BRAIN TUMOR CLASSIFICATION IN 3D-MRI USING FEATURES FROM RADIOMICS AND 3D-CNN COMBINED WITH KNN CLASSIFIER

In the diagnosis of Brain tumor Magnetic Resonance Imaging has an important role in the identification of tumor. But classification becomes very difficult for the physician due to the complex structure of the brain. A very few features can be extracted from 2D Brain MRI. 3D MRI provides comparable diagnostic performance and gives more features than 2D MRI. In this paper, 3D MRI is employed for the detection and classification of a Brain Tumor. Radiomics uses data-characterization algorithms capable of getting a large number of features from MRI. These radiomics features can uncover the characteristics of the disease. Pyradiomics, a python open-source package is used to extract GLCM features. A Combinational Model that uses the features of GLCM (Grey Level Co-occurrence Matrix) and 3D-CNN (Convolution Neural Network) combined with KNN (K-Nearest Neighbor) is carried out on 3D MRI. 3DCNN is used to extract a more powerful volumetric representation across all three axes. The last layer of 3D-CNN is supposed to learn a good representation of an image. The features are extracted from that layer and provided to KNN classifier for further prediction. The accuracy is observed to be improved by up to 96.7% using this method.