This project aims at overcoming this deficit by providing a planning system for liver interventions. A major contribution of this work will be the automatic detection and segmentation of liver lesions in CT images. To ensure a robust segmentation even for difficult tumors, information from various sources, such as CT images of different phases of contrast enhancement in the liver, will be incorporated into the process.

An automatic characterization of the found lesions and analysis of their position relative to important anatomical structures like vessels or liver segments provides additional information, that can not only be visualized in 3-D for surgeons to get a better orientation. It can also be used to simulate entire interventions.

Additionally, with the segmentation available, inoperable tumors or those treated without excision can be monitored over a longer period of time in order to allow an assessment of tumor growth or shrinkage and thus the success of the treatment.