Comparison of Deep Learning and Support Vector Machine Learning for Subgroups of Multiple Sclerosis

  • Yeliz KaracaEmail author
  • Carlo Cattani
  • Majaz Moonis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10405)


Machine learning methods are frequently used for data sets in many fields including medicine for purposes of feature extraction and pattern recognition. This study includes lesion data obtained from Magnetic Resonance images taken in three different years and belonging to 120 individuals (with 76 RRMS, 6 PPMS, 38 SPMS). Many alternative methods are used nowadays to be able to find out the strong and distinctive features of Multiple Sclerosis based on MR images. Deep learning has the working capacity pertaining to a much wider scaled space (120 \(\times \) 228), less dimension (50 \(\times \) 228) (also referred to as distinctive) feature space and SVM (120 \(\times \) 228). Deep learning has formed a more skillful system in the classification of MS subgroups by working with fewer sets of features compared to SVM algorithm. Deep learning algorithm has a better accuracy rate in comparing the MS subgroups compared to multiclass SVM algorithm kernel types which are among the conventional machine learning systems.


Deep learning Support vector machines kernel types Multiple Sclerosis subgroups MRI 


  1. 1.
    Duncan, I.D., Franklin, R.J.: Myelin Repair and Neuroprotection in Multiple Sclerosis, pp. 23–47. Springer Science and Business Media, Heidelberg (2012)Google Scholar
  2. 2.
    Murray, T.J., Saunders, C., Holland, N.J.: Multiple Sclerosis: A Guide for the Newly Diagnosed, pp. 1–39. Demos Medical Publishing, New York (2012)Google Scholar
  3. 3.
    Scalfari, A., Lederer, C., Daumer, M., Nicholas, R., Ebers, G.C., Muraro, P.A.: The relationship of age with the clinical phenotype in multiple sclero sis. Multiple Scler. J. 22(13), 1750–1758 (2016)CrossRefGoogle Scholar
  4. 4.
    McAlpine, D., Compston, A.: McAlpine’s Multiple Sclerosis, pp. 2–10. Elsevier Health Sciences, Amsterdam (2005)Google Scholar
  5. 5.
    Hirst, C., Ingram, G., Swingler, R., Compston, D.A.S., Pickersgill, T., Robertson, N.P.: Change in disability in patients with multiple sclerosis: a 20-year prospective population-based analysis. J. Neurol. Neurosurg. Psychiatry 79(10), 1137–1143 (2008)CrossRefGoogle Scholar
  6. 6.
    Liu, S., Liu, S., Cai, W., Pujol, S., Kikinis, R., Feng, D.: Early diagnosis of Alzheimer’s disease with deep learning. In: IEEE 11th International Symposium Biomedical Imaging (ISBI), pp. 1015–1018 (2014)Google Scholar
  7. 7.
    Xie, R., Quitadamo, A., Cheng, J., Shi, X.: A predictive model of gene expression using a deep learning framework. In: IEEE International Conference Bioinformatics and Biomedicine (BIBM), pp. 676–681 (2016)Google Scholar
  8. 8.
    Wang, A., Wang, J., Lin, H., Zhang, J., Yang, Z., Xu, K.: Biomedical event extraction based on distributed representation and deep learning. In: 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), p. 775 (2016)Google Scholar
  9. 9.
    Sarraf, S., Tofighi, G.: Deep learning-based pipeline to recognize Alzheimer’s disease using fMRI data. In: Future Technologies Conference, pp. 816–820 (2016)Google Scholar
  10. 10.
    Petersson, H., Gustafsson, D., Bergstrom, D.: Hyperspectral image analysis using deep learning: a review. In: 2016 6th International Conference Image Processing Theory Tools and Applications (IPTA), pp. 1–6 (2016)Google Scholar
  11. 11.
    Brosch, T., Yoo, Y., Li, D.K.B., Traboulsee, A., Tam, R.: Modeling the variability in brain morphology and lesion distribution in multiple sclerosis by deep learning. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8674, pp. 462–469. Springer, Cham (2014). doi: 10.1007/978-3-319-10470-6_58 Google Scholar
  12. 12.
    Brosch, T., Tang, L.Y., Yoo, Y., Li, D.K., Traboulsee, A., Tam, R.: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. IEEE Trans. Med. Imaging 35(5), 1229–1239 (2016)CrossRefGoogle Scholar
  13. 13.
    Karaca, Y., Zhang, Y., Cattani, C., Ayan, U.: The differential diagnosis of Multiple Sclerosis using convex combination of infinite kernels. CNS Neurol. Disord. Drug Targets 16(1), 36–43 (2017)CrossRefGoogle Scholar
  14. 14.
    Karaca, Y., Osman, O., Karabudak, R.: Linear modeling of multiple sclerosis and its subgroups. Turk. J. Neurol. 21, 7–13 (2015)CrossRefGoogle Scholar
  15. 15.
    Rajan, S.S.: MRI A Conceptual Overview. Library of Congress Catalog in Publication Data. Springer, New York (1998)Google Scholar
  16. 16.
    Mamoshina, P., Vieira, A., Putin, E., Zhavoronkov, A.: Applications of deep learning in biomedicine. Mol. Pharm. 13(5), 1445–1454 (2016)CrossRefGoogle Scholar
  17. 17.
    Deng, L., Yu, D.: Deep learning methods and applications. Found. Trends Sig. Process. 7(3–4), 230–239 (2014)MathSciNetGoogle Scholar
  18. 18.
    Graupe, D.: Deep Learning Neural Networks: Design and Case Studies, pp. 23–53. World Scientific Publishing, Singapore (2016)Google Scholar
  19. 19.
    Galas, D.J., Dewey, T.G., Kunert-Graf, J., Sakhanenko, N.A.: Expansion of the Kull back-Leibler divergence, and a new class of information metrics. Entropy Inf. Theor. MDPI 6(2), 8 (2017)Google Scholar
  20. 20.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, pp. 155–194. MIT Press, Cambridge (2016)Google Scholar
  21. 21.
    Suthaharan, S.: Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning, vol. 36. Springer (2015)Google Scholar
  22. 22.
    Han, J., Kamber, M., Pei, J.: Data Mining Concepts and Techniques, 3rd edn., pp. 408–413. Elsevier, Amsterdam (2012)Google Scholar
  23. 23.
    Amari, S.I., Wu, S.: Improving support vector machine classifiers by modifying kernel functions. Neural Netw. 12(6), 783–789 (1999)CrossRefGoogle Scholar
  24. 24.
    Fung, G.M., Mangasarian, O.L.: Multicategory proximal support vector machine classifiers. Mach. Learn. 1–21 (2004)Google Scholar
  25. 25.
    Karaca, Y., Hayta, Ş., Karabudak, R.: Case study application for C-support vector classification: the estimation of MS subgroup classification with selected kernels and parameters. Eur. J. Pure Appl. Math. 9(2), 196–215 (2016)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Visiting Engineering School (DEIM)Tuscia UniversityViterboItaly
  2. 2.Engineering School (DEIM)Tuscia UniversityViterboItaly
  3. 3.University of Massachusetts Medical SchoolWorcesterUSA

Personalised recommendations