A New Fast Brain Skull Stripping Method
Yunjie Chen, Jianwei Zhang, Shunfeng Wang · 2009
The segmentation of brain tissue from non-brain tissue in magnetic resonance (MR) images, commonly referred to as skull stripping, is an important image processing step in many neuroimage studies. In this paper, we propose a fast automatic skull-stripping method. The proposed method is based on an adaptive gauss mixture model and a 3D Mathematical Morphology method. The adaptive gauss mixture model classifies the brain tissues, meanwhile estimates the bias field. The new 3D Mathematical Morphology method can skull stripping other tissues efficiently and accurately. Comparisons with two existing methods, the brain extraction tool (BET) and the brain surface extractor (BSE), show the promising results of our method in terms of robustness and accuracy.