Multiresolution automatic segmentation of T1-weighted brain MR images

Automatic segmentation of brain tissues is crucial to many medical imaging applications. We use a multi-resolution analysis and a power transform to extend the well-known Gaussian mixture model expectation maximization based algorithm for segmentation of white matter, gray matter, and cerebrospinal fluid from T1-weighted magnetic resonance images (MRI) of the brain. Experimental results with near 4000 synthetic and real images are included. The results illustrate that the proposed method outperforms six existing methods.