Skull Stripping from MRI of Head Scans based on 2D Region Growing

Skull stripping is a process of segmenting brain portion 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 2D region growing. This is a fully automatic method for segmenting the brain portion from T1, T2 and PD weighted MR images. The proposed method consists of two major processes. First we extract the brain portion in the middle slice and then we extract brains in the remaining slices. In this method the binary form of the brain image is processed first to find the rough brain. Then by using the 2D region growing method the fine brain area in the rough brain is detected. A circle is defined inside the rough brain to select the seed points for region growing. We use the geometric similarities of the adjacent slice to extract brain portions in the remaining slices. The proposed method extracts the brain accurately in T1, T2 and PD weighted images. Experimental results show that the proposed method extract the brain portion more accurately than BET and BSE methods. Keywords— Skull stripping, Region growing, Magnetic resonance image(MRI), Segmentation