We describe a sequence of low-level operations to isolate and classify brain tissue within T1-weighted magnetic resonance images (MRI). Our method first removes nonbrain tissue using a combination of anisotropic diffusion filtering, edge detection, and mathematical morphology. We compensate for image non-uniformities due to magnetic field inhomogeneities by fitting a tricubic B-spline gain field to local estimates of the image nonuniformity spaced throughout the MRI volume. The local estimates are computed by fitting a partial volume tissue measurement model to histograms of neighborhoods about each estimate point. The measurement model uses mean tissue intensity and noise variance values computed from the global image and a multiplicative bias parameter that is estimated for each region during the histogram fit. Voxels in the intensity-normalized image are then classified into six tissue types using a maximum a posteriori classifier. This classifier combines the partial volume tissue measurement model with a Gibbs prior that models the spatial properties of the brain. We validate each stage of our algorithm on real and phantom data. Using data from the 20 normal MRI brain data sets of the Internet Brain Segmentation Repository, our method achieved average κ indices of κ = 0.746 ± 0.114 for gray matter (GM) and κ = 0.798 ± 0.089 for white matter (WM) compared to expert labeled data. Our method achieved average κ indices κ = 0.893 ± 0.041 for GM and κ = 0.928 ± 0.039 for WM compared to the ground truth labeling on 12 volumes from the Montreal Neurological Institute's BrainWeb phantom.
Bibliographical noteFunding Information:
This work was supported in part by the National Institute of Mental Health Grants RO1-MH53213 and P50-MH57180.