A New Optimal Neuro-Fuzzy Inference System for MR Image Classification and Multiple Scleroses Detection

Hakima Zouaoui (1) , Abdelouahab Moussaoui (1) , Abdelmalik Taleb-Ahmed (2) , Mourad Oussalah (3)

1 Faculty of Sciences, University Ferhat Abbas
2 LAMIH - Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201
3 Oulu University of Applied Sciences

In the present article, we propose a new approach for the segmentation of the MR images of the Multiple Sclerosis (MS) which is an autoimmune inflammatory disease affecting the central nervous system. Our algorithm of segmentation is composed of three stages: segmentation of the brain into regions using the algorithm FCM (Fuzzy C-Means) in order to obtain the characterization of the different healthy tissues (White matter, grey matter and cerebrospinal fluid (CSF)), the elimination of the atypical data (outliers) of the white matter by the optimization algorithm PSOBC (Particle Swarm Optimization-Based image Clustering), finally, the use of a Mamdani-type fuzzy model to extract the MS lesions among all the absurd data

Mots clés: "Fuzzy C-mean"; "Fuzzy controller"; "Magnetic resonance imaging"; "Multiple sclerosis"; "Particle swarm optimization"; "Segmentation"

Domaines: Informatique [cs]

Hakima Zouaoui, Abdelouahab Moussaoui, Abdelmalik Taleb-Ahmed, Mourad Oussalah. A New Optimal Neuro-Fuzzy Inference System for MR Image Classification and Multiple Scleroses Detection. 11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016, Oct 2016, Xian, China. pp.487-493, ⟨10.1007/978-981-10-3611-8_45⟩. ⟨hal-03671286⟩