Advertisement

Mammographic Mass Detection Using Unsupervised Clustering in Synergy with a Parcimonious Supervised Rule-Based Classifier

  • Michel Bruynooghe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4046)

Abstract

We develop a novel CAD detection system that can help a radiologist to detect masses in mammograms. The proposed algorithm concurrently detects the breast boundary and the pectoral muscle. Then, a clustering and morphology based segmentation algorithm is applied to the enhanced mammography image to separate the mass from the normal breast tissues. This technique outlines the shape of candidate masses in mammograms. To maximize detection specificity, we develop a two-stage hybrid classification network. First, an unsupervised classifier is used to classify suspicious opacities as suspect or not. Then, a few supervised interpretation rules are applied to further reduce the number of false detections. Using a private mammography database and the publicly available USF/DDSM database, experimental results demonstrate that a sensitivity of 94% (resp. 80%) can be achieved at a specificity level of 1.02 (resp. 0.69) false positives per image. Even in dense mammograms, the CAD algorithm can still correctly detect subtle masses.

Keywords

Digital Mammography Pectoral Muscle Mass Detection Unsupervised Cluster Candidate Masse 
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.
    Allen, B.H., Oxley, M.E., Collins, M.J.: A universal segmentation platform for computer-aided detection. In: Peitgen, H.-O. (ed.) 6th International Workshop on Digital Mammography, Bremen, Germany, June 22-25, 2002, pp. 164–168. Springer, Heidelberg (2003)Google Scholar
  2. 2.
    Bin-Zheng, Yuan-Hsiang-Chang, Xiao-Hui-Wang, Good, W.F., Gur, D.: Application of a Bayesian belief network in a computer-assisted diagnosis scheme for mass detection. In: Medical Imaging 1999: Image Processing, Proceedings of the SPIE, San Diego, CA, USA, February 22-25, pp. 1553–1561, The International Society for Optical Engineering. vol. 3661 pt. 1-2 (1999)Google Scholar
  3. 3.
    Bruynooghe, M.: Maximal Theoretical Complexity of Fast Hierarchical Clustering Algorithms Based on the Reducibility Property. International Journal of Pattern Recognition and Artificial Intelligence 7(3), 541–571 (1993)CrossRefGoogle Scholar
  4. 4.
    te-Brake, G.M., Karssemeijer, N., Hendriks, J.: An automatic method to discriminate malignant masses from normal tissue in digital mammograms. Physics-in-Medicine-and-Biology 45(10), 2843–2857 (2000)CrossRefGoogle Scholar
  5. 5.
    Campanini, R., Dongiovanni, D., Iampieri, E., Lanconelli, N., Masotti, M., Palermo, G., Riccardi, A., Roffilli, M.: A novel featureless approach to mass detection in digital mammograms based on support vector machines. Physics-in-Medicine-and-Biology 49(6), 961–975 (2004)CrossRefGoogle Scholar
  6. 6.
    Cheng, H.D., Cui, M.: Mass lesion detection with a fuzzy neural network. Pattern-Recognition 37(6), 1189–1200 (2004)CrossRefGoogle Scholar
  7. 7.
    Gale, A., Mugglestone, M., Cowley, H., Wooding, D.: Human factors considerations for CAD implementation in breast screening. In: 5th International Workshop on Digital Mammography, Toronto, Canada, June 11-14, pp. 461–467 (2000)Google Scholar
  8. 8.
    Hatanaka, Y., Hara, T., Fujita, H., Kasai, S., Endo, T., Iwase, T.: Development of an automated method for detecting mammographic masses with a partial loss of region. IEEE-Transactions-on-Medical-Imaging 20(12), 1209–1214 (2001)CrossRefGoogle Scholar
  9. 9.
    Heath, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, P.: The Digital Database for Screening Mammography. In: 5th International Workshop on Digital Mammography, Toronto, Canada, June 11-14, pp. 212–218 (2000)Google Scholar
  10. 10.
    Heath, M., Bowyer, K.: Mass detection by relative image intensity. In: 5th International Workshop on Digital Mammography, Toronto, Canada, June 11-14, pp. 219–225 (2000)Google Scholar
  11. 11.
    Hong, B.W., Brady, M.: A topographic representation for mammogram segmentation. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2879, pp. 730–737. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  12. 12.
    Khan, F., Sarma, A., Ying-Sun, Tufts, D.: Mass detection using tolerance intervals and a rank detector. In: IEEE International Symposium on Biomedical Imaging, Washington, DC, USA, July 7-10 (2002)Google Scholar
  13. 13.
    Kupinski, M.A., Giger, M.L.: Automated seeded lesion segmentation on digital mammograms. IEEE-Transactions-on-Medical-Imaging 17(4), 510–517 (1998)CrossRefGoogle Scholar
  14. 14.
    Paquerault, S., Petrick, N., Heang-Ping-Chan, Sahiner, B., Helvie, M.A.: Improvement of computerized mass detection on mammograms: Fusion of two-view information. Medical-Physics 29(2), 238–247 (2002)CrossRefGoogle Scholar
  15. 15.
    Lei-Zheng, Chan, A.K., McCord, G., Wu, S., Liu, J.S.: Detection of cancerous masses for screening mammography using discrete wavelet transform-based multiresolution Markov random field. Journal-of-Digital-Imaging 12(2), 18–23 (1999)Google Scholar
  16. 16.
    Lihua-Li, Yang-Zheng, Lei-Zhang, Clark, R.A.: False-positive reduction in CAD mass detection using a competitive classification strategy. Medical-Physics 28(2), 250–258 (2001)Google Scholar
  17. 17.
    Mudigonda, N.R., Rangayyan, R.M., Leo-Desautels, J.E.: Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE-Transactions-on-Medical-Imaging 20(12), 1215–1227 (2001)CrossRefGoogle Scholar
  18. 18.
    Petrick, N., Heang-Ping-Chan, Sahiner, B., Helvie, M.A.: Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms. Medical-Physics 26(8), 1642–1654 (1999)CrossRefGoogle Scholar
  19. 19.
    Sahiner, B., Petrick, N., Heang-ping-Chan, Paquerault, S., Helvie, M.A., Hadjiiski, L.M.: Recognition of lesion correspondence on two mammographic views-a new method of false-positive reduction for computerized mass detection. In: Medical Imaging 2001: Image Processing, Proceedings of the SPIE, San Diego, CA, USA, February 19-22, vol. 4322 pt. 1-3, pp. 649–655, The International Society for Optical Engineering (2001)Google Scholar
  20. 20.
    Timp, S., Karssemeijer, N., Hendricks, J.: Comparison of three different mass segmentation methods. In: Peitgen, H.-O. (ed.) 6th International Workshop on Digital Mammography, Bremen, Germany, June 22-25, pp. 218–222. Springer, Heidelberg (2002)Google Scholar
  21. 21.
    Yarlagadda, N., Bowyer, K., Li, R.: Baseline Comparison of Microcalcification Detection Algorithms. In: 5th International Workshop on Digital Mammography, Toronto, Canada, June 11-14, pp. 414–420 (2000)Google Scholar
  22. 22.
    Yates, K., Evans, C., Brady, M.: Improving the Brake’s mammographic mass-detection algorithm using phase congruency. In: Proceedings of the Sixth Digital Image Computing Techniques and Applications. Dicta 2002, pp. 179–183 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Michel Bruynooghe
    • 1
  1. 1.University Louis Pasteur of StrasbourgKarlsruheGermany

Personalised recommendations