Segmentation and classification of brain tumor using wavelet and Zernike based features on MRI

This study aimed was to initiate an automated tumor diagnostic system based on T1 and T2 weighted magnetic resonance images (MRI). This system comprise of enhancement and segmentation as the initial steps to segment benign and malignant tumor or tissue by various image processing filtering and k-means algorithm. The textural and shape based features were extracted by wavelet transform and Zernike moments from the segmented tumor regions. Finally, the implementation of the suggested system was evaluated with extreme learning machine (ELM) algorithm to discriminate two types of tumor on MR images. The Diagnostic efficiency of the proposed system was evaluated with sensitivity, specificity and accuracy.