MRI brain image classification using neural networks

• Published in: 2013 INTERNATIONAL CONFERENCE ON COMPUTING, ELECTRICAL AND ELECTRONIC ENGINEERING (ICCEEE) pp. 253 - 258
• Main Authors: Ibrahim, Walaa Hussein, Osman, Ahmed AbdelRhman Ahmed, Mohamed, Yusra Ibrahim
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2013
• Subjects: Artificial neural networks; Back-Propagation neural networks; Biological neural networks; Brain tumor detection; Linear regression; MRI; Neurons; PCA; Principal component analysis; Training; Vectors
• DOI: 10.1109/ICCEEE.2013.6633943

Classification of brain tumor using Magnetic resonance Imaging (MRI) is a difficult task due to the variance and complexity of tumors. This paper presents Neural Network techniques for the classification of the magnetic resonance human brain images. The proposed Neural Network technique consists of three stages, preprocessing, dimensionality reduction, and classification. In the first stage, we The MR image will obtain and convert it to data form (encoded information that can be stored, manipulated and transmitted by digital devices), in the second stage have obtained the dimensionally reduction using principles component analysis (PCA), then In the classification stage the Back-Propagation Neural Network has been used as a classifier to classify subjects as normal or abnormal MRI brain images. In the experiment 3×58 datasets of MRI Brain segital images (www.cipr.rpi.edu/resource/sequences/sequence01) have been used for tainting and testing the proposed method. The result of the proposed technique was compared with the results of baseline algorithms, and it presents validity as competitive results quality-wise, and showed that the classification accuracy of our method is 96.33%.