Neurodegenerative diseases such as Alzheimer’s disease (AD), present increasing challenges. Determining the sequence and evolution of the symptoms and pathologies of AD will enable pre-symptom differential diagnosis, and treatment monitoring. Current diagnosis of Alzheimer is made by clinical, neuropsychological, and neuroimaging assessments. In fact, Magnetic Resonance Imaging (MRI) can be considered as the best neuroimaging examination for AD due to the well-defined measurement of brain structures, especially the size of the hippocampus and related regions. Image processing techniques has been used for processing the (MRI) image. Multi-agent Systems (MAS) is a strong paradigm full of complexity that offers promoters solution. We present a MAS solution that aims to automate the search and optimization of image processing. In this survey we propose a three-dimensional (3D) segmentation process based on cooperative MAS.