Heart Cavity Detection in Ultrasound Images with SOM

  • Mary Carmen Jarur
  • Marco Mora
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4293)


Ultrasound images are characterized by high level of speckle noise causing undefined contours and difficulties during the segmentation process. This paper presents a novel method to detect heart cavities in ultrasound images. The method is based on a Self Organizing Map and the use of the variance of images. Successful application of our approach to detect heart cavities on real images is presented.


IEEE Transaction Image Segmentation Ultrasound Image Active Contour Synthetic Aperture Radar 
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.
    Dong, G., Xie, M.: Color Clustering and Learning form Image Segmentation Based on Neural Networks. IEEE Transactions on Neural Networks 16(4), 925–936 (2005)CrossRefGoogle Scholar
  2. 2.
    Frost, V., Stiles, J., Shanmugan, K., Holtzman, J.: A model for radar images and its application to adaptive digital filtering of multiplicative noise. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-4, 157–166 (1982)CrossRefGoogle Scholar
  3. 3.
    Gonzalez, R., Woods, R.: Digital Images Processing. Addison-Wesley, Reading (1992)Google Scholar
  4. 4.
    Jiang, Y., Chen, K., Zhou, Z.: SOM Based Image Segmentation. In: Wang, G., Liu, Q., Yao, Y., Skowron, A. (eds.) RSFDGrC 2003. LNCS (LNAI), vol. 2639, pp. 640–643. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  5. 5.
    Kohonen, T.: Self-Organizing Maps. Springer, Berlin (2001)MATHGoogle Scholar
  6. 6.
    Kuan, D., Sawchuk, A., Strand, T., Chavel, P.: Adaptive restoration of images with speckle. IEEE Transaction on Acoustics, Speech and Signal Processing 35, 373–383 (1987)CrossRefGoogle Scholar
  7. 7.
    Lee, J.: Digital image enhancement and noise filtering by using local statistic. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-2, 165–168 (1980)CrossRefGoogle Scholar
  8. 8.
    Levienaise-Obadia, B., Gee, A.: Adaptive Segmentation of Ultrasound Images. In: Electronic Proceedings of the Eight British Machine Vision Conference (BMVC) (1997)Google Scholar
  9. 9.
    Littmann, E., Ritter, H.: Adaptive Color Segmentation: A Comparison of Neural Networks and Statistical Methods. IEEE Transactions on Neural Networks 8(1), 175–185 (1997)CrossRefGoogle Scholar
  10. 10.
    Lopes, A., Touzi, R., Nezry, E.: Adaptive speckle filters and scene heterogeneity. IEEE Transactions on Geoscience and Remote Sensing 28(6), 992–1000 (1990)CrossRefGoogle Scholar
  11. 11.
    Moreira, J., Costa, L.: Neural-based color image segmentation and classification using self-organizing maps. In: Proceedings of the IX Brazilian Symposium of Computer Vision and Image Processing (SIBGRAPI 1996), pp. 47–54 (1996)Google Scholar
  12. 12.
    Tauber, C., Batatia, H., Ayache, A.: A Robust Speckle Reducing Anisotropic Diffusion. In: IEEE International Conference on Image Processing (ICIP), pp. 247–250 (2004)Google Scholar
  13. 13.
    Tauber, C., Batatia, H., Morin, G., Ayache, A.: Robust B-Spline Snakes for Ultrasound Images Segmentation. In: Proceedings of IEEE Computers in Cardiology (2004)Google Scholar
  14. 14.
    Yu, Y., Acton, S.: Edge detection in ultrasound imagery using the instantaneous coefficient of variation. IEEE Transaction on Image Processing 13(12), 1640–1655 (2004)CrossRefGoogle Scholar
  15. 15.
    Yu, Y., Acton, S.: Speckle Reducing Anisotropic Diffusion. IEEE Transaction on Image Processing 11(11) (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mary Carmen Jarur
    • 1
  • Marco Mora
    • 1
    • 2
  1. 1.Department of Computer ScienceCatholic University of MauleTalcaChile
  2. 2.IRIT-ENSEEIHTToulouseFrance

Personalised recommendations