Using MAS to Detect Retinal Blood Vessels Carla Pereira 1 , Jason Mahdjoub 2 , Zahia Guessoum 2 , Luís Gonçalves 3 , Manuel Ferreira 1 1 Industrial Electronics Department, University of Minho, Campus de Azurém, 4800-058 Guimarães, Portugal 2 CReSTIC – MODECO, University of Reims, rue des Crayères, 51100, Reims, France 3 Ophthalmology Service, Centro Hospitalar do Alto Ave, Guimarães, Portugal Abstract The segmentation of retinal vasculature by color fundus images analysis is crucial for several medical diagnostic systems, such as the dia- betic retinopathy early diagnosis. Several interesting approaches have been done in this field but the obtained results need to be improved. We propose therefore a new approach based on an organization of agents. This multi-agent approach is preceded by a preprocessing phase in which the fundamental filter is an improved version of the Kirsch derivative. This first phase allows the construction of an environment where the agents are situated and interact. Then, edges detection emerged froŵ ageŶts’ in- teraction. With this study, competitive results as compared with those present in the literature were achieved and it seems that a very efficient system for the diabetic retinopathy diagnosis could be built using MAS mechanisms. Keywords. Diabetic retinopathy; Fundus images; Image processing; Kirsch filter; Multi-agent system 1 Introduction The segmentation of the retinal vasculature is of major importance for clinical purposes. In fact, by analyzing the vascular structures it is possible to have the early diagnosis of several chronic pathologies, such as diabetic retinopathy (DR). In this study, the blood vessels segmentation was per-