Advertisement

A Multichannel Markov Random Field Approach for Automated Segmentation of Breast Cancer Tumor in DCE-MRI Data Using Kinetic Observation Model

  • Ahmed B. Ashraf
  • Sara Gavenonis
  • Dania Daye
  • Carolyn Mies
  • Michael Feldman
  • Mark Rosen
  • Despina Kontos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6893)

Abstract

We present a multichannel extension of Markov random fields (MRFs) for incorporating multiple feature streams in the MRF model. We prove that for making inference queries, any multichannel MRF can be reduced to a single channel MRF provided features in different channels are conditionally independent given the hidden variable. Using this result we incorporate kinetic feature maps derived from breast DCE MRI into the observation model of MRF for tumor segmentation. Our algorithm achieves an ROC AUC of 0.97 for tumor segmentation. We present a comparison against the commonly used approach of fuzzy C-means (FCM) and the more recent method of running FCM on enhancement variance features (FCM-VES). These previous methods give a lower AUC of 0.86 and 0.60 respectively, indicating the superiority of our algorithm. Finally, we investigate the effect of superior segmentation on predicting breast cancer recurrence using kinetic DCE MRI features from the segmented tumor regions. A linear prediction model shows significant prediction improvement when segmenting the tumor using the proposed method, yielding a correlation coefficient r = 0.78 (p < 0.05) to validated cancer recurrence probabilities, compared to 0.63 and 0.45 when using FCM and FCM-VES respectively.

Keywords

Breast DCE MRI breast tumor segmentation tumor characterization breast cancer recurrence prediction 

References

  1. 1.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 1(4), 321–331 (1988)CrossRefzbMATHGoogle Scholar
  2. 2.
    Bhooshan, N., Giger, M.L., Jansen, S.A., Li, H., Lan, L., Newstead, G.M.: Cancerous breast lesions on DCE MR Images: Computerized characterization for Image based prognostic markers. Radiology 254(3), 680–690 (2010)CrossRefGoogle Scholar
  3. 3.
    Lee, S.H., Kim, J.H., Cho, N., Park, J.S., Yang, Z., Jung, Y.S., Moon, W.K.: Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI. Med. Phys. 37, 3940 (2010)CrossRefGoogle Scholar
  4. 4.
    Zhang, Y., Brady, M., Smith, S.: Segmentation of Brain MR Images Through a Hidden Markov Random Field Model and the Expectation-Maximization Algorithm. IEEE Trans. Med. Imag. 20, 45–57 (2001)CrossRefGoogle Scholar
  5. 5.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV, vol. 1, pp. 10–17 (2003)Google Scholar
  6. 6.
    Meltzer, T., Globerson, A., Weiss, Y.: Convergent message passing algorithms – a unifying view. In: UAI, pp. 393–401 (2009)Google Scholar
  7. 7.
    Paik, S., Tang, G., Shak, S., Kim, C., Baker, J., Kim, W., Cronin, M., Baehner, F.L., Watson, D., Bryant, J., Costantino, J.P., Geyer, C.E., Wickerham, D.L., Wolmark, N.: Gene expression and benefit of chemotherapy in women with node-negative, estrogen receptor-positive breast cancer. J. Clin. Oncol. 24(23), 3726–3734 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ahmed B. Ashraf
    • 1
  • Sara Gavenonis
    • 1
  • Dania Daye
    • 1
  • Carolyn Mies
    • 1
  • Michael Feldman
    • 1
  • Mark Rosen
    • 1
  • Despina Kontos
    • 1
  1. 1.The University of PennsylvaniaPhiladelphiaUSA

Personalised recommendations