In-Vivo Intensity Correction and Segmentation of Magnetic Resonance Image Data
William M. Wells, R. Kikinis, Ferenc Andras Jolesz · 1994
Applications that use the structural contents of MRI are facilitated by segmenting the imaged volume into different tissue types. Such tissue segmentation is often achieved by applying statistical classification methods to the signal intensities [Gerig el ai., 1989] [Cline et al., 1990] [Vannier et al., 1985] , sometimes in conjunction with morphological image processing operations. Intensity-based classification of MR images has proven problematic, however, even when advanced techniques such as non-parametric multi-channel methods are used, primarily due to spatial intensity inhomogeneities that are due to the equipment. When differentiating between white matter and gray matter in the brain, the spatial intensity inhomogeneities are often of sufficient magnitude to cause the distributions of intensities associated with these two tissue classes to overlap, thereby defeating intensity-based classification. This paper describes a statistical method that uses knowledge of tissue properties and intensity inhomogeneities to correct in-vivo MR images. The result is a method that allows for more accurate segmentation of tissue types as well as better visualization of MRI data.