No abstract

In the medical world, most challenging disease is Brain tumor. Brain tumors formed inside the brain as an abnormal cell. It is a mass of tissues which results in hormonal changes results in mortality. In the recent years, various brain tumor detection techniques are evolved. We propose, a novel brain tumor detection technique is proposed to detect tumors accurately in given brain MR image and also it classifies the given brain MR image is normal or abnormal. At first the preprocessing is performed by median filtering and segmentation by means of morphological technique. Then the Gray Level Co-occurrence Matrix (GLCM) is applied to extract the texture features. Then, the derived features are applied to classification using three classifiers such as Naïve Bayes, Multilayer perceptron, and Decision Tree C4.5 classifiers. By conducting experiments, the proposed technique is assessed and validated for performance as well as quality analysis based on accuracy, sensitivity and specificity on brain MR images. In experimental section, the performance of all three classifiers are compared in which the decision tree C4.5 algorithm provides better performance with 75% of accuracy, 79% of sensitivity and 56% of specificity.