Affiliations: National University of Computer & Emerging Sciences FAST, Islamabad, Pakistan | Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, Pakistan
Note: [] Corresponding author. Muhammad Nazir, National University of Computer & Emerging Sciences FAST, Islamabad, Pakistan. Tel.: +9251 111 128 128; Fax: +9251 831 4119; E-mail: [email protected]
Abstract: There are many approaches for accurate and automatic classification of brain MRI. In this paper, a simple approach for automatic detection and classification is presented. Artificial Neural Network has been utilized for brain MRI classification as malignant or benign. The approach consists of three stages namely pre processing, features' extraction and classification. In pre-processing stage, filters are applied for the removal of noise. In the features' extraction phase, color moments are extracted as mean features from the MRI images and the color moments extracted are presented to simple feed forward artificial neural network for classification. The method was applied using total 70 images with 25 normal images and 45 abnormal images. The classification accuracy was found to be 88.9% for training data, 94.9% for validation data and 94.2% for testing data whereas the overall accuracy of 91.8% was observed.
Keywords: MRI classification, features' extraction, color moments, artificial neural network
