Dual-Energy CT (DECT) uses two different x-ray spectra simultaneously. This technique enables decomposition of images into the underlying materials by detecting the different attenuation of materials at different x-ray spectra. Thus, the diagnostic significance of DECT is improved compared to single-energy CT. So far, the method of material decomposition is only efficient for certain organs and works only with organ-specific parameters. The organ-specific parameters have to be given manually by the user. And the parameters should be patient-specific. This project aims at decomposing the materials with anatomy knowledge automatically. An atlas provides the prior knowledge - the anatomic structures. The anatomy knowledge allows then automatic decomposition and classification of the different materials. This project is in cooperation with the German Cancer Research Center (DKFZ) Heidelberg and the University Hospital Erlangen.