Renal cortex localization by combining 3D Generalized Hough Transform and 3D Active Appearance Models

Abstract

Automatic localization is one of important steps in medical image segmentation. In this paper, a model-based method for three-dimensional image localization is developed. Our method is based on a combination of 3D Generalized Hough Transform and 3D Active Appearance Models. It consists of two main parts: training and localization. The proposed method was tested on a clinical abdomen CT data set, including 27 contrast-enhanced volume data, in which 15 were chose as training data while the other 12 as testing data. The experimental results show that: (1) an overall cortex localization average distance is 12.58±3.26 voxels. (2) The proposed method is highly efficient, the running time is about only 35.70±3.62 seconds for each volume data.