Advertisement

Causal Probabilistic Modelling for Two-View Mammographic Analysis

  • Marina Velikova
  • Maurice Samulski
  • Peter J. F. Lucas
  • Nico Karssemeijer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5651)

Abstract

Mammographic analysis is a difficult task due to the complexity of image interpretation. This results in diagnostic uncertainty, thus provoking the need for assistance by computer decision-making tools. Probabilistic modelling based on Bayesian networks is among the suitable tools, as it allows for the formalization of the uncertainty about parameters, models, and predictions in a statistical manner, yet such that available background knowledge about characteristics of the domain can be taken into account. In this paper, we investigate a specific class of Bayesian networks—causal independence models—for exploring the dependencies between two breast image views. The proposed method is based on a multi-stage scheme incorporating domain knowledge and information obtained from two computer-aided detection systems. The experiments with actual mammographic data demonstrate the potential of the proposed two-view probabilistic system for supporting radiologists in detecting breast cancer, both at a location and a patient level.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Velikova, M., Samulski, M., Lucas, P.J.F., Karssemeijer, N.: Improved mammographic CAD performance using multi-view information: A Bayesian network framework. Physics in Medicine and Biology 54, 1131–1147 (2009)CrossRefPubMedGoogle Scholar
  2. 2.
    Samulski, M., Karssemeijer, N.: Matching mammographic regions in mediolateral oblique and cranio caudal views: A probabilistic approach. In: Proceedings of SPIE, Medical Imaging, vol. 6915 (2008)Google Scholar
  3. 3.
    Good, W., Zheng, B., Chang, Y., Wang, X., Maitz, G., Gur, D.: Multi-image cad employing features derived from ipsilateral mammographic views. In: Proceedings of SPIE, Medical Imaging, vol. 3661 (1999)Google Scholar
  4. 4.
    van Engeland, S., Karssemeijer, N.: Combining two mammographic projections in a computer aided mass detection method. Medical Physics 34, 898–905 (2007)CrossRefPubMedGoogle Scholar
  5. 5.
    Paquerault, S., Petrick, N., Chan, H., Sahiner, B., Helvie, M.A.: Improvement of computerized mass detection on mammograms: Fusion of two-view information. Medical Physics 29, 238–247 (2002)CrossRefPubMedGoogle Scholar
  6. 6.
    Qian, W., Song, D., Lei, M., Sankar, R., Eikman, E.: Computer-aided mass detection based on ipsilateral multiview mammograms. Acad. Rad. 14, 530–538 (2007)CrossRefGoogle Scholar
  7. 7.
    Heckerman, D., Breese, J.S.: Causal independence for probability assessment and inference using Bayesian networks. IEEE Trans. on SMC–A 26, 826–831 (1996)Google Scholar
  8. 8.
    Visscher, S., Lucas, P.J.F., Schurink, C.A.M., Bonten, M.J.M.: Modelling treatment effects in a clinical Bayesian network using Boolean threshold functions. Artificial Intelligence in Medicine (2008)Google Scholar
  9. 9.
    Murphy, K.: Bayesian Network Toolbox (BNT) (2007), http://www.cs.ubc.ca/~murphyk/Software/BNT/bnt.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Marina Velikova
    • 1
  • Maurice Samulski
    • 1
  • Peter J. F. Lucas
    • 2
  • Nico Karssemeijer
    • 1
  1. 1.Department of RadiologyRadboud University Nijmegen Medical CentreNijmegenThe Netherlands
  2. 2.Institute for Computing and Information SciencesRadboud University NijmegenNijmegenThe Netherlands

Personalised recommendations