3D Liver Volume Morphing and Statistical Modeling Using Generalized N-Dimensional Principal Component Analysis Method

摘要

In this paper, we propose a statistical texture modeling method for medical volumes. In order to deal with the problems of high-dimension and Small number of medial samples, we propose an effective image compression method named Generalized N-dimensional Principal Component Analysis (GND-PCA) to construct a statistical model. As the shapes of the human organ are very different from one case to another, we apply 3D volume morphing to normalize all the volume datasets to a same shape for removing shape variations. Then, we use GND-PCA method to get features, which just contain the information of texture. Experiments applied on liver volumes show good property of generalization using our method. We also did a simple experiment to show that the features extracted by our models have capability of discrimination for different types of data, such as normal and abnormal.