Classification of Brain Tumor Using Artificial Neural Network

In our work we try to exploit the capability of Back propagation neural network (BPN) and Radial Basis Function Neural network (RBFN) to classify brain MRI images either cancerous or Non- cancerous tumour automatically. Classification is with respect to symmetry of brain images exhibited in the axial and coronal images. The initial objective of our work is to study which algorithm is superior in classification tasks, and to examine the advantages and downfalls of each algorithm under varying conditions. We use BPN and RBF classifiers to classify and segment the tumour portion in abnormal images using optimal texture feature extracted from normal and tumour region of MRI by using statistical features. Since testing and training phase gives the percentage of accuracy on each parameter in neural networks, which gives the idea to choose the best one to be used in further works. Later feasible modifications will be incorporated in the BPN and RBF classification to obtain the promising results.