Spatial Modeling of Multiple Sclerosis for Disease Subtype Prediction

  • Bernd Taschler
  • Tian Ge
  • Kerstin Bendfeldt
  • Nicole Müller-Lenke
  • Timothy D. Johnson
  • Thomas E. Nichols
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)


Magnetic resonance imaging (MRI) has become an essential tool in the diagnosis and managing of Multiple Sclerosis (MS). Currently, the assessment of MS is based on a combination of clinical scores and subjective rating of lesion images by clinicians. In this work we present an objective 5-way classification of MS disease subtype as well as a comparison between three different approaches. First we propose two spatially informed models, a Bayesian Spatial Generalized Linear Mixed Model (BSGLMM) and a Log Gaussian Cox Process (LGCP). The BSGLMM accounts for the binary nature of lesion maps and the spatial dependence between neighboring voxels, and the LGCP accounts for the random spatial variation in lesion location. Both improve upon mass univariate analyses that ignore spatial dependence and rely on some level of arbitrarily defined smoothing of the data. As a comparison, we consider a machine learning approach based on multi-class support vector machine (SVM). For the SVM classification scheme, unlike previous work, we use a large number of quantitative features derived from three MRI sequences in addition to traditional demographic and clinical measures. We show that the spatial models outperform standard approaches with average prediction accuracies of up to 85%.


Multiple Sclerosis Support Vector Machine Expand Disability Status Scale Expand Disability Status Scale Score Clinically Isolate Syndrome 
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.
    Allwein, E., Schapire, R., Singer, Y.: Reducing multiclass to binary: a unifying approach for margin classifiers. J. Mach. Learn. Res. 1, 113–141 (2001)MathSciNetGoogle Scholar
  2. 2.
    Arns, C., Knackstedt, M., Pinczewski, W., Mecke, K.: Euler-Poincaré characteristics of classes of disordered media. Phys. Rev. E 63, 31112 (2001)CrossRefGoogle Scholar
  3. 3.
    Cohen, J., Rae-Grant, A.: Handbook of multiple sclerosis. Springer Healthcare LCC, London (2010)Google Scholar
  4. 4.
    Ge, T., Müller-Lenke, N., Bendfeldt, K., Nichols, T., Johnson, T.: Analysis of multiple sclerosis lesions via spatially varying coefficients. Ann. Appl. Stat. (in press, 2014)Google Scholar
  5. 5.
    Gelfand, A., Dey, D., Chang, H.: Model determination using predictive distributions with implementation via sampling-based methods. Bayes. Stat. 4, 147–167 (1992)MathSciNetGoogle Scholar
  6. 6.
    Kappos, L., Antel, J., Comi, G., Montalban, X., O’Connor, P., Polman, C., Haas, T., Korn, A., Karlsson, G., Radü, E.: Oral fingolimod (FTY720) for relapsing multiple sclerosis. N. Engl. J. Med. 355, 1124–1140 (2006)CrossRefGoogle Scholar
  7. 7.
    Lang, C., Ohser, J., Hilfer, R.: On the analysis of spatial binary images. J. Microsc. 203, 303–313 (2001)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Lövblad, K., Anzalone, N., Dörfler, A., Essig, M., Hurwitz, B., Kappos, L., Lee, S.-K., Filippi, M.: MR imaging in multiple sclerosis: Review and recommendations for current practice. AJNR 31, 983–989 (2010)CrossRefzbMATHGoogle Scholar
  9. 9.
    MacKay-Altman, R., Petkau, J., Vrecko, D., Smith, A.: A longitudinal model for magnetic resonance imaging lesion count data in multiple sclerosis patients. Stat. Med. 31, 449–469 (2011)CrossRefGoogle Scholar
  10. 10.
    Møller, J., Syversveen, A., Waagepetersen, R.: Log Gaussian Cox processes. Scand. J. Stat. 25, 451–482 (1998)Google Scholar
  11. 11.
    Møller, J., Waagepetersen, R.: Statistical inference and simulation for spatial point processes. Chapman & Hall/CRC (2004)Google Scholar
  12. 12.
    Morgan, C., Aban, I., Katholi, C., Cutter, G.: Modeling lesion counts in multiple sclerosis when patients have been selected for baseline activity. Mult. Scl. 16, 926–934 (2010)CrossRefGoogle Scholar
  13. 13.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Bernd Taschler
    • 1
  • Tian Ge
    • 2
  • Kerstin Bendfeldt
    • 3
  • Nicole Müller-Lenke
    • 3
  • Timothy D. Johnson
    • 4
  • Thomas E. Nichols
    • 2
  1. 1.Centre for Complexity ScienceUniversity of WarwickCoventryUnited Kingdom
  2. 2.Department of StatisticsUniversity of WarwickCoventryUnited Kingdom
  3. 3.Medical Image Analysis CenterUniversity Hospital BaselBaselSwitzerland
  4. 4.Department of BiostatisticsUniversity of MichiganAnn ArborUSA

Personalised recommendations