Advertisement

Efficient and Automatic Subspace Relevance Determination via Multiple Kernel Learning for High-Dimensional Neuroimaging Data

  • Murat Seçkin Ayhan
  • Vijay Raghavan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11309)

Abstract

Alzheimer’s disease is a major cause of dementia. Its pathology induces complex spatial patterns of brain atrophy that evolve as the disease progresses. The diagnosis requires accurate biomarkers that are sensitive to disease stages. Probabilistic biomarkers naturally support the interpretation of decisions and evaluation of uncertainty associated with them. We obtain probabilistic biomarkers via Gaussian Processes, which also offer flexible means to accomplish Multiple Kernel Learning. Exploiting this flexibility, we propose a novel solution, Multiple Kernel Learning for Automatic Subspace Relevance Determination, to tackle the challenges of working with high-dimensional neuroimaging data. The proposed Gaussian Process models are competitive with or better than the well-known Support Vector Machine in terms of classification performance even in the cases of single kernel learning. Also, our method improves the capability of the Gaussian Process models and their interpretability in terms of the known anatomical correlates of the disease.

Keywords

Gaussian processes MRI Alzheimer’s Disease 

Notes

Acknowledgements

Data used in this study are from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). For up-to-date information, see www.adni-info.org or adni.loni.usc.edu.

Majority of this work was completed at the Center for Advanced Computer Studies, University of Louisiana at Lafayette, where M.S.A completed his graduate studies under the supervision of V.R.

References

  1. 1.
    Ashburner, J., et al.: SPM8 Manual, July 2010Google Scholar
  2. 2.
    Association, A., et al.: 2018 Alzheimer’s disease facts and figures. Alzheimers Dement. 14(3), 367–429 (2018)CrossRefGoogle Scholar
  3. 3.
    Ayhan, M.S., Benton, R.G., Choubey, S., Raghavan, V.V.: Utilization of domain-knowledge for simplicity and comprehensibility in predictive modeling of Alzheimer’s disease. In: Proceedings of the 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW), BIBMW 2012, pp. 265–272 (2012)Google Scholar
  4. 4.
    Ayhan, M.S., Benton, R.G., Raghavan, V.V., Choubey, S.: Composite kernels for automatic relevance determination in computerized diagnosis of Alzheimer’s disease. In: Imamura, K., Usui, S., Shirao, T., Kasamatsu, T., Schwabe, L., Zhong, N. (eds.) BHI 2013. LNCS (LNAI), vol. 8211, pp. 126–137. Springer, Cham (2013).  https://doi.org/10.1007/978-3-319-02753-1_13CrossRefGoogle Scholar
  5. 5.
    Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML 2004, pp. 6–13 (2004)Google Scholar
  6. 6.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011)CrossRefGoogle Scholar
  7. 7.
    Fan, Y., Batmanghelich, N., Clark, C.M., Davatzikos, C.: Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline. NeuroImage 39(4), 1731–1743 (2008).  https://doi.org/10.1016/j.neuroimage.2007.10.031CrossRefGoogle Scholar
  8. 8.
    Gupta, A., Ayhan, M.S., Maida, A.S.: Natural image bases to represent neuroimaging data. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), ICML 2013, June 2013Google Scholar
  9. 9.
    Hinrichs, C., Singh, V., Peng, J., Johnson, S.C.: Q-MKL:Matrix-induced regularization in multi-kernel learning withapplications to neuroimaging. In: NIPS, pp. 1430–1438 (2012)Google Scholar
  10. 10.
    Imabayashi, E., et al.: Superiority of 3-dimensional stereotactic surface projection analysis over visual inspection in discrimination of patients with very early Alzheimer’s disease from controls using brain perfusion SPECT. J. Nucl. Med. 45(9), 1450–1457 (2004)Google Scholar
  11. 11.
    Klöppel, S., Stonnington, C.M., Barnes, J., Chen, F., Chu, C., Good, C.D., Mader, I., Mitchell, L.A., Patel, A.C., Roberts, C.C., et al.: Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method. Brain 131(11), 2969–2974 (2008)CrossRefGoogle Scholar
  12. 12.
    MacKay, D.J.C.: Bayesian methods for backpropagation networks. In: Domany, E., van Hemmen, J.L., Schulten, K. (eds.) Models of Neural Networks III. Physics of Neural Networks, pp. 211–254. Springer, New York (1996)CrossRefGoogle Scholar
  13. 13.
    Matsuda, H.: Role of neuroimaging in Alzheimer’s disease, with emphasis on brain perfusion spect. J. Nucl. Med. 48(8), 1289–1300 (2007)CrossRefGoogle Scholar
  14. 14.
    Minoshima, S., Frey, K.A., Koeppe, R.A., Foster, N.L., Kuhl, D.E.: A diagnostic approach in Alzheimer’s disease using three-dimensional stereotactic surface projections of fluorine-18-FDG PET. J. Nucl. Med. 36(7), 1238–1248 (1995)Google Scholar
  15. 15.
    Neal, R.M.: Bayesian Learning for Neural Networks. Springer, New York (1996).  https://doi.org/10.1007/978-1-4612-0745-0CrossRefzbMATHGoogle Scholar
  16. 16.
    Nickisch, H., Rasmussen, C.E.: Approximations for binary Gaussian process classification. J. Mach. Learn. Res. 9, 2035–2078 (2008)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Petersen, R.C.: Current concepts in mild cognitive impairment. Arch. Neurol. 58(12), 1985 (2001)CrossRefGoogle Scholar
  18. 18.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10(3), 61–74 (1999)Google Scholar
  19. 19.
    Rasmussen, C.E., Nickisch, H.: Gaussian processes for machine learning (GPML) toolbox. J. Mach. Learn. Res. 9999, 3011–3015 (2010)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2005)Google Scholar
  21. 21.
    Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  22. 22.
    Thatcher, R.W.: Functional Neuroimaging: Technical Foundations. Academic Press, San Diego (1994)Google Scholar
  23. 23.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995).  https://doi.org/10.1007/978-1-4757-3264-1CrossRefzbMATHGoogle Scholar
  24. 24.
    Whitwell, J.L., Przybelski, S.A., Weigand, S.D., Knopman, D.S., Boeve, B.F., Petersen, R.C., Jack, C.R.: 3D maps from multiple MRI illustrate changing atrophy patterns as subjects progress from mild cognitive impairment to Alzheimer’s disease. Brain 130(7), 1777–1786 (2007)CrossRefGoogle Scholar
  25. 25.
    Williams, C.K.I., Barber, D.: Bayesian classification with Gaussian processes. IEEE Trans. Pattern Anal. Mach. Intell. 20(12), 1342–1351 (1998)CrossRefGoogle Scholar
  26. 26.
    Wipf, D.P., Nagarajan, S.S.: A new view of automatic relevance determination. In: Advances in Neural Information Processing Systems, pp. 1625–1632 (2007)Google Scholar
  27. 27.
    Wu, T.F., Lin, C.J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. J. Mach. Learn. Res. 5, 975–1005 (2004)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Institute for Ophthalmic ResearchUniversity of TübingenTübingenGermany
  2. 2.Center for Advanced Computer StudiesUniversity of LouisianaLafayetteUSA

Personalised recommendations