Fast Renal Cortex Localization by Combining Generalized Hough Transform and Active Appearance Models

Automatic localization of objects is one of great important steps in object recognition and analysis, such as segmentation, registration in many medical applications. In this paper, an automated method is proposed to recognize renal cortex on contrast-enhanced abdominal CT images. The proposed method is based on a strategic combination of the Generalized Hough Transform and Active Appearance Model. It consists of two main phases: training and localization. In the training phase, we train the mean shape models of renal cortex by using Active Appearance Model and compute Generalized Hough Transform parameters. In the localization phase, a modified Generalized Hough Transform algorithm is advanced to estimate potential center of gravity for improving the conventional Active Appearance Model matching method, and then a two-pass Active Appearance Model matching method is proposed based on Generalized Hough Transform. The Active Appearance Models and Generalized Hough Transform parameters were trained with 20 CT angiography datasets, and then the proposed method was tested on a clinical data set of 17 CT angiography datasets. The experimental results show that: 1 an overall cortex localization accuracy is 0.9920±0.0038, average distance is 11.00±9.34 pixels. 2 The proposed method is highly efficient such that the overall localization can be finalized within 1.2075±0.3738 seconds for each 2D slice.

[1]  Timothy F. Cootes,et al.  A minimum description length approach to statistical shape modeling , 2002, IEEE Transactions on Medical Imaging.

[2]  Wiro J. Niessen,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2001 , 2001, Lecture Notes in Computer Science.

[3]  José M. F. Moura,et al.  Integrated registration of dynamic renal perfusion MR images , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[4]  W. Rathmell,et al.  Renal cell carcinoma , 2007, Current opinion in oncology.

[5]  Bjarne K. Ersbøll,et al.  FAME-a flexible appearance modeling environment , 2003, IEEE Transactions on Medical Imaging.

[6]  Xinjian Chen,et al.  Medical Image Segmentation by Combining Graph Cuts and Oriented Active Appearance Models , 2012, IEEE Transactions on Image Processing.

[7]  Alejandro F. Frangi,et al.  Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling , 2002, IEEE Transactions on Medical Imaging.

[8]  Lixu Gu,et al.  Recognition of abdominal organs using 3D mathematical morphology , 2002, Systems and Computers in Japan.

[9]  Xinjian Chen,et al.  An automatic method for renal cortex segmentation on CT images: evaluation on kidney donors. , 2012, Academic radiology.

[10]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[11]  Hyunjin Park,et al.  Construction of an abdominal probabilistic atlas and its application in segmentation , 2003, IEEE Transactions on Medical Imaging.

[12]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[13]  L. Ruskó,et al.  Fully automatic liver segmentation for contrast-enhanced CT images , 2007 .

[14]  Kourosh Khoshelham,et al.  Extending generalized hough transform to detect 3D objects in laser range data , 2007 .

[15]  Ravi Bansal,et al.  Segmentation of Dynamic N-D Data Sets via Graph Cuts Using Markov Models , 2001, MICCAI.

[16]  Ashraf A. Kassim,et al.  Segmentation of kidney cortex in MRI studies: a constrained morphological 3D h-maxima transform approach , 2009, Int. J. Medical Eng. Informatics.

[17]  Arvid Lundervold,et al.  ssessment of 3 D DCE-MRI of the kidneys using non-rigid image registration nd segmentation of voxel time courses rank , 2009 .