Unsupervised Detection of Mammogram Regions of Interest

  • Michal Haindl
  • Stanislav Mikeš
  • Giuseppe Scarpa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4694)


We present an unsupervised method for fully automatic detection of regions of interest containing fibroglandular tissue in digital screening mammography. The unsupervised segmenter is based on a combination of several unsupervised segmentation results, each in different resolution, using the sum rule. The mammogram tissue textures are locally represented by four causal monospectral random field models recursively evaluated for each pixel. The single-resolution segmentation part of the algorithm is based on the underlying Gaussian mixture model and starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous mammogram segments is reached. The performance of the presented method is extensively tested on the Digital Database for Screening Mammography (DDSM) from the University of South Florida as well as on the Prague Texture Segmentation Benchmark using the commonest segmentation criteria and where it compares favourably with several alternative texture segmentation methods.


Unsupervised segmentation mammography Markov random fields 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tweed, T., Miguet, S.: Automatic detection of regions of interest in mammographies based on a combined analysis of texture and histogram. ICPR 2, 448–452 (2002)Google Scholar
  2. 2.
    Qi, H., Diakides, N.A.: Thermal infrared imaging in early breast cancer detection - a survey of recent research. In: 25th Annual Int. Conference of the IEEE EMBS, pp. 448–452. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  3. 3.
    Kashyap, R.: Image models. In: Young, T.Y. (ed.) Handbook of Pattern Recognition and Image Processing, Academic Press, New York (1986)Google Scholar
  4. 4.
    Reed, T.R., du Buf, J.M.H.: A review of recent texture segmentation and feature extraction techniques. CVGIP–Image Understanding 57, 359–372 (1993)CrossRefGoogle Scholar
  5. 5.
    Haindl, M.: Texture synthesis. CWI Quarterly 4, 305–331 (1991)zbMATHGoogle Scholar
  6. 6.
    Panjwani, D., Healey, G.: Markov random field models for unsupervised segmentation of textured color images. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 939–954 (1995)CrossRefGoogle Scholar
  7. 7.
    Manjunath, B., Chellapa, R.: Unsupervised texture segmentation using markov random field models. IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 478–482 (1991)CrossRefGoogle Scholar
  8. 8.
    Andrey, P., Tarroux, P.: Unsupervised segmentation of markov random field modeled textured images using selectionist relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 252–262 (1998)CrossRefGoogle Scholar
  9. 9.
    Haindl, M.: Texture segmentation using recursive markov random field parameter estimation. In: Bjarne, K., Peter, J., (eds.) Proceedings of the 11th Scandinavian Conference on Image Analysis, Lyngby, Denmark, Pattern Recognition Society of Denmark, pp. 771–776 (1999)Google Scholar
  10. 10.
    Haindl, M., Mikeš, S.: Model-based texture segmentation. In: Campilho, A., Kamel, M. (eds.) ICIAR 2004. LNCS, vol. 3212, pp. 306–313. Springer, Heidelberg (2004)Google Scholar
  11. 11.
    Haindl, M., Šimberová, S.: A Multispectral Image Line Reconstruction Method. In: Theory & Applications of Image Analysis, pp. 306–315. World Scientific Publishing Co. Singapore (1992)Google Scholar
  12. 12.
    Kittler, J., Hojjatoleslami, A., Windeatt, T.: Weighting factors in multiple expert fusion. In: Proc. BMVC, BMVA, BMVA, pp. 41–50 (1997)Google Scholar
  13. 13.
    Haindl, M., Mikeš, S.: Unsupervised texture segmentation using multiple segmenters strategy. In: LNCS, vol. 4472, 2007 (accepted)Google Scholar
  14. 14.
    Heath, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, P.: The digital database for screening mammography. In: Proc. of the 5th Int. Workshop on Digital Mammography, Medical Physics Publishing (2000)Google Scholar
  15. 15.
    Deng, Y., Manjunath, B.: Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 800–810 (2001)CrossRefGoogle Scholar
  16. 16.
    Carson, C., Thomas, M., Belongie, S., Hellerstein, J.M., Malik, J.: Blobworld: A system for region-based image indexing and retrieval. In: Third International Conference on Visual Information Systems, Springer, Heidelberg (1999)Google Scholar
  17. 17.
    Christoudias, C., Georgescu, B., Meer, P.: Synergism in low level vision. In: Kasturi, R., Laurendeau, D., Suen, C. (eds.) Proceedings of the 16th International Conference on Pattern Recognition, vol. 4, pp. 150–155. IEEE Computer Society, Los Alamitos (2002)Google Scholar
  18. 18.
    Mikeš, S., Haindl, M.: Prague texture segmentation data generator and benchmark. ERCIM News, pp. 67–68 (2006),

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Michal Haindl
    • 1
  • Stanislav Mikeš
    • 1
  • Giuseppe Scarpa
    • 2
  1. 1.Dep. of Pattern Recognition, Institute of Information Theory and Automation, Academy of Sciences CR, PragueCzech Republic
  2. 2.University Federico II, NaplesItaly

Personalised recommendations