Automatic Segmentation of the Prostate from Ultrasound Data Using Feature-Based Self Organizing Map

  • Amjad Zaim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


Traditional segmentation methods cannot provide satisfying results for extraction of prostate gland from Transrectal Ultrasound (TRUS) images because of the presence of strong speckle noise and shadow artifacts. Most ultrasound image segmentation techniques that adopt model-based approach such as active contour are considered semi-automatic because they require initial seeds or contours to be manually identified. In this paper, we propose a method for automatic segmentation of prostate using feature-based self organizing map (SOM). Median filtering and top hat transform are first applied to remove speckle noise. A technique is developed to remove ultrasound-specific speckles using texture-based thresholding. An SOM algorithm is employed to identify prostate pixels taking spatial information, gray-level as well as texture information to form its input vector. The clustered image is then processed to produce a fully connected prostate contour. A number of experiments comparing extracted contours with manually-delineated contours validated the performance of our method.


Automatic Segmentation Reference Vector Ultrasound Data Input Data Vector Minimal Human Intervention 
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.


  1. 1.
    Zaim, A., Keck, R., Selman, S., Jankun, J.: Three-Dimensional Ultrasound Image Matching System for Photodynamic Therapy. In: Proceedings of BIOS-SPIE, vol. 4244, pp. 327–337 (2001)Google Scholar
  2. 2.
    Jankun, J., Zaim, A.: An image-guided robotic System for photodynamic Therapy of the Prostate. SPIE Proceeding 39, 22–22 (1999)Google Scholar
  3. 3.
    Ghanei, A., Soltanian-Zadeh, H., Ratkesicz, A., Yin, F.: A three-dimensional deformable model for segmentation of human prostate from ultrasound image. Medical Physics 28, 2147–2153 (2001)CrossRefGoogle Scholar
  4. 4.
    Hu, N., Downey, D., Fenster, A., Ladak, H.: Prostate surface segmentation from 3D ultra-sound images. In: IEEE International Symposium on Biomedical Imaging, Washington, D. C, pp. 613–616 (2002)Google Scholar
  5. 5.
    Pathak, S., Chalana, V., Haynor, D., Kim, Y.: Edge-Guided Boundary Delineation in Protate Ultrasound Images. IEEE Trans. Med. Img. 19, 1211–1219 (2000)CrossRefGoogle Scholar
  6. 6.
    Shen, D., Zhan, Y., Davatzikos, C.: Segmentation Prostate Boundaries from Ultrasound Images Using Statistical Shape Model. IEEE Trans. On Med. Img. 22, 539–551 (2003)CrossRefGoogle Scholar
  7. 7.
    Aarnink, R., Huyanen, A., Giesen, J., De la Rosette, D., Debruyne, F., Wijkstra, H.: Auto-mated prostate volume determination with ultrasonographic imaging. Journal of Urology 155, 1038–1039 (1996)CrossRefGoogle Scholar
  8. 8.
    Castleman, R.: Digital Image Processing. Upper Saddle River/Prentice-Hall, New Jersey/Englewood Cliffs (1996)Google Scholar
  9. 9.
    Niblack, W.: An Introduction to Digital Image Processing. Upper Saddle River/Prentice-Hall, Massachusetts/New Jersey (1996)Google Scholar
  10. 10.
    Gonzalez, R.: Digital Image Processing. Addison-Wisely, Massachusetts (1996)Google Scholar
  11. 11.
    Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (2001)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Amjad Zaim
    • 1
  1. 1.Biomedical Engineering DepartmentAmman UniversityAmmanJordan

Personalised recommendations