Application of Statistical Shape Model of the Liver in Classification of Cirrhosis

In computational anatomy, statistical shape model is used for quantitative evaluation of the variations of an organ shape. In this paper, we focus our researches on construction of Statistical Shape Model of the liver and its application to computer aided diagnosis of cirrhosis. We have proved the potential application of statistical shape models in classification of normal and cirrhosis livers. We first construct a statistical shape model of the liver from a training set (either different individuals (inter-patient variability) or the same individual (intra-patient variability)) and then coefficients of the model are used as features to recognize whether liver is normal or abnormal. The effectiveness of the constructed model is evaluated by the classification accuracy of normal and abnormal.