Fast, accurate, and reproducible automatic segmentation of the brain inT(1)-weighted volume MRI data

A new fast automated algorithm has been developed to segment the brain from T-1-weighted volume MR images, The algorithm uses automated thresholding a nd morphological operations. It is fully three-dimensional and therefore in dependent of scan orientation. The validity and the performance of the algo rithm were evaluated by comparing the automatically calculated brain volume with semi-automated measurements in 10 subjects, by calculating the brain volume from repeated scans in another 10 subjects, and by visual inspection . The mean and standard deviation of the difference between semi-automated and auto mated measurements were 0.56% and 2.8% of the mean brain volume, r espectively, which is within inter-observer variability of the semi-automat ed method. The mean and standard deviation of the difference between the to tal volumes calculated from repeated scans were 0.40% and 1.2% of the mean brain volume, respectively. Good results were also obtained from a scan of abnormal brains. Magn Reson Med 42:127-135, 1999. (C) 1999 Wiley-Liss, Inc.