
Computer aided tools that can help doctors in repetitive analysis are becoming more reliable and faster, contributing for its increasing acceptance. In this paper it is presented an algorithm based on smoothing splines for non-uniform illumination correction, and a software application based on Levenberg-Marquardt optimization algorithm for automatic modelling of drusen deposits in retina images. For improving the modelling process a customized algorithm for detecting image intensity maximums based on labelling gradient paths is presented. The results of applying this methodology to retina images containing medium sized Drusen will also be presented.
