作者: J.W. Snell , M.B. Merickel , J.M. Ortega , J.C. Goble , J.R. Brookeman
DOI: 10.1016/0031-3203(95)00021-Q
关键词:
摘要: A method for the segmentation of complex, three-dimensional objects using hierarchical active surface templates is presented. The consist one or more models which are specified according to a priori knowledge about expected shape and location desired object. This allows complex be naturally modeled as collections simple subparts geometrically constrained. template adaptively deformed by image data in it initialized such that boundaries brought into correspondence with assumed An external energy field developed based on vector distance transform surfaces object shape. demonstrated human brain from magnetic resonance images head given an model normal brain.