The Automated Skull Stripping of Brain Magnetic Resonance Images using the Integrated Method

Skull stripping is one of the significant steps in brain image processing. There are still a number of difficulties using those common methods such as the region growing method. Aforesaid methods were largely depended on shape or intensity of non-brain tissues. This led to a difficulty when those non-brain tissues and intracranial have approximately the same intensity values. This research proposed an automatic skull stripping method based on the combination of mathematical morphology, component labeling and segmentation by Object Attribute Threshold (OAT). With this proposed method: MLO that combined the morphology, labeling and object attribute threshold method together, the removing of non-cerebral tissues can be completed. The proposed method also performed well even for the case that both cerebral and non-cerebral values on the MRI brain images have similar intensity. We used 20 samples of T1-weighted MRI brain images in the experiments.