Registration of retinal images by a MAS-ICP approach - a preliminary study

Diabetic retinopathy has been revealed as the most common cause of blindness among people of working age. For monitoring the pathology image registration algorithms applied to retinal images is very useful. In this work, a novel vessel-based retinal image registration approach is proposed. The segmentation of the vasculature is performed by a multi-agent system model. All these information is then used in a Robust Point Matching Iterative Closest Point algorithm improved by a Region Bootstrap approach. With this preliminary study, the novelty of integrating all these algorithms for image registration preceded by a multi-agents system for image edges detection seems to be efficient for temporal retinal image registration. Consequently, a system developed on basis of this approach could help in screening programs for the diabetic retinopathy prevention.C. P. thanks the Fundacao para a Ciencia e Tecnologia (FCT), Portugal for the Ph.D. Grant SFRH/BD/ 61829/2009