Comparison of Feature Extraction Methods for Breast Cancer Detection

  • Rafael Llobet
  • Roberto Paredes
  • Juan C. Pérez-Cortés
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3523)


Although screening mammography is widely used for the detection of breast tumors, it is difficult for a radiologist to interpret correctly a mammogram. It is possible to improve this task by using a computer aided diagnosis system (CAD) which highlights the areas most likely to contain cancer cells. In this paper, we present and compare five different feature extraction methods for breast cancer detection in digitized mammograms. All the methods are based on features extracted from a local window and on a k-nearest neighbor classifier with fast search.


Feature Vector Digital Mammography Feature Extraction Method Breast Cancer Detection Digitize Mammogram 
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.
    Arya, S., et al.: An optimal algorithm for approximate nearest neighbor searching. Journal of the ACM 45, 891–923 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Bovis, K.J., Singh, S.: Detection of masses in mammograms using texture features. In: Proceedings of the International Conference on Pattern Recognition (ICPR), vol. 2, pp. 2267–2270 (2000)Google Scholar
  3. 3.
    Te Brake, G.M., Karssemeijer, N.: Comparison of three mass detection methods. In: Digital Mammography, Dordrecht, The Netherlands, pp. 119–126. Kluwer Academic Publishers, Dordrecht (1998)Google Scholar
  4. 4.
    Campanini, R., Bazzani, A., et al.: A novel approach to mass detection in digital mammography based on support vector machines (svm). In: Proceedings of the 6th International Workshop on Digital Mammography (IWDM), Bremen, Germany, pp. 399–401. Springer, Heidelberg (2002)Google Scholar
  5. 5.
    Chen, C., Daponte, J., Fox, M.: Fractal feature analysis and classification in medical imaging (1989)Google Scholar
  6. 6.
    Christoyianni, I., Koutras, A., et al.: Computer aided diagnosis of breast cancer in digitized mammograms. Computerized Medical Imaging and Graphics 26, 309–319 (2002)CrossRefGoogle Scholar
  7. 7.
    Diyana, W.M., Larcher, J., Besar, R.: A comparison of clustered microcalcifications automated detection methods in digital mammogram. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hong Kong, pp. 385–388 (2003)Google Scholar
  8. 8.
    Duda, R., Hart, P.: Pattern Recognition and Scene Analysis. John Wiley, New York (1973)Google Scholar
  9. 9.
    Rowley, H.A., Baluja, S., et al.: Neural network-based face detection. IEEE Transactions on PAMI 20(1), 23–38 (1998)Google Scholar
  10. 10.
    Haralick, R.M., et al.: Textural features for image classification. IEEE Trans. SMC 3(6), 610–621 (1973)MathSciNetGoogle Scholar
  11. 11.
    Heath, M.D., Bowyer, K.W.: Mass detection by relative image intensity. In: Proceedings of the 5th International Workshop on Digital Mammography (IWDM-2000), pp. 219–225. Medical Physics Publishing (2000)Google Scholar
  12. 12.
    Insana, M., et al.: Analysis of ultrasound image texture via generalized rician statistics. Opt. Eng. 25, 743–748 (1986)Google Scholar
  13. 13.
    Lado, M.J., Tahoces, P.G., et al.: Evaluation of an automated wavelet-based system dedicated to the detection of clustered microcalcifications in digital mammograms. Med. Inform. In Med. 26, 149–163 (2001)CrossRefGoogle Scholar
  14. 14.
    Landeweerd, G., Gelsema, E.: The use of nuclear texture parameters in the automatic analysis of leukocytes. Pattern Recognition 10, 57–61 (1978)CrossRefGoogle Scholar
  15. 15.
    Llobet, R., Perez-Cortes, J.C.: Breast cancer detection in digitized mammograms using non-parametric methods. In: Proceedings of the 2nd International Conference on Advances in Biomedical Signal and Information Processing (MEDSIP), Sliema, Malta, vol. 1, pp. 281–287 (2004)Google Scholar
  16. 16.
    Llobet, R., Toselli, A.H., Perez-Cortes, J.C., Juan, A.: Computer-aided prostate cancer detection in ultrasonographic images. In: Proceedings of the 1st Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), Puerto de Andratx (Mallorca, Spain), vol. 1, pp. 411–419 (2003)Google Scholar
  17. 17.
    Perez-Cortes, J.C., Arlandis, J., Llobet, R.: Fast and accurate handwritten character recognition using approximate nearest neighbours search on large databases. In: Amin, A., Pudil, P., Ferri, F., Iñesta, J.M. (eds.) SPR 2000 and SSPR 2000. LNCS (LNAI), vol. 1876, pp. 767–776. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  18. 18.
    Suckling, J., Parker, J., et al.: The mammographic images analysis society digital mammogram database. In: Exerpta Medica. International Congress Series, vol. 1069, pp. 375–378 (1994)Google Scholar
  19. 19.
    te Brake, G.M., Karssemeijer, N.: Automated detection of breast carcinomas that were not detected in a screening program. Radiology 207, 465–471 (1998)Google Scholar
  20. 20.
    Wallis, M., Walsh, M., et al.: A review of false negative mammography in a symptomatic population. Clin. Radiol. 44, 13–15 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Rafael Llobet
    • 1
  • Roberto Paredes
    • 1
  • Juan C. Pérez-Cortés
    • 1
  1. 1.Instituto Tecnológico de InformáticaUniversidad Politécnica de ValenciaValenciaSpain

Personalised recommendations