The use of statistical shape models is a promising approach for robust segmentation of medical images. One of the major challenges in building a 3D shape model from a training set of segmented instances of an object is the determination of the correspondence between them. We propose a novel geometric approach that is based on minimizing the distortion of the mapping between two surfaces. In this work we investigate the accuracy and completeness of a 3D statistical shape model for the liver built from 20 manually segmented individual CT data sets. The quality of the shape model is crucial for its application as a segmentation tool.