A Kidney Segmentation Framework for Dynamic Contrast Enhanced Magnetic Resonance Imaging

Abstract

In the United States, more than 12000 renal transplantations are performed annually; but the transplanted kidneys face a number of surgical and medical complications that cause a decrease in their functionality. In an effort to understand the reasons for this functionality decrease, considerable attention has recently been focused on Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) due to its superior functional and anatomical information. The biggest challenge in the analysis of DCE-MRI is the segmentation of kidneys from abdomen images because of the high noise and partial volume effects introduced during the rapid and repeated scanning process. In this paper, a general framework is introduced for the segmentation of kidneys from DCE-MR images of the abdomen. The proposed segmentation algorithm consists of three main steps. In the first step, an average kidney shape is constructed from a dataset of previously segmented kidneys, and an average signed distance map density is obtained describing the shape of the kidneys. In the second step, the gray level density is calculated for a given new kidney image using a modified expectation maximization (EM) algorithm. In the third step, a deformable model is evolved based on the two density functions obtained from the previous two steps: the first one describes the prior shape of the kidney, and the second one describes the distribution of the gray level inside and outside the kidney region. The new deformable model is able to handle intricate shapes without getting stuck in edge points; and gives very promising results that are comparable to radiologists' segmentation.

Keywords

Dynamic Contrast Enhanced MRI Gd-DTPA acute rejection renal transplantation deformable models segmentation shape database

Get full access to this article

View all access options for this article.

References

Boykov, Y. , Lee, V.S. , Rusinek, H. , and Bansal, R. , 2001, “Segmentation of dynamic N-D data sets via graph cuts using Markov models,” in Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Utrecht, The Netherlands, October 14—17, pp. 1058—1066.

El-Baz, A. , Yuksel, S.E. , Shi, H. , Farag, A.A. , El-Ghar, M.A. , Eldiasty, T. , and Ghoneim, M.A. , 2005, “2D and 3D shape based segmentation using deformable models,” in Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) , Palm Springs, CA, October 26—29, pp. 821—829.

Farag, A.A. , El-Baz, A. , and Gimel'farb, G. , 2004, “Density estimation using modified expectationmaximization for a linear combination of Gaussians,” in Proceedings of IEEE International Conference on Image Processing, Saint-Malo, France, September 26—29, Vol. 3, pp.1871—1874.

Farag, A.A. , El-Baz, A. , and Gimel'farb, G. , 2006, “Precise segmentation of multi-modal images, ” IEEE Transactions on Image Processing 15(4), 952—968.

Farag, A.A. , El-Baz, A. , Yuksel, S.E. , El-Ghar, M.E.A. , Eldiasty, T.A. , and Ghoneim, M.A. , 2006, “A framework for the detection of acute rejection with dynamic contrast enhanced magnetic resonance imaging,” in IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI), Arlington, VA, April 6—9, pp. 418—421.

Gerig, G. , Kikinis, R. , Kuoni, W. , van Schulthess, G.K. , and Kubler, O. , 1992, “Semiautomated ROI analysis in dynamic MRI studies: Part I: Image analysis tools for automatic correction of organ displacements ,” IEEE Transactions on Image Processing 11(2), 221—232.

Giele, E.L.W. , 2002, Computer methods for semi-automatic MR renogram determination. PhD thesis, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.

El-Baz, A. , Rachid, F. , Yuksel, S.E. , Farag, A.A. , Miller, W. , El-Ghar, M.A. , and Eldiasty, T. , 2006, “A new CAD system for the evaluation of kidney diseases using DCE-MRI,” in Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) , Singapore, October 24—27, pp. 446—453.

Rigg, K.M. , 1995, “ Renal transplantation: current status, complications and prevention,” Journal of Antimicrobial Chemotherapy 36, Suppl:B51—B57.

10.

Schlesinger, M.I. and Hlavac, V. , 2002, Ten Lectures on Statistical and Structural Pattern Recognition , Kluwer Academic, Norwell, MA.

11.

Sun, Y. , Jolly, M. , and Moura, J.M.F. , 2004, “Integrated registration of dynamic renal perfusion MR images,” in Proceedings of 2004 IEEE International Conference on Image Processing, Copenhagen, Denmark, October 1—6, pp. 1923—1926.

12.

Tsai, A. , Yezzi, A. , Wells, W. , Tempany, C. , Tucker, D. , Fan, A. , Grimson, E. , and Willsky, A. , 2003, “A shapebased approach to curve evolution for segmentation of medical imagery,” IEEE Transactions on Medical Imaging 22(2), 137—154.

13.

Witkin, A. , Kass, M. , and Terzopoulos, D. , 1987, “Snakes: Active contour models,” International Journal of Computer Vision 1, 321—331.

14.

Yang, D. , Ye, Q. , Williams, M. , Sun, Y. , Hu, T.C.C. , Williams, D.S. , Moura, J.M.F. , and Ho, C. , 2001, “USPIO enhanced dynamic MRI: Evaluation of normal and transplanted rat kidneys,” Magnetic Resonance in Medicine 46, 1152—1163.

15.

Yuksel, S.E. , 2005, Image processing methods for the detection of acute rejection after kidney transplantation. MS thesis, Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY, December.

16.

Yuksel, S.E. , El-Baz, A. , Farag, A.A. , El-Ghar, M.E.A. , Eldiasty, T.A. , and Ghoneim, M.A. , 2005, “Automatic detection of renal rejection after kidney transplantation,” in Proceedings of Computer Assisted Radiology and Surgery (CARS), Berlin, Germany, June 22—25, pp. 773—778, June.