Automated 3D PDM Construction Using Deformable Models

In recent years several methods have been proposed for constructing statistical shape models to aid image analysis tasks by providing a-priori knowledge. Examples include principal component analysis (PCA) of manually or semi-automatically placed corresponding landmarks on the learning shapes (point distribution models, PDM), which is time consuming and subjective. However, automatically establishing surface correspondences continues to be a difficult problem. This paper presents a novel method for the automated construction of 3D PDM from segmented images. Corresponding surface landmarks are established by adapting a triangulated learning shape to segmented volumetric images of the remaining shapes. The adaptation is based on a novel deformable model technique. We illustrate our approach using CT data of the vertebra and the femur. We demonstrate that our method accurately represents and predicts shapes.