An efficient brain tumor detection method based on image registration technique

Detection and diagnosis of brain tumor is complicated due to its similar characteristics between tumor pixels and non tumor pixels in brain image. This paper proposes an efficient methodology for the detection and segmentation of tumor region in brain. The proposed methodology has the following stages as image registration, noise reduction, transformation, feature extraction and classification. The linear image registration technique is used to align the reference image with respect to source brain image to obtain higher classification rate. Adaptive median filter is used for denoising the registered image. Gabor transform is further applied on the denoised image inorder to process the image multi scale and orientation. Features are extracted from the transformed image and these features are trained and classified using Adaptive Neuro Fuzzy Inference (ANFIS) classifier. The performance of the proposed methodology is analysedin terms of sensitivity, specificity and accuracy.