Machine Learning Application for Classification of Brain Tumors Through MR Images to Detect Malignancy

In the present paper classification of Brain Tumours through MRI imaging as Fine, Medium and Coarse textures is proposed. The other methods of classification of brain tumours that are frequently used are based on size, shape and spread of the tumour. The importance of classifying tumours based on texture is that there is correlation between malignancy of the tumour and the texture of the tumour. The other methods normally don't give this information. In this paper relation between texture of the tumour and it's malignancy has been explored. Four methods of feature extraction have been used, in order to obtain texture information of the tumour. They are, Gray Level Co-occurrence Matrix (GLCM), Gradient Matrix (GM), Laplacian Of Gaussian (LoG) and the Run-Length Matrix (RLM). Once the features are extracted, they are passed to Decision Tree classification algorithm. The classification algorithms classified the extracted features as having Fine, Medium or Coarse textures. The result obtained showed correlation between texture of the tumour and its malignancy. If the texture is predicted as Fine, then it is most likely a non-malignant, or benign tumour, and its diagnosis is most likely going to give a Complete response. A Medium texture would most likely give a Partial response, and is not very malignant. This is important, since knowing this information can benefit the patient and clinicians. This improves the diagnostic confidence of the clinicians and allows them to diagnose and report multiple patients that results in lower cost of the examination as well as access to diagnostics to people living in remote areas.