Bioinspired Inference System for Medical Image Segmentation

Abstract

In the present article, we propose a new approach for the segmentation of the MRI images of the Multiple Sclerosis which is an autoimmune inflammatory disease affecting the central nervous system. Clinical tracers are used nowadays for the diagnosis and the Inter-observer and intra-observer therapeutic assessment. However, those tracers are subjective and subject to a huge variability. The Magnetic Resonance Imaging (MRI) allows the visualization of the brain and it is widely used in the diagnosis and the follow-up of the patients suffering from MS. Aiming to automate a long and tedious process for the clinician, we propose the automatic segmentation of the MS lesions. 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.