Brain tumor detection and classification in MRI images using image and data mining

Brain tumor is a perilous disease which causes brain damage. So, detection and classification of brain tumor in early stage is necessary. In the proposed work MRI brain images are pre-processed by median filtering. To segregate lesion from image, color based segmentation and edge detection is performed. Multiple feature extraction schemes, namely histogram of oriented gradients and gray level co-occurrence matrix are used to represent the images. All the extracted features are stored in a transactional database to which IBkLG classifier (Instance based K-Nearest using Log and Gaussian weight Kernels) has been applied using WEKA 3.9 tool, to classify the tumor into normal benign or malignant. The classification accuracy is observed found to be 86.6%.