Classification of Brain Tumor Using Neural Network

Abstract

Brain tumors classification in magnetic resonance imaging (MRI) is very important in medical diagnosis. Most of the current conventional diagnosis techniques are based on human experience in interpreting the MRI-scan for classification. This paper presents an automated method based on backpropagation neural network (BPNN) for classification of the MRI of a human brain. The proposed method utilizes wavelet transform (WT) as a feature extraction tool of the MRI.  The proposed method follows two steps: feature extraction and classification. WT is first employed for decomposing the image into different levels of approximate and detailed coefficients and then these coefficients are fed into a BPNN for further classification and tumor detection. The proposed method has been applied on several MRI scans, and the results showed an acceptable accuracy of classification.