SEGMENTATION ET INTERPRÉTATION D’IMAGES MÉDICALES PAR APPRENTISSAGE AUTOMATIQUE ET SYSTÈME MULTI-AGENTS

Abstract

In an image processing system, segmentation is primordial. Until now, there is no universal image segmentation method. Any technique is effective only for a given type of image, for a given type of application, and in a given context. The main objective of this work is to achieve the semantic segmentation of medical images using machine learning, a category Artificial Intelligence (AI) algorithm. It is precisely about implementing several approaches by taking advantage of the complementarities between different models of Deep Learning (DL). This allows to increase the robustness of the segmentation process. he challenge of this cooperation is based on segmentation by pixel classification in order to extract useful and relevant information. We have proposed four semantic segmentation approaches using different models of the Unet and Resnet50 architectures. An implementation is then done around a multi-agent system (MAS), providing a distribution of expertise and a reduction in execution time on 3D image sequences (slice). Keywords : Medical Imaging,segmentation, Machine Learning (ML), Artificial Intelligence (AI), Deep Learning (DL), Multi-Agent Systems (MAS).