A Survey on Brain Tumor Classification Using Artificial Neural Network

Magnetic Resonance imaging (MRI) has become a widely used method of high quality medical imaging. Brain tumor classification is one of the major problems in diagnosing the tumor at early stage. Thus various methods are surveyed in order to obtain better classification accuracy and to reduce the computational time. Since misclassification occurs due to high diversity in tumor appearance and tumor boundaries. The various image processing techniques preprocessing, feature selection and extraction are used to detect exact tumor location. This study classifies brain tumor MRI images automatically as benign, grade1, grade2 and malignant tumor. Classification of tumor is done through Artificial Neural Network. The result of performance ensures that the GLCM with Neural Network Classifier provides about 95% accuracy.