Bayesian Model Selection for Pathological Data

  • Carole H. Sudre
  • Manuel Jorge Cardoso
  • Willem Bouvy
  • Geert Jan Biessels
  • Josephine Barnes
  • Sébastien Ourselin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)


The detection of abnormal intensities in brain images caused by the presence of pathologies is currently under great scrutiny. Selecting appropriate models for pathological data is of critical importance for an unbiased and biologically plausible model fit, which in itself enables a better understanding of the underlying data and biological processes. Besides, it impacts on one’s ability to extract pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a fully unsupervised hierarchical model selection framework for neuroimaging data which permits the stratification of different types of abnormal image patterns without prior knowledge about the subject’s pathological status.


Gaussian Mixture Model Markov Random Field White Matter Hyperintensities Multiple Sclerosis Lesion Tissue Class 
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.


  1. 1.
    Admiraal-Behloul, F., van den Heuvel, D., Olofsen, H., van Osch, M., van der Grond, J., van Buchem, M., Reiber, J.: Fully automatic segmentation of white matter hyperintensities in MR images of the elderly. NeuroImage 28 (2005)Google Scholar
  2. 2.
    Balafar, M.A.: Gaussian mixture model based segmentation methods for brain MRI images. Artificial Intelligence Review (2012)Google Scholar
  3. 3.
    Battaglini, M., Jenkinson, M., De Stefano, N.: Evaluating and reducing the impact of white matter lesions on brain volume measurements. HBM 33, 2062–2071 (2012)CrossRefGoogle Scholar
  4. 4.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM Algorithm. J. R. Stat. Soc. B 39(1), 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  5. 5.
    Fraley, C., Raftery, A.E.: Model-based clustering, discriminant analysis, and density estimation. J. Am. Statist. Assoc. 97(458), 611–631 (2002)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    García-Lorenzo, D., Francis, S., Narayanan, S., Arnold, D.L., Collins, D.L.: Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Medical Image Analysis 17, 1–18 (2013)CrossRefGoogle Scholar
  7. 7.
    García-Lorenzo, D., Prima, S., Douglas, A.L., Collins, D.L., Barillot, C.: Trimmed-likelihood estimation for focal lesions and tissue segmentation in multisequence mri for multiple sclerosis. IEEE TMI 30(8), 1455–1467 (2011)Google Scholar
  8. 8.
    Groves, A.R., Beckmann, C.F., Smith, S.M., Woolrich, M.W.: Linked independent component analysis for multimodal data fusion. NeuroImage 54(3) (2011)Google Scholar
  9. 9.
    Li, Y., Li, L.: A split and merge EM algorithm for color image segmentation. In: IEEE ICIS 2009, vol. 4, pp. 395–399 (2009)Google Scholar
  10. 10.
    Sajja, B.R., Datta, S., He, R., Mehta, M., Gupta, R.K., Wolinsky, J.S., Narayana, P.A.: Unified approach for multiple sclerosis lesion segmentation on brain MRI. Ann. Biomed. Eng. 34(1), 142–151 (2006)CrossRefGoogle Scholar
  11. 11.
    Shiee, N., Bazin, P.-L., Cuzzocreo, J., Blitz, A., Pham, D.L.: Segmentation of brain images using adaptive atlases with application to ventriculomegaly. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 1–12. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Shroeter, P., Vesin, J.M., Langenberger, T., Meuli, R.: Robust parameter estimation of intensity distributions for brain magnetic resonance images. IEEE TMI 17(2), 172–186 (1998)Google Scholar
  13. 13.
    Ueda, N., Nakano, R., Ghahramani, Z., Hinton, G.E.: SMEM Algorithm for Mixture Models. Neural Comput. 12(9), 2109–2128 (2000)CrossRefGoogle Scholar
  14. 14.
    Van Leemput, K., Maes, F., Vandermeulen, D., Colchester, A., Suetens, P.: Automated segmentation of multiple sclerosis lesions by model outlier detection. IEEE TMI 20(8), 677–688 (2001)Google Scholar
  15. 15.
    Wolff, Y., Miron, S., Achiron, A., Greespan, H.: Improved CSF classification and lesion detection in MR brain images with multiple sclerosis. In: SPIE, vol. 6512 (2007)Google Scholar
  16. 16.
    Wu, Y., Warfield, S.K., Tan, I.L., Wells III, W.M., Meier, D.S., van Schijndel, R.A., Barkhof, F., Guttmann, C.R.: Automated segmentation of multiple sclerosis lesion subtypes with multichannel MRI. NeuroImage 32, 1205–1215 (2006)CrossRefGoogle Scholar
  17. 17.
    Zhuang, X., Huang, Y., Palaniappan, K., Zhao, Y.: Gaussian mixture density modeling, decomposition, and applications. IEEE TIP 5(9), 1293–1302 (1996)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Carole H. Sudre
    • 1
    • 2
  • Manuel Jorge Cardoso
    • 1
    • 2
  • Willem Bouvy
    • 3
  • Geert Jan Biessels
    • 3
  • Josephine Barnes
    • 2
  • Sébastien Ourselin
    • 1
    • 2
  1. 1.Translational Imaging Group, CMICUniversity College LondonUK
  2. 2.Dementia Research CentreUCL Institute of NeurologyLondonUK
  3. 3.Department of Neurology and NeurosurgeryUMC UtrechtNetherlands

Personalised recommendations