Optimized MR image segmentation for tissue characterization
Hong Yan, John C. Gore · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · 1988
A novel MR (magnetic resonance) image segmentation algorithm has been implanted for tissue classification. The original image is first split into two subimages to minimize a specified cost function. Each image is then split into two smaller subimages and this procedure is repeated for several levels. Finally subimages are merged into desired number of groups according to a measure of the distance between subimages.>