A Dynamic Particle Swarm Optimisation and Fuzzy Clustering Means Algorithm for Segmentation of Multimodal Brain Magnetic Resonance Image Data

Kies Karima and Benamrane Nacera

Department of Computer Science, Université des Sciences et de la Technologie d’Oran “Mohamed Boudiaf”, Algeria

Abstract: Fuzzy Clustering Means (FCM) algorithm is a widely used clustering method in image segmentation, but it often falls into local minimum and is quite sensitive to initial values which are random in most cases. In this work, we consider the extension to FCM to multimodal data improved by a Dynamic Particle Swarm Optimization (DPSO) algorithm which by construction incorporates local and global optimization capabilities. Image segmentation of three-variate MRI brain data is achieved using FCM-3 and DPSOFCM-3 where the three modalities T1-weighted, T2-weighted and Proton Density (PD), are treated at once (the suffix -3 is added to distinguish our three-variate method from mono-variate methods usually using T1-weighted modality). FCM-3 and DPSOFCM-3 were evaluated on several Magnetic Resonance (MR) brain images corrupted by different levels of noise and intensity non-uniformity. By means of various performance criteria, our results show that the proposed method substantially improves segmentation results. For noisiest and most no-uniform images, the performance improved as much as 9% with respect to other methods.

Keywords: Fuzzy c-mean, particle swarm optimization, brain Magnetic Resonance Images segmentation.

Received December 24, 2019; accepted March 10, 2020