Jaya Algorithm based Tool to Examine Tumor of Brain MRI

Abstract

Brain malignancy is a hazardous sickness among human beings and distress people regardless of their race, age, gender and locality. Due to its significance, a considerable research works are obtainable in the literature. This work implements a semi-automated computer based tool to extract the tumor region from the benchmark BRATS 2015 brain MRI database. A process by incorporating the thresholding and level-set (DRLS) segmentation is implemented to extract the tumor section from the MRI. Initially, Kapur’s entropy assisted thresholding is implemented to improve the tumor section; later the segmentation practice is executed to extract the tumor. After extracting the infected segment, a comparative investigation is accomplished with respect to the ground truth (GT) image in order to evaluate the performance of the proposed semi-automated tool. The experimental results of this work confirm that, proposed approach offers better average result for the Jaccard, Dice, sensitivity, specificity and accuracy. In future, this procedure can be considered to examine the real-time brain MRI obtained from the clinics.