Automatic Kidney Segmentation Using Gaussian Mixture Model on MRI Sequences

  • Evgin Goceri
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 99)


Robust kidney segmentation from MR images is a very difficult task due to the especially gray level similarity of adjacent organs, partial volume effects and injection of contrast media. In addition to different image characteristics with different MR scanners, the variations of the kidney shapes, gray levels and positions make the identification and segmentation task even harder. In this paper, we propose an automatic kidney segmentation approach using Gaussian mixture model (GMM) that adapts all parameters according to each MR image dataset to handle all these challenging problems. The efficiency in terms of the segmentation performance is achieved by the estimation of the GMM parameters using the Expectation Maximization (EM) method. The segmentation approach is compared to k-means method. The results show that the model based probabilistic segmentation technique gives better performance for both low contrast images and atypical kidney shapes where several algorithms fail on abdominal MR images.


Kidney segmentation MRI Gaussian mixture model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kobashi, L., Shapiro, M.: Knowledge-based Organ Identification from CT Images. Pattern Recognition 28, 475–491 (1995)CrossRefGoogle Scholar
  2. 2.
    Lin, D.T., Lei, C.C., Hsiung, S.Y.: An Efficient Method for Kidney Segmentation on Abdominal CT Images. In: 8th Australian and New Zealand Intelligent Information Systems Conference, Sydney, Australia, pp. 75–82 (2003)Google Scholar
  3. 3.
    Pohle, R., Tönnies, K.D.: A New Approach for Model-Based Adaptive Region Growing in Medical Image Analysis. In: Skarbek, W. (ed.) CAIP 2001. LNCS, vol. 2124, pp. 238–246. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  4. 4.
    Pohle, R., Toennies, K.D.: Segmentation of Medical Images Using Adaptive Region Growing. In: Proceedings of the Medical Imaging Conference of SPIE, vol. 4322, pp. 1337–1346 (2001)Google Scholar
  5. 5.
    Pohle, R., Toennies, K.D.: Self-learning Model-based Segmentation of Medical Images. Image Processing & Communication 7, 97–113 (2001)Google Scholar
  6. 6.
    Yan, G., Wang, B.: An Automatic Kidney Segmentation from Abdominal CT Images. In: International Conference on Intelligent Computing and Intelligent Systems (ICIS), pp. 280–284. IEEE Press, Xiamen (2010)CrossRefGoogle Scholar
  7. 7.
    Spiegel, M., Hahn, D.A., Daum, V., Wasza, J., Hornegger, J.: Segmentation of Kidneys Using a New Active Shape Model Generation Technique Based on Non-rigid Image Registration. Computerized Medical Imaging and Graphics 33, 29–39 (2009)CrossRefGoogle Scholar
  8. 8.
    Huang, C.L., Kuo, L.Y., Huang, Y.J., Lin, Y.H.: Shape-based Level Set Method for Kidney Segmentation on CT Image. In: 22nd Conference on Computer Vision, Nantou, Taiwan (2009)Google Scholar
  9. 9.
    Tsagaan, B., Shimizu, A., Kobatake, H., Kunihisa, M., Hanzawa, Y.: Segmentation of Kidney by Using a Deformable Model. In: International Conference on Image Processing (ICIP), pp. 1059–1062. IEEE Press, Thessaloniki (2001)Google Scholar
  10. 10.
    Tsagaan, B., Shimizu, A., Kobatake, H., Miyakawa, K.: An automated segmentation method of kidney using statistical information. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2488, pp. 556–563. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Tang, Y., Jackson, H., Lee, S., Nelson, M., Moats, R.A.: Shape-aided Kidney Extraction in MR Urography. In: 31st Annual International Conference on Engineering in Medicine and Biology Society (EMBS), pp. 5781–5784. IEEE Press, Minneapolis (2009)Google Scholar
  12. 12.
    Shental, N., Bar-Hillel, A., Hertz, T., Weinshall, D.: Computing Gaussian Mixture Models with EM Using Equivalence Constraints. In: Advances in Neural Information Processing System, vol. 15, pp. 465–473 (2003)Google Scholar
  13. 13.
    Dempster, A., Laird, N., Rubin, D.: Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society 39, 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  14. 14.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley and Sons Inc., New York (2000)Google Scholar
  15. 15.
    Abdelmunim, H., Farag, A.A., Miller, W., AbdelGhar, M.: A Kidney Segmentation Approach from DCE-MRI Using Level Sets. In: Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1–6. IEEE Press, Anchorage (2008)CrossRefGoogle Scholar
  16. 16.
    Blum, H.A.: Transformation for Extracting New Descriptors of Shapes. In: Wathen-Dunn, W. (ed.) Models for the Perception of Speech and Visual Form, pp. 362–380. MIT Press, Cambridge (1967)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Evgin Goceri
    • 1
  1. 1.Department of Computer Engineering, Faculty of EngineeringPamukkale UniversityDenizliTurkey

Personalised recommendations