Towards a Generic Multi-agent Approach for Medical Image Segmentation

Mohamed Tahar Bennai (1, 2) , Zahia Guessoum (1, 3) , Smaine Mazouzi (4) , Stephane Cormier (1) , Mohamed Mezghiche (2)

1 CRESTIC - Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804
2 LIMOSE - Laboratoire d’Informatique de Modélisation d’Optimisation et de Systèmes Electroniques [Boumerdes]
3 SMA - Systèmes Multi-Agents
4 Université 20 Août 1955 Skikda

Medical image segmentation is a difficult task, essentially due to the inherent complexity of human body structures and the acquisition methods of this kind of images. Manual segmentation of medical images requires advance radiological expertize and is also very time-consuming. Several methods have been developed to automatize medical image segmentation, including multi-agent approaches. In this paper, we propose a new multi-agent approach based on a set of autonomous and interactive agents that integrates an enhanced region growing algorithm. It does not require any prior knowledge. This approach was implemented and experiments were performed on brain MRI simulated images and the obtained results are promising.

Domaines: Système multi-agents [cs.MA]; Intelligence artificielle [cs.AI]

Mohamed Tahar Bennai, Zahia Guessoum, Smaine Mazouzi, Stephane Cormier, Mohamed Mezghiche. Towards a Generic Multi-agent Approach for Medical Image Segmentation. International Conference on Principles and Practice of Multi-Agent Systems (PRIMA), Oct 2017, Nice, France. pp.198-211, ⟨10.1007/978-3-319-69131-2_12⟩. ⟨hal-02531244⟩