Subject e.g. patient head, three-dimensional digital image data`s target structures segmenting method for medical imaging application, involves segmenting structure based on optimal sequence and limiting segmenting area to segment structure

摘要

The method involves providing pre-segmented training images of structures that represent target structures, and modeling inner structural spatial dependencies for each structure of training images. The dependencies are integrated into a segmenting algorithm, in which anchor structures of three-dimensional image data are registered in reference anchor structures. An optimal sequence for segmenting the structures is determined, and each structure is segmented based on the sequence. A segmenting area for each structure in the sequence is limited for segmenting the structures. Independent claims are also included for the following: (1) a machine-readable program memory device with a program medium for implementing the method for segmenting a number of target structures in three-dimensional image data (2) a system for segmenting a number of target structures in three-dimensional image data.