Skip to main content
SpringerLink
Log in

Predicting Clinically Definite Multiple Sclerosis from Onset Using SVM

  • Conference paper
Machine Learning and Interpretation in Neuroimaging

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 7263))

Abstract

We aim to determine, with the support vector machine (SVM), whether a combination of magnetic resonance imaging (MRI) and demographic features at onset can better predict conversion to clinically definite multiple sclerosis (CDMS) than the single best feature, and which combination is the best predictor. Several lesional features were extracted from MRI scans, e.g., lesion count, lesion load, lesion size distribution, average lesion intensity, average distance of lesions from centre. Other features include type of presentation, age, and expanded disability status scale (EDSS) at onset. With knowledge of further clinical event within one year, we first used individual features and then combinations of features to perform SVM classification by leave-one-out. The best classification accuracies from the two are compared. Combinations of features give higher classification accuracy (77.3%) than the single best feature (61.4%). The best feature combination is: lesion load, average lesion T2 intensity, average distance from centre, shortest horizontal distance from centre, and type of presentation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 49.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bakshi, R., Benedict, R.H., Bermel, R.A., Caruthers, S.D., Puli, S.R., Tjoa, C.W., Fabiano, A.J., Jacobs, L.: T2 Hypointensity in the Deep Grey Matter of Patients with Multiple Sclerosis: A Quantitative Magnetic Resonance Imaging Study. Archives of Neurology 59(1), 62–68 (2002)

    Article  Google Scholar 

  2. Barlett, M.S., Littlewort, G., Frank, M., Lainscsek, C., Fasel, I., Movellan, J.: Recognizing Facial Expression: Machine Learning and Application to Spontaneous Behavior. Computer Vision and Pattern Recognition 2, 568–573 (2005)

    Google Scholar 

  3. Bhasin, M., Raghava, G.P.S.: ESLpred: SVM-Based Method for Subcellular Localization of Eukaryotic Proteins Using Dipeptide Composition and PSI-BLAST. Nucleic Acids Research 32, W414–W419 (2004)

    Article  Google Scholar 

  4. Bodini, B., Battaglini, M., De Stefano, N., Khaleeli, Z., Barkhof, F., Chard, D., Filippi, M., Montalban, X., Polman, C., Rovaris, M., Rovira, A., Samson, R., Miller, D., Thompson, A., Ciccarelli, O.: T2 Lesion Location Really Matters: A 10 Year Follow-Up Study in Primary Progressive Multiple Sclerosis. J. Neurol. Neurosurg. Psychiatry 82, 72–77 (2011)

    Article  Google Scholar 

  5. Brex, P.A., Ciccarelli, O., O’Riordan, J.I., Sailer, M., Thompson, A., Miller, D.: A Longitudinal Study of Abnormalities on MRI and Disability from Multiple Sclerosis. The New England Journal of Medicine 346, 158–164 (2002)

    Article  Google Scholar 

  6. Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press (2000)

    Google Scholar 

  7. Ecker, C., Marquand, A., Mourao-Miranda, J., Johnston, P., Daly, E.M., Brammer, M.J., Maltezos, S., Murphy, C.M., Robertson, D., Williams, S.C., Murphy, D.G.M.: Describing the Brain in Autism in Five Dimensions - Magnetic Resonance Imaging-Assisted Diagnosis of Autism Spectrum Disorder Using a Multiparameter Classification Approach. The Journal of Neuroscience 30(32), 10612–10623 (2010)

    Article  Google Scholar 

  8. Ecker, C., Rocha-Reggo, V., Johnston, P., Mourao-Miranda, J., Marquand, A., Daly, E.M., Brammer, M.J., Murphy, C., Murphy, D.G.: Investigating the Predictive Value of Whole-Brain Structural MR Scans in Autism: A Pattern Classification Approach. Neuroimage 49(1), 44–56 (2010)

    Article  Google Scholar 

  9. Fazekas, F., Barkhof, F., Filippi, M., Grossman, R.I., Li, D.K.B., McDonald, W.I., McFarland, H.F., Paty, D.W., Simon, J.H., Wolinsky, J.S., Miller, D.H.: The Contribution of Magnetic Resonance Imaging to the Diagnosis of Multiple Sclerosis. Neurology 53, 448–456 (1999)

    Article  Google Scholar 

  10. 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 Journal 5, 244–250 (1999)

    Article  Google Scholar 

  11. Fischer, J.S., Rudick, R.A., Cutter, G.R., Reingold, S.C.: Multiple Sclerosis Functional Composite Measure (MSFC): Administration and Scoring Manual. National Multiple Sclerosis Society (2001)

    Google Scholar 

  12. Fisniku, L.K., Brex, P.A., Altmann, D.R., Miszkiel, K.A., Benton, C.E., Lanyon, R., Thompson, A.J., Miller, D.H.: Disability and T2 MRI Lesions: A 20-year Follow-Up of Patients with Relapse Onset of Multiple Sclerosis. Brain 131, 808–817 (2008)

    Article  Google Scholar 

  13. Geurts, J.J., Roosendaal, S.D., Calabrese, M., Ciccarelli, O., Agosta, F., Chard, D.T., Gass, A., Huerga, E., Moraal, B., Pareto, D., Rocca, M.A., Wattjes, M.P., Yousry, T.A., Uitdehaag, B.M., Barkhof, F.: Consensus Recommendations for MS Cortical Lesion Scoring Using Double Inversion Recovery MRI. Neurology 76, 418–424 (2011)

    Article  Google Scholar 

  14. Giorgio, A., Battaglini, M., Rocca, M.A., et al.: Relevance of Brain Lesion Distribution and Frequency to the Subsequent Conversion of a Clinically Isolated Syndrome to Multiple Sclerosis. In: Congress of the European and Americans Committees for Treatment and Research in MS (ECTRIMS 2011), Amsterdam, The Netherlands. Abstract number 90 (2011)

    Google Scholar 

  15. Hua, S., Sun, Z.: Support Vector Machine Approach for Protein Subcellular Localization Prediction. Bioinformatics 17, 721–728 (2001)

    Article  Google Scholar 

  16. Ingle, G.T., Stevenson, V.L., Miller, D.H., Thompson, A.J.: Primary Progressive Multiple Sclerosis: A 5-year Clinical and MR Study. Brain 126, 2528–2536 (2003)

    Article  Google Scholar 

  17. Khaleeli, Z., Ciccarelli, O., Manfredonia, F., Barkhof, F., Brochet, B., Cercignani, M., Dousset, V., Filippi, M., Montalban, X., Polman, C., Rovaris, M., Rovira, A., Sastre-Garriga, J., Vellinga, M., Miller, D., Thompson, A.: Predicting Progression in Primary Progressive Multiple Sclerosis: A 10-year Multicenter Study. Annals of Neurology 63, 790–793 (2008)

    Article  Google Scholar 

  18. Koopmans, R.A., Li, D.K., Oger, J.J., Mayo, J., Paty, D.W.: The Lesion of Multiple Sclerosis: Imaging of Acute and Chronic Stages. Neurology 39(7), 959–963 (1989)

    Article  Google Scholar 

  19. Kragt, J.J., Thompson, A.J., Montalban, X., Tintore, M., Rio, J., Polman, C.H., Uitdehaag, B.M.J.: Responsiveness and Predictive Value of EDSS and MSFC in Primary Progressive MS. Neurology 70, 1084–1091 (2008)

    Article  Google Scholar 

  20. Kurtzke, J.F.: Rating Neurologic Impairment in Multiple Sclerosis: An Expanded Disability Status Scale (EDSS). Neurology 33, 1444–1452 (1983)

    Article  Google Scholar 

  21. Li, D.K., Paty, D.W.: Magnetic Resonance Imaging Results of the PRISMS Trial: A Randomized, Double-Blind, Placebo-Controlled Study of Interferon-beta1a in Relapsing–Remitting Multiple Sclerosis. Prevention of Relapses and Disability by Interferon-beta1a Subcutaneously in Multiple Sclerosis. Annals of Neurology 46, 197–206 (1999)

    Google Scholar 

  22. Miller, D.H., Molyneux, P.D., Barker, G.J., MacManus, D.G., Moseley, I.F., Wagner, K.: Effect of Interferon-beta1b on Magnetic Resonance Imaging Outcomes in Secondary Progressive Multiple Sclerosis: Results of a European Multicenter, Randomized, Double-Blind, Placebo-Controlled Trial. European Study Group on Interferon-beta1b in Secondary Progressive Multiple Sclerosis. Annals of Neurology 46, 850–859 (1999)

    Google Scholar 

  23. Mitchell, T.: Machine Learning. McGraw-Hill (1997)

    Google Scholar 

  24. Morrissey, S.P., Miller, D.H., Kendall, B.E., Kingsley, D.P., Kelly, M.A., Francis, D.A., MacManus, D.G., McDonald, W.I.: The Significance of Brain Magnetic Resonance Imaging Abnormalities at Presentation with Clinically Isolated Syndromes Suggestive of Multiple Sclerosis. A 5-Year Follow-Up Study. Brain 116(1), 135–146 (1993)

    Google Scholar 

  25. Nallapati, R.: Discriminative Models for Information Retrieval. In: SIGIR (2004)

    Google Scholar 

  26. Narayanan, S., Fu, L., Pioro, E., De Stefano, N., Collins, D.L., Francis, G.S., Antel, J.P., Matthews, P.M., Arnold, D.L.: Imaging of Axonal Damage in Multiple Sclerosis: Spatial Distribution of Magnetic Resonance Imaging Lesions. Annals of Neurology 41(3), 385–391 (1997)

    Article  Google Scholar 

  27. Offenbacher, H., Fazekas, F., Schmidt, R., Freidl, W., Flooh, E., Payer, F., Lechner, H.: Assessment of MRI Criteria for a Diagnosis of MS. Neurology 43, 905–909 (1993)

    Article  Google Scholar 

  28. O’Riordan, J.I., Thompson, A.J., Kingsley, D.P., MacManus, D.G., Kendall, B.E., Rudge, P., McDonald, W.I., Miller, D.H.: The Prognostic Value of Brain MRI in Clinically Isolated Syndromes of the CNS: A 10-year Follow-Up. Brain 121, 495–503 (1998)

    Article  Google Scholar 

  29. Paty, D.W., Li, D.K., Oger, J.J., Kastrukoff, L., Koopmans, R., Tanton, E., Zhao, G.J.: Magnetic Resonance Imaging in the Evaluation of Clinical Trials in Multiple Sclerosis. Annals of Neurology 36(suppl.), 95–96 (1994)

    Article  Google Scholar 

  30. Poser, C.M., Paty, D.W., Scheinberg, L., McDonald, W.I., Davis, F.A., Ebers, G.C., Johnston, K.P., Sibley, W.A., Silberberg, D.H., Tourtellotte, W.W.: New Diagnostic Criteria for Multiple Sclerosis: Guidelines for Research Protocols. Annals of Neurology 13, 227–231 (1983)

    Article  Google Scholar 

  31. Rosenblatt, F.: Principles of Neurodynamics: Perceptron and the Theory of Brain Mechanisms. Spartan (1962)

    Google Scholar 

  32. Rudick, R.A., Lee, J.C., Simon, J., Fisher, E.: Significance of T2 Lesions in Multiple Sclerosis: A 13-Year Longitudinal Study. Annals of Neurology 60, 236–242 (2006)

    Article  Google Scholar 

  33. Sastre-Garriga, J., Ingle, G.T., Rovaris, M., Tellez, N., Jasperse, B., Altmann, D.R., Benedetti, B., Stevenson, W.L., Cercignani, M., Leary, S.M., Barkhof, F., Brochet, B., Dousset, V., Filippi, M., Montalban, X., Kalkers, F., Polman, H., Rovira, A., Miller, D.H., Thompson, A.J.: Long-Term Clinical Outcome of Primary Progress MS: Predictive Value of Clinical and MRI Data. Neurology 65, 633–635 (2005)

    Article  Google Scholar 

  34. Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)

    Book  MATH  Google Scholar 

  35. Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK

    Philip P. Kwok & Daniel C. Alexander

  2. Nuclear Magnetic Resonance Research Unit, UCL Institute of Neurology, University College London, London, UK

    Olga Ciccarelli, Declan T. Chard & David H. Miller

Authors
  1. Philip P. Kwok
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Olga Ciccarelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Declan T. Chard
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. David H. Miller
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daniel C. Alexander
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Radiology, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Wien, Austria

    Georg Langs

  2. Computational Biology Center, IBM T.J. Watson Research Center, 1101 Kitchawan Road, 10598, Yorktown Heights, NY, USA

    Irina Rish

  3. Max Planck Institute for Intelligent Systems, Spemannstraße 38, 72076, Tübingen, Germany

    Moritz Grosse-Wentrup

  4. Machine Learning Department, Carnegie Mellon University, 5000 Forbes Avenue, 15213-3891, Pittsburgh, PA, USA

    Brian Murphy

Rights and permissions

Reprints and permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kwok, P.P., Ciccarelli, O., Chard, D.T., Miller, D.H., Alexander, D.C. (2012). Predicting Clinically Definite Multiple Sclerosis from Onset Using SVM. In: Langs, G., Rish, I., Grosse-Wentrup, M., Murphy, B. (eds) Machine Learning and Interpretation in Neuroimaging. Lecture Notes in Computer Science(), vol 7263. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34713-9_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-34713-9_15

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-34712-2

  • Online ISBN: 978-3-642-34713-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation