Brain tumor segmentation from MRI using fractional sobel mask and watershed transform

In this paper a novel brain tumor segmentation scheme using fractional order sobel mask and marker controlled watershed transform is proposed. To obtain the bright tumor region, regional maxima operation is performed on morphological preprocessed input T2-weighted MR image. The output regional maxima image is taken as an internal marker. Distance transform based watershed transform is applied on regional maxima image, the watershed ridge lines are used as external marker. Now, the fractional sobel mask of order a=0.3 is applied on input T2-weighted MR brain image to obtain gradient magnitude image. The segmentation of tumor region is achieved by using the watershed transform of gradient magnitude image with the help of derived internal and external markers. Region of interest (ROI) is selected to get the final segmented tumor image. Simulations are performed on images taken from the BRATS-2013 dataset for different values of a. For a = 0.3 values of accuracy, sensitivity and specificity performance parameters are comparable to other schemes compared. Moreover, fractional order a provides additional degree of freedom in optimizing the segmentation results. Proposed scheme can be used to segment other types of tumors and also for segmentation of CT images.