Simultaneous extraction of multiple organs from abdominal CT

We propose a simultaneous extraction method for 12 organs from threedimensional abdominal CT images. The method uses an abdominal cavity standardization process and atlas guided segmentation incorporating parameter estimation with the EM algorithm, and thus can deal with the large fluctuations in the feature distribution parameters between subjects. Segmentation is then performed using multiple level sets, which minimizes the energy function that takes into account hierarchy and exclusiveness between organs as well as uniformity of grey values in organs. The level set method is implemented in a clustered computer environment using MPI (Message Passing Interface) to reduce the computational cost. We present here the experimental results of applying this algorithm to actual non-contrast 3D CT images and discuss the effectiveness of the method.