Classification of Brain Tumor Using Texture Analysis

Diagnosis of brain tumor is very critical ordinarily, this study presents a highly efficient method to identify, diagnosis and classify the intracranial tumors. Forty-nine CT images contain different types of intracranial tumor were selected, the procedure contain dual phase, phase one contain feature extraction from the selected images, phase two classification of images component according to the extracted features using linear discriminant analysis, the quantitative results showed that the proposed method has high accuracy in recognizing the intracranial tumor from the normal surrounding tissues. The accuracy of classification was 90.4 %.