Home // ADAPTIVE 2019, The Eleventh International Conference on Adaptive and Self-Adaptive Systems and Applications // View article

A Multi-Agent Approach for Self-adaptive MRI Segmentation

Authors:
Mohamed Tahar Bennai
Mazouzi Smaine
Zahia Guessoum
Mohamed Mezghiche
Stéphane Cormier

Keywords: Image processing, image segmentation, multi-agent systems, Self-adaptation.

Abstract:
Medical image processing provides important help for establishing diagnoses for several pathologies. In medical imagery, image segmentation is crucial for several applications such as lesion detection and delimitation, and tracking of disease evolution. Different image segmentation approaches have been proposed. However, the segmentation parameters are beforehand adjusted in most of those approaches. The latter do not allow the segmentation process to handle all the situations that can be found in the images. The goal of this paper is to introduce a new multi-agent approach for self-adaptive segmentation of Magnetic Resonance Image (MRI) data. Our approach is based on situated agents that interact together, and where each agent can perform discontinuity detection or similarity detection. Each agent parameters rely on its location in the image. That approach was implemented and tested on MRI data, and the first results are promising.

Pages: 7 to 12

Copyright: Copyright (c) IARIA, 2019

Publication date: May 5, 2019

Published in: conference

ISSN: 2308-4146

ISBN: 978-1-61208-706-1

Location: Venice, Italy

Dates: from May 5, 2019 to May 9, 2019