In MR brain images, segmentation using intensity values is severely limited owing to field inhomogeneities, susceptibility artifacts and partial volume effects. Edge based segmentation methods suffer from spurious edges and gaps in boundaries. A method is presented which combines the advantages of edge based and region based segmentation. First a multiscale image representation, is constructed which favors intratissue diffusion over inter-tissue diffusion by exploiting local contrast. Subsequently a multiscale linking model (the hyperstack) is used to group voxels into a number of segments. This facilitates segmentation of grey matter, white matter and cerebrospinal fluid with minimal user interaction. Using a supervised segmentation, technique and MR simulations of a brain phantom as validation it is shown that the errors are in the order of or smaller than reported in literature.
Three-dimensional MR brain segmentation
1998-01-01
824657 byte
Conference paper
Electronic Resource
English
Three Dimensional MR Brain Segmentation
British Library Conference Proceedings | 1998
|Multiscale Segmentation of Three-Dimensional MR Brain Images
British Library Online Contents | 1999
|Three dimensional segmentation of volume data
IEEE | 1994
|Three Dimensional Segmentation of Volume Data
British Library Conference Proceedings | 1994
|Volumetric Segmentation of Medical Images by Three-Dimensional Bubbles
British Library Conference Proceedings | 1995
|