MRI brain tumor image classification with support vector machine

Abstract

Digital image processing is becoming a developing research arena in medical disciplines for various pathological operations for detection of brain tumor and classification and also for examining and testing critical parts of the human body using microscopic images. In the proposed work segmentation is done by hybridizing the traditional k-means algorithm with SGHO (swarm -based grass hopper optimization algorithm). The SURF (speeded up robust feature) algorithm has been applied to extract features of the brain tumor images and SGHO based technique is used for selecting the features. In the last step svm classifier is applied for the classification of the tumor images. For performing all the steps of the proposed system, publicly accessible Contrast- Enhanced MRI dataset is utilized. The values for accuracy, precision and recall are 99.24%, 95.83%, and 95.30 % respectively. In terms of performance parameters, the results shows that the efficiency of the system is better when compared with earlier works.