A hybrid method for automatic skull stripping of magnetic resonance images (MRI) of human head scans

Abstract

Automatic segmentation of brain tissue on magnetic resonance images is a challenging process due to the variation in brain shapes and similarity of intensity values in the brain and non-brain tissues. Skull stripping is a process of segmenting brain and non-brain tissues in MR brain images. It is an important image processing step in many neuroimage studies. In this paper, we propose a new skull stripping method for magnetic resonance image (MRI) of human head scans based on image contour. We used hybrid method, which combines two or more methods to produce better result. This algorithm first pre-processes the image by denoising using mean filter. The denoised image is blurred to obtain a rough brain mask using image contour. The rough mask is further processed to produce final brain mask. The proposed algorithm is compared with standard manual stripping (Gold standard) images and produced significant result. The experimental results show that the proposed method extracted the brain accurately which are comparable to that of BSE, BET, WAT and HWA using IBSR data set.