Skull stripping and automatic segmentation of brain MRI using seed growth and threshold techniques

Segmentation of human brain from MRI scan slices without human intervention is the objective of this paper. A simple and accurate method is developed for extracting the brain tissues from the T1 weighted MR Images. The DICOM images are used for segmenting. A hybrid of threshold and seed growth techniques are used in classifying the brain tissues into white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF).