Tissue classification and segmentation of MR images

Previously reported classification or segmentation methods are reviewed, and some statistical approaches that may be capable of automatically classifying tissues and segmenting magnetic resonance (MR) images are discussed. The image segmentation methods reviewed are edge detection methods and region detection methods. The key feature of statistical approaches toward automatically classifying tissues and segmenting MR images is the determination of the number of image classes and the model parameters of these classes from the image data directly by a computer. Any free parameter requiring extensive user interactions should be avoided. Further research on the Gaussian Markov random field (GMRF) model and the MRF penalty term will push the statistical approaches further along the automatic track. As these approaches become more practical they will become more valuable.<<ETX>>