DefinePK

Abstract

Magnetic Resonance Imaging (MRI) has been a robust tool for the diagnosis of brain tumors. MRI is an imaging technique that provides detailed information about brain anatomy. This paper announces a novel method for efficient and accurate MRI analysis. The images are pre-processed to increase the contrast and to remove the skull region. A novel algorithm is used to check whether the given image is normal or not. This algorithm reduces the computational complexity and increase the speed of proposed classification system by selecting abnormal images alone for further processing. Segmentation is performed on abnormal images to find the tumor region. Segmentation is based on a hybrid algorithm using K-means clustering and Texture Pattern Matrix. Texture Features and shape features are separately extracted from the segmented binary image using Gray Level Co-occurrence Matrix (GLCM) and connected regions. The features thus obtained are used to train the neural network using Back Propagation Algorithm defined by Levenberg-Marquardt (LM) algorithm. Feed Forward Neural Network (FFNN) is used for the classification of MR images. While using the proposed method, accuracy is 98.06%, specificity is 97.77% and sensitivity is 98.34%. Speed, Robustness and computational complexity are the major advantages of the proposed system.