Efficient Brain and Liver Tumor Segmentation using Seagull Optimization Algorithm based Super Pixel Fuzzy Clustering

Now a days, medical image segmentation has been utilized in many applications with the consideration of computer aided diagnosis system. From that, brain tumour segmentation with MRI image play a main role in disease prediction. Hence, in this paper Seagull Optimization Algorithm Based Super Pixel Fuzzy Clustering (SOA-SFC)is designed for segmentation. The proposed segmentation process is designed with the combination of Super Pixel Fuzzy Clustering and Seagull Optimization Algorithm. In the Super Pixel Fuzzy Clustering, the efficient cluster center is chosen with the assistance of Seagull Optimization Algorithm. Initially, the Super Pixel Fuzzy Clustering objective function is considered with the consideration of fuzzy information extracted from the images of brain. After that, Seagull Optimization Algorithm is utilized towards optimize the cluster center in addition fuzzifier from the clustering method. The projectedtechniquecan be implemented in the MATLAB in additionpresentationiscomputed. The projectedtechniquecan becontrasted with the existing techniqueslike fuzzy c means clustering, k means clustering methods and Chimp Optimization Algorithm Based Type-2 Intuitionistic Fuzzy C-Means Clustering (COA-T2FCM). The projected method can be validated by performance metrices such as Dice similarity coefficient (DSC), Jaccard Similarity Index (JSI), accuracy, sensitivity, and specificity.