Performance Analysis of Machine Learning Classifiers for Brain Tumor MR Images

Brain cancer has remained one of the key causes of deaths in people of all ages. One way to survival amongst patients is to correctly diagnose cancer in its early stages. Recently machine learning has become a very important tool in medical image classification. Our approach is to examine and compare various machine learning classification algorithms that help in brain tumor classification of Magnetic Resonance (MR) images. We have compared Artificial Neural Network (ANN), K-nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM) and Naïve Bayes (NB) classifiers to determine the accuracy of each classifier and find the best amongst them for classification of cancerous and noncancerous brain MR images. We have used 86 MR images and extracted a large number of features for each image. Since the equal number of images, have been used thus there is no suspicion of results being biased. For our data set the most accurate results were provided by ANN. It was found that ANN provides better results for medium to large database of Brain MR Images.