Modeling the Variability in Brain Morphology and Lesion Distribution in Multiple Sclerosis by Deep Learning

  • Tom Brosch
  • Youngjin Yoo
  • David K. B. Li
  • Anthony Traboulsee
  • Roger Tam
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)


Changes in brain morphology and white matter lesions are two hallmarks of multiple sclerosis (MS) pathology, but their variability beyond volumetrics is poorly characterized. To further our understanding of complex MS pathology, we aim to build a statistical model of brain images that can automatically discover spatial patterns of variability in brain morphology and lesion distribution. We propose building such a model using a deep belief network (DBN), a layered network whose parameters can be learned from training images. In contrast to other manifold learning algorithms, the DBN approach does not require a prebuilt proximity graph, which is particularly advantageous for modeling lesions, because their sparse and random nature makes defining a suitable distance measure between lesion images challenging. Our model consists of a morphology DBN, a lesion DBN, and a joint DBN that models concurring morphological and lesion patterns. Our results show that this model can automatically discover the classic patterns of MS pathology, as well as more subtle ones, and that the parameters computed have strong relationships to MS clinical scores.


Population modeling multiple sclerosis T2 lesion machine learning brain imaging MRI deep learning deep belief networks 


  1. 1.
    Ceccarelli, A., Jackson, J., Tauhid, S., Arora, A., Gorky, J., Dell’Oglio, E., Bakshi, A., Chitnis, T., Khoury, S., Weiner, H., et al.: The impact of lesion in-painting and registration methods on voxel-based morphometry in detecting regional cerebral gray matter atrophy in multiple sclerosis. AJNR American Journal of Neuroradiology 33(8), 1579–1585 (2012)CrossRefGoogle Scholar
  2. 2.
    Wolz, R., Aljabar, P., Hajnal, J.V., Rueckert, D.: Manifold learning for biomarker discovery in MR imaging. In: Wang, F., Yan, P., Suzuki, K., Shen, D. (eds.) MLMI 2010. LNCS, vol. 6357, pp. 116–123. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Aljabar, P., Wolz, R., Srinivasan, L., Counsell, S.J., Rutherford, M.A., Edwards, A.D., Hajnal, J.V., Rueckert, D.: A combined manifold learning analysis of shape and appearance to characterize neonatal brain development. IEEE Transactions on Medical Imaging 30(12), 2072–2086 (2011)CrossRefzbMATHGoogle Scholar
  4. 4.
    Wolz, R., Aljabar, P., Hajnal, J.V., Lötjönen, J., Rueckert, D.: Nonlinear dimensionality reduction combining MR imaging with non-imaging information. Medical Image Analysis 16(4), 819–830 (2012)CrossRefGoogle Scholar
  5. 5.
    Cayton, L.: Algorithms for manifold learning. Univ. of California at San Diego Tech. Rep., 1–17 (2005)Google Scholar
  6. 6.
    Gerber, S., Tasdizen, T., Fletcher, P.T., Joshi, S., Whitaker, R.: Manifold modeling for brain population analysis. Medical Image Analysis 14(5), 643–653 (2010)CrossRefGoogle Scholar
  7. 7.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: 28th International Conference on Machine Learning, pp. 689–696 (2011)Google Scholar
  9. 9.
    Fonov, V., Evans, A.C., Botteron, K., Almli, C.R., McKinstry, R.C., Collins, D.L.: Unbiased average age-appropriate atlases for pediatric studies. NeuroImage 54(1), 313–327 (2011)CrossRefGoogle Scholar
  10. 10.
    Jenkinson, M., Bannister, P., Brady, M., Smith, S.: Improved optimization for the robust and accurate linear registration and motion correction of brain images. NeuroImage 17(2), 825–841 (2002)CrossRefGoogle Scholar
  11. 11.
    Andersson, J.L.R., Jenkinson, M., Smith, S.: Non-linear registration, aka spatial normalisation. Technical Report TR07JA2, FMRIB Centre, Oxford, United Kingdom (2007)Google Scholar
  12. 12.
    Hinton, G.E.: A practical guide to training restricted Boltzmann machines. Technical Report UTML TR 2010-003, Department of Computer Science, University of Toronto (2010)Google Scholar
  13. 13.
    Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 609–616 (2009)Google Scholar
  14. 14.
    Fischer, J.S., Rudick, R.A., Cutter, G.R., Reingold, S.C.: The multiple sclerosis functional composite measure (MSFC): an integrated approach to MS clinical outcome assessment. Multiple Sclerosis 5(4), 244–250 (1999)CrossRefGoogle Scholar
  15. 15.
    Smith, S.M., Zhang, Y., Jenkinson, M., Chen, J., Matthews, P., Federico, A., De Stefano, N.: Accurate, robust, and automated longitudinal and cross-sectional brain change analysis. NeuroImage 17(1), 479–489 (2002)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Tom Brosch
    • 1
    • 4
  • Youngjin Yoo
    • 1
    • 4
  • David K. B. Li
    • 2
    • 4
  • Anthony Traboulsee
    • 3
    • 4
  • Roger Tam
    • 2
    • 4
  1. 1.Department of Electrical and Computer EngineeringUBCVancouverCanada
  2. 2.Department of RadiologyUBCVancouverCanada
  3. 3.Division of NeurologyUBCVancouverCanada
  4. 4.MS/MRI Research GroupUniversity of British ColumbiaVancouverCanada

Personalised recommendations