Fractional order derivatives becoming popular and recently finds applications in the field of medical image segmentation. They even extract edge features in the low contrast areas of the images. This motivated us to design a novel brain segmentation approach using Fractional Order PSO. Thus a novel brain tumor segmentation using Fuzzy C-means (FCM) with Fractional Order Darwinian Particle Swam Optimization (FO-DPSO) is implemented in this paper. This segmentation method divides brain tumour segmentation into three stages. In the first phase skull stripping and de-noising steps are used for pre-processing in order to remove the noise and improve the speed of processing. In the second phase fuzzy c-means clustering based segmentation is used with Fractional order particle swarm optimization and in the third phase the proposed method is evaluated. This novel segmentation method can be evaluated in the result analysis and the outputs are compared with state of the art techniques PSO and DPSO in terms of DC (Dice Coefficient), SSIM (Structural Similarity Index) and JSI (Jaccard Similarity Index). The novel segmentation method shows biased performance than the other and reduces the processing time compared to PSO algorithm and DPSO algorithm.

Brain Tumour Segmentation, Functional Order Darwinian Particle Swam Optimization (FO-DPSO), fuzzy C-means (FCM)