Parameter estimation and NMR image segmentation

A statistical method is proposed to classify tissue types and to segment the corresponding tissue regions from relaxation time T/sub 1/, T/sub 2/, and proton density N/sub H/ weighted nuclear magnetic resonance (NMR) images. The method assumes that the distribution of image intensities associated with each tissue type can be expressed as a multivariate likelihood function of three variables (T/sub 1/, T/sub 2/, N/sub H/) at each location within that tissue region. The method is tested by a set of T/sub 1/, T/sub 2/, and N/sub H/ weighted images of the brain acquired with a 1.5-T whole body scanner. The number of tissue types and the parameters of these tissue types are satisfactorily estimated. The regions of different tissue types are successfully segmented.<
>