INTENSITY-ADAPTIVE SEGMENTATION OF SINGLE-ECHO T-1-WEIGHTED MAGNETIC-RESONANCE IMAGES

A procedure for segmentation of intracranial tissues, including cerebr ospinal fluid surrounding the brain, cortical and subcortical gray mat ter, and white matter, in a T-1-weighted magnetic resonance image of t he brain, has been developed. The proposed method utilizes information from the histogram of pixel intensities of the intracranial image. Ba sed on this information, an unsupervised K-means clustering procedure separates various tissue regions. Information about the approximate lo cation of anatomical regions within the intracranial space is used to detect ventricles and the caudate nuclei. First a description and just ification for tile procedure is presented. Then the performance of the procedure is evaluated by analysis of variance. In conclusion, the re sults of applying this procedure to 31 healthy subjects are presented and future improvements are discussed. (C) 1997 Wiley-Liss, Inc.