Brain tumors and associated nervous system cancers are one of the largest reasons behind the death of human beings. Timely identification of a tumor can help save a person's life. The detection of brain tumors is time-consuming and also needs a specialized radiologist for lesion detection. Machine Learning techniques can assist in the detection of brain tumors. These algorithms are critical in correctly predicting the presence of tumors in human beings. In this context, this paper uses the K-means algorithm to segment the brain MRI and then extracts features from these segmented MRIs for the purpose of detecting the brain tumor. The features are extracted by using the Gray Level Co-occurrence Matrix (GLCM). The features extracted are fed into the classifiers Support Vector Machine (SVM) and Decision Tree (DT) to segregate the tumorous and non-tumorous MRIs. Our proposed approach performs better than state-of-the-art methods in terms of classification accuracy.

sbrain tumor, gray level co-occurrence matrix, K-means, machine learning, magnetic resonance imaging