Automatic morphology-based brain segmentation (MBRASE) from MRI-T1 data

A method called morphology-based brain segmentation (MBRASE) has been devel oped for fully automatic segmentation of the brain from T1-weighted MR imag e data. The starting point is a supervised segmentation technique, which ha s proven highly effective and accurate for quantitation and visualization p urposes. The proposed method automates the required user interaction, i.e., defining a seed point and a threshold range, and is based on the simple op erations thresholding, erosion, and geodesic dilation. The thresholds are d etected in a region growing process and are defined by connections of the b rain to other tissues. The method is first evaluated on three computer simu lated datasets by comparing the automated segmentations with the original d istributions. The second evaluation is done on a total of 30 patient datase ts, by comparing the automated segmentations with supervised segmentations carried out by a neuroanatomy expert. The comparison between two binary seg mentations is performed both quantitatively and qualitatively. The automate d segmentations are found to be accurate and robust. Consequently, the prop osed method can be used as a default segmentation for quantitation and visu alization of the human brain from T1-weighted MR images in routine clinical procedures. (C) 2000 Academic Press.