Discriminant Analysis Based Level Set Segmentation for Ultrasound Imaging

  • Daniel Tenbrinck
  • Xiaoyi Jiang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8048)


Segmentation is one of the fundamental tasks in computer vision applications. The nature of ultrasound images, which are subject to multiplicative noise instead of the widely used additive noise modeling, leads to problems of standard segmentation algorithms. In this paper we propose a new level set approach for the segmentation of medical ultrasound data. The advantage of this approach is both its simpleness and robustness: the noise inherent in ultrasound images does not have to be modeled explicitly but is rather estimated by means of discriminant analysis. In particular, we determine an optimal threshold, which enables us to separate two signal distributions in the intensity histogram and incorporate this information in the evolution of the level set contour. The superiority of our approach over the popular Chan-Vese formulation is demonstrated on real 2D patient data from echocardiography.


Optimal Threshold Multiplicative Noise Speckle Noise Signed Distance Function Segmentation Contour 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chan, T.F., Vese, L.A.: Active Contours Without Edges. IEEE-TIP 10(2), 266–277 (2001)zbMATHGoogle Scholar
  2. 2.
    Chan, T.F., Vese, L.A.: A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model. IJCV 50(3), 271–293 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Ma, M., et al.: Model Driven Quantification of Left Ventricular Function from Sparse Single-Beat 3D Echocardiography. Med. Img. Anal. 14, 582–593 (2010)CrossRefGoogle Scholar
  4. 4.
    Noble, J.A., Boukerroui, D.: Ultrasound Image Segmentation: A Survey. IEEE-TMI 25(8), 987–1010 (2006)Google Scholar
  5. 5.
    Osher, S., Fedkiw, R.P.: Level Set Methods and Dynamic Implicit Surfaces. Springer, New York (2003)zbMATHGoogle Scholar
  6. 6.
    Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE-TSMC 9(1), 62–66 (1979)MathSciNetGoogle Scholar
  7. 7.
    Sawatzky, A., Tenbrinck, D., Jiang, X., Burger, M.: A Variational Framework for Region-Based Segmentation Incorporating Physical Noise Models. J. Math. Imaging and Vision (2013), doi:10.1007/s10851-013-0419-6Google Scholar
  8. 8.
    Tenbrinck, D., Sawatzky, A., Jiang, X., Burger, M., Haffner, W., Willems, P., Paul, M., Stypmann, J.: Impact of Physical Noise Modeling on Image Segmentation in Echocardiography. Eurographics Workshop on Vis. Comp. for Bio. and Med., 33–40 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Daniel Tenbrinck
    • 1
    • 2
  • Xiaoyi Jiang
    • 1
    • 2
    • 3
  1. 1.Department of Mathematics and Computer ScienceUniversity of MünsterGermany
  2. 2.European Institute for Molecular ImagingUniversity of MünsterGermany
  3. 3.Cluster of Excellence EXC 1003Cells in Motion, CiMMünsterGermany

Personalised recommendations