Multi-resolution Statistical Shape Models for Multi-organ Shape Modelling

Abstract

Statistical shape models (SSMs) are widely used in medical image segmentation. However, traditional SSM methods suffer from the High-Dimension-Low-Sample-Size (HDLSS) problem in modelling. In this work, we extend the state-of-the-art multi-resolution SSM approach from two dimension (2D) to three dimension (3D) and from single organ to multiple organs. Then we proposed a multi-resolution multi-organ 3D SSM method that uses a downsampling-and-interpolation strategy to overcome HDLSS problem. We also use an inter-surface-point distance thresholding scheme to achieve multi-resolution modelling effect. Our method is tested on the modelling of multiple mouse abdominal organs from mouse micro-CT images in three different resolution levels, including global level, single organ level and local organ level. The minimum specificity error and generalization error of this method are less than 0.3 mm, which are close to the pixel resolution of mouse micro-CT images (0.2 mm) and better than the modelling results of traditional principal component analysis (PCA) method.