3D Fast Automatic Segmentation of Kidney Based on Modified AAM and Random Forest
J. Chao, F. Shi, D. Xiang, X. Jiang, B. Zhang, X. Wang, W. Zhu, E. Gao, X. Chen
IEEE Trans Med Imaging, vol. 35, issue 6, January 2016
In this paper, a fully automatic method is proposed to segment the kidney into multiple components: renal cortex, renal column, renal medulla and renal pelvis, in clinical 3D CT abdominal images. This is the first framework which can segment kidney into four components. The proposed fast automatic segmentation method of kidney consists of two main parts: localization of renal cortex and segmentation of kidney components. In the localization of renal cortex phase, a method which fully combines 3D Generalized Hough Transform (GHT) and 3D Active Appearance Models (AAM) is applied to localize the renal. In the segmentation of kidney components phase, an improved Random Forests (RF) method is proposed to segment the kidney into four components based on the result from localization phase accurately and efficiently, where both 2D and 3D features are utilized.
During the implementation, a multithreading technology is applied to speed up the segmentation process. The proposed method was evaluated on a clinical abdomen CT data set, including 37 contrast-enhanced volume data. The overall true-positive volume fraction and false-positive volume fraction were 93.15%, 0.37% for renal cortex segmentation; 83.09%, 0.97% for renal column segmentation; 81.92%, 0.55% for renal medulla segmentation; and 80.28%, 0.30% for renal pelvis segmentation, respectively. The proposed method is highly efficient which can segment kidney into four components within only 20 seconds. In experiment part of this paper, we also analyzed the volume change of kidney components after surgery based on the proposed method.