Advertisement

Classification of FDG-PET Brain Data by Generalized Matrix Relevance LVQ

  • M. BiehlEmail author
  • D. Mudali
  • K. L. Leenders
  • J. B. T. M. Roerdink
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10087)

Abstract

We apply Generalized Matrix Learning Vector Quantization (GMLVQ) to the classification of Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) brain data. The aim is to achieve accurate detection and discrimination of neurodegenerative syndromes such as Parkinson’s Disease, Multiple System Atrophy and Progressive Supranuclear Palsy. Image data are pre-processed and analysed in terms of low-dimensional representations obtained by Principal Component Analysis in the Scaled Subprofile Model approach. The performance of the GMLVQ classifiers is evaluated in a Leave-One-Out framework. Comparison with earlier results shows that GMLVQ and Support Vector Machine with linear kernel achieve comparable performance while both outperform a C4-5 Decision Tree classifier.

Keywords

Support Vector Machine Multiple System Atrophy Receiver Operator Characteristic Progressive Supranuclear Palsy Progressive Supranuclear Palsy 
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.

References

  1. 1.
    Appel, L., Jonasson, M., Danfors, T., Nyholm, D., Askmark, H., Lubberink, M., Sörensen, J.: Use of 11C-PE2I PET in differential diagnosis of parkinsonian disorders. J. Nucl. Med. 56(2), 234–242 (2015)CrossRefGoogle Scholar
  2. 2.
    Silverman, D.H.: Brain 18F-FDG PET in the diagnosis of neurodegenerative dementias: comparison with perfusion SPECT and with clinical evaluations lacking nuclear imaging. J. Nucl. Med. 45(4), 594–607 (2004)Google Scholar
  3. 3.
    Eckert, T., Sailer, M., Kaufmann, J., Schrader, C., Peschel, T., Bodammer, N., Heinze, H.J., Schoenfeld, M.A.: Differentiation of idiopathic Parkinson’s disease, multiple system atrophy, progressive supranuclear palsy, and healthy controls using magnetization transfer imaging. Neuroimage 21(1), 229–235 (2004)CrossRefGoogle Scholar
  4. 4.
    van Laere, K., Casteels, C., de Ceuninck, L., Vanbilloen, B., Maes, A., Mortelmans, L., Vandenberghe, W., Verbruggen, A., Dom, R.: Dual-tracer dopamine transporter and perfusion SPECT in differential diagnosis of parkinsonism using template-based discriminant analysis. J. Nucl. Med. 47(3), 384–392 (2006)Google Scholar
  5. 5.
    Duda, R.O., Hart, P.E., Storck, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)Google Scholar
  6. 6.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn. Springer, New York (2009)CrossRefzbMATHGoogle Scholar
  7. 7.
    Shawe-Taylor, J., Christianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)CrossRefGoogle Scholar
  8. 8.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)CrossRefzbMATHGoogle Scholar
  9. 9.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  10. 10.
    Kohonen, T.: Self-organizing Maps. Springer, Heidelberg (1995)CrossRefzbMATHGoogle Scholar
  11. 11.
    Sato, A., Yamada, K. Generalized learning vector quantization. In: Advances in Neural Information Processing Systems, pp. 423–429 (1996)Google Scholar
  12. 12.
    Schneider, P., Biehl, M., Hammer, B.: Adaptive relevance matrices in learning vector quantization. Neural Comput. 21(12), 3532–3561 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Mudali, D., Teune, L.K., Renken, R.J., Leenders, K.L., Roerdink, J.: Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM, PCA features. Computational, Mathematical Methods in Medicine: Article ID 136921 (2015)Google Scholar
  14. 14.
    Mudali, D., Biehl, M., Leenders, K.L., Roerdink, J.B.T.M.: LVQ and SVM classification of FDG-PET brain data. In: Merényi, E., Mendenhall, M.J., O’Driscoll, P. (eds.) Advances in Self-Organizing Maps and Learning Vector Quantization. AISC, vol. 428, pp. 205–215. Springer, Heidelberg (2016). doi: 10.1007/978-3-319-28518-4_18 CrossRefGoogle Scholar
  15. 15.
    Biehl, M., Hammer, B., Villmann, T.: Distance measures for prototype based classification. In: Grandinetti, L., Lippert, T., Petkov, N. (eds.) BrainComp 2013. LNCS, vol. 8603, pp. 100–116. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-12084-3_9 Google Scholar
  16. 16.
    Biehl, M., Hammer, B., Villmann, T.: Prototype-based models in machine learning. Wileys Interdisciplinary Reviews (WIRES). Cogn. Sci. 7(2), 92–111 (2016)Google Scholar
  17. 17.
    Teune, L.K., Bartels, A.L., de Jong, B.M., Willemsen, A.T., Eshuis, S.A., de Vries, J.J., van Oostrom, J.C., Leenders, K.L.: Typical cerebral metabolic patterns in neurodegenerative brain diseases. Mov. Disord. 25(14), 2395–2404 (2010)CrossRefGoogle Scholar
  18. 18.
    Moeller, J.R., Strother, S.C., Sidtis, J.J., Rottenberg, D.A.: Scaled subprofile model: a statistical approach to the analysis of functional patterns in positron emission tomographic data. J. Cereb. Blood Flow Metab. 7(5), 649–658 (1987)CrossRefGoogle Scholar
  19. 19.
    Moeller, J.R., Strother, S.C.: A regional covariance approach to the analysis of functional patterns in positron emission tomographic data. J. Cereb. Blood Flow Metab. 11(2), A121–135 (1991)CrossRefGoogle Scholar
  20. 20.
    Spetsieris, P.G., Eidelberg, D.: Scaled subprofile modeling of resting state imaging data in Parkinson’s disease: Methodological issues. NeuroImage 54(4), 2899–2914 (2011)CrossRefGoogle Scholar
  21. 21.
    Spetsieris, P.G., Ma, Y., Dhawan, V., Eidelberg, D.: Differential diagnosis of parkinsonian syndromes using PCA-based functional imaging features. NeuroImage 45(4), 1241–1252 (2009)CrossRefGoogle Scholar
  22. 22.
    Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861–874 (2006)CrossRefGoogle Scholar
  23. 23.
    Arlt, W., Biehl, M., Taylor, A.E., et al.: Urine steroid metabolomics as a biomarker tool for detecting malignancy in adrenal tumors. J. Clin. Endocrinol. Metab. 96, 3775–3784 (2011)CrossRefGoogle Scholar
  24. 24.
    Biehl, M., Bunte, K., Schneider, P.: Analysis of flow cytometry data by matrix relevance learning vector quantization. PLoS ONE 8(3), e59401 (2013)CrossRefGoogle Scholar
  25. 25.
    Leo, Y., Adlard, N., Biehl, M., Juarez, M., Smallie, T., Snow, M., Buckley, C.D., Raza, K., Filer, A., Scheel-Toellner, D.: Expression of chemokines CXCL4 and CXCL7 by synovial macrophages defines early stages of rheumatoid arthritis. Ann. Rheum. Dis. 75, 763–771 (2016)CrossRefGoogle Scholar
  26. 26.
    Bunte, K., Schneider, P., Hammer, B., Schleif, F.-M., Villmann, T., Biehl, M.: Limited rank matrix learning, discriminative dimension reduction and visualization. Neural Netw. 26, 159–173 (2012)CrossRefGoogle Scholar
  27. 27.
    Mahalanobis, P.C.: On the generalized distance in statistics. Proc. Natl. Instit. Sci. India 2, 49–55 (1936)zbMATHGoogle Scholar
  28. 28.
    Biehl, M.: A no-nonsense Matlab (TM) toolbox for GMLVQ (2015). http://www.cs.rug.nl/biehl/gmlvq.html. Accessed 16 Mar 2016
  29. 29.
    Papari, G., Bunte, K., Biehl, M.: Waypoint Averaging and step size control in learning by gradient descent. Machine Learning Reports MLR-2011-06, pp. 16–26 (2011)Google Scholar
  30. 30.
    Biehl, M., Hammer, B., Schleif, F.-M., Schneider, P., Villmann, T.: Stationarity of Matrix Relevance LVQ. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2015), 8 p. IEEE (2015)Google Scholar
  31. 31.
    Burges, C.J.: A tutorial on support vector machines for pattern recognition. Data Mining Knowl. Discov. 2(2), 121–167 (1998)CrossRefGoogle Scholar
  32. 32.
    Hsu, C.W., Lin, C.J.: A comparison of methods for multiclass support vector machines. IEEE Trans. Neural Netw. 13(2), 415–425 (2002)CrossRefGoogle Scholar
  33. 33.
    Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011). software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • M. Biehl
    • 1
    Email author
  • D. Mudali
    • 1
  • K. L. Leenders
    • 2
  • J. B. T. M. Roerdink
    • 1
    • 3
  1. 1.Johann Bernoulli Institute for Mathematics and Computer ScienceUniversity of GroningenGroningenThe Netherlands
  2. 2.Department of NeurologyUniversity Medical Center GroningenGroningenThe Netherlands
  3. 3.Neuroimaging Center, University Medical Center GroningenGroningenThe Netherlands

Personalised recommendations