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.
Keywords
- Multiple Sclerosis
- Support Vector Machine
- Expand Disability Status Scale
- High Classification Accuracy
- Lesion Load
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
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)
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)
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)
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)
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)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press (2000)
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)
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)
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)
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)
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)
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)
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)
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)
Hua, S., Sun, Z.: Support Vector Machine Approach for Protein Subcellular Localization Prediction. Bioinformatics 17, 721–728 (2001)
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)
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)
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)
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)
Kurtzke, J.F.: Rating Neurologic Impairment in Multiple Sclerosis: An Expanded Disability Status Scale (EDSS). Neurology 33, 1444–1452 (1983)
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)
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)
Mitchell, T.: Machine Learning. McGraw-Hill (1997)
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)
Nallapati, R.: Discriminative Models for Information Retrieval. In: SIGIR (2004)
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)
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)
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)
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)
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)
Rosenblatt, F.: Principles of Neurodynamics: Perceptron and the Theory of Brain Mechanisms. Spartan (1962)
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)
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)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights 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)