A recursive estimation approach to the segmentation of MR imagery

Magnetic resonance imaging (MRI) has become a widely used research and clinical tool in the study of the human brain. The ability to accurately segment the MRI data set into homogeneous regions such as gray matter, white matter, and cerebro spinal fluid aids in morphological quantification of brain features. The large amount of data associated with typical MRI brain scans makes completely manual segmentation prohibitive on a large scale. We develop an estimation-theoretic interpretation of the segmentation problem which leads to a computationally efficient, statistically based recursive technique for its solution. Being statistically based, the method also provides associated measures of uncertainty of the resulting estimates, which are useful both for evaluation of the estimates as well as their combination with other sources of information