Advertisement

Texture Based Mammogram Classification and Segmentation

  • Yang Can Gong
  • Michael Brady
  • Styliani Petroudi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4046)

Abstract

Several studies have showed that increased mammographic density is an important risk factor for breast cancer. Dense tissue often appears as textured regions in mammograms, so density and texture estimation are inextricably linked. It has been demonstrated that texture classes can be learned, and that subsequently textures can be classified using the joint distribution of intensity values over extremely compact neighbourhoods. Motivated by the success of texture classification, we propose an fully automated scheme for mammogram texture classification and segmentation. The classification method first has a training step to model the joint distribution for each breast density class. Subsequently, a statistical comparison is used to determine the class label for new images. Inspired by the classification, we combine the so-called image patch method with a HMRF(Hidden Markov Random Field) to achieve mammogram segmentation.

Keywords

Breast Cancer Risk Training Image Mammographic Density Markov Random Field Image Patch 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Varma, M.: Statistical Approaches to Texture Classification (2004)Google Scholar
  2. 2.
    Boyd, N.F., et al.: Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. J. Natl. Cancer Inst. 87(9), 670–675 (1995)CrossRefGoogle Scholar
  3. 3.
    Saftlas, A.F., Szklo, M.: Mammographic parenchymal patterns and breast cancer risk. Epidemiol Review 9, 146–174 (1987)Google Scholar
  4. 4.
    Oza, M., Boyd, N.F.: Mammographic parenchymal patterns: a marker of breast cancer risk. Epidemiol review 15, 196–208 (1993)CrossRefGoogle Scholar
  5. 5.
    Wolfe, J.N.: Breast parenchymal patterns and their changes with age. Radiology 121, 545–552 (1976a)Google Scholar
  6. 6.
    Leung, T., Malik, J.: Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons. International Journal of Computer Vision 43(1), 29–44 (2001)MATHCrossRefGoogle Scholar
  7. 7.
    Evertsz, C.J.G., et al.: Soft-copy reading environment for screening mammography - screen. In: Fifth International Workshop in Digital Mammogrphy, pp. 566–572 (2000)Google Scholar
  8. 8.
    Petroudi, S., Brady, M.: An automated algorithm for breast background segmentation. Medical Imaging Understanding and Analysis, 181–184 (2003a)Google Scholar
  9. 9.
    Duda, R.O., Hart, P.E.: Pattern Classificaton and Scene Analysis. Wiley, Chichester (1973)Google Scholar
  10. 10.
    Brault, P., Mohammad-Djafari, A.: Bayesian segmentation and motion estimation in video sequences using a markov-potts model. In: Proceedings of WSEAS Conference on Applied Mathematics 2004 (2004)Google Scholar
  11. 11.
    Evertsz, C.J.G., et al.: Highthroughput soft-copy reading system for digital mammography in nationwide european screening mammography programs: Requirements and first solutions. In: Proceedings of the Radiographic Society of North America (2000)Google Scholar
  12. 12.
    Petroudi, S., Brady, M.: Automatic nipple detection on mammograms. Medical Image Computing and Computer-Assisted Intervention, 971–972 (2003)Google Scholar
  13. 13.
    Marroquin, J.L., Santana, E.A., Botello, S.: Hidden Markov Measure Field Models for Image Segmentation. IEEE Pattern Analysis and Machine Intelligence 25(11), 1380–1387 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yang Can Gong
    • 1
  • Michael Brady
    • 1
  • Styliani Petroudi
    • 1
  1. 1.Wolfson Medical Vision Laboratory, Robotics Research GroupUniversity of OxfordOxfordUK

Personalised recommendations