Bayesian Classification Using DCT Features for Brain Tumor Detection

Mortality rate by the brain tumor was very high some years before. But now this rate is decreased in the recent years due to the earlier diagnosis and proper treatment. Chances of the long survival of the patient can be increased by the accurate brain tumor diagnosis. For this regard we are proposing more accurate and efficient system for brain tumor diagnosis and brain tumor region extraction. Proposed system first diagnosis the tumor from the brain MR images using naive bayes classification. After diagnosis brain tumor region is extracted using K-means clustering and boundary detection techniques. We are achieving diagnosis accuracy more than 99%. Qualitative results show that accurate tumor region is extracted by the proposed system. The proposed technique is tested against the datasets of different patients received from Holy Family hospital and Abrar MRI&CT Scan center Rawalpindi.