Advertisement

Randomized Denoising Autoencoders for Smaller and Efficient Imaging Based AD Clinical Trials

  • Vamsi K. Ithapu
  • Vikas Singh
  • Ozioma Okonkwo
  • Sterling C. Johnson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)

Abstract

There is growing body of research devoted to designing imaging-based biomarkers that identify Alzheimer’s disease (AD) in its prodromal stage using statistical machine learning methods. Recently several authors investigated how clinical trials for AD can be made more efficient (i.e., smaller sample size) using predictive measures from such classification methods. In this paper, we explain why predictive measures given by such SVM type objectives may be less than ideal for use in the setting described above. We give a solution based on a novel deep learning model, randomized denoising autoencoders (rDA), which regresses on training labels y while also accounting for the variance, a property which is very useful for clinical trial design. Our results give strong improvements in sample size estimates over strategies based on multi-kernel learning. Also, rDA predictions appear to more accurately correlate to stages of disease. Separately, our formulation empirically shows how deep architectures can be applied in the large d, small n regime — the default situation in medical imaging. This result is of independent interest.

Keywords

Mild Cognitively Impaired Deep Learning Weak Learner Prediction Variance Deep Architecture 
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.
    Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2, 1–127 (2009)CrossRefGoogle Scholar
  2. 2.
    Dietterich, T.G.: Machine-learning research. AI Magazine 18(4), 97–136 (1997)zbMATHGoogle Scholar
  3. 3.
    Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? JMLR 11, 625–660 (2010)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Grill, J.D., Di, L., Lu, P.H., Lee, C., Ringman, J., Apostolova, L.G., et al.: Estimating sample sizes for predementia Alzheimer’s trials based on the Alzheimer’s Disease Neuroimaging Initiative. Neurobiology of Aging 34, 62–72 (2013)CrossRefGoogle Scholar
  5. 5.
    Gupta, A., Ayhan, M., Maida, A.: Natural image bases to represent neuroimaging data. In: Proceedings of the 30th ICML, pp. 987–994 (2013)Google Scholar
  6. 6.
    Hinrichs, C., Dowling, N.M., Johnson, S.C., Singh, V.: MKL-based sample enrichment and customized outcomes enable smaller AD clinical trials. In: Langs, G. (ed.) MLINI 2011. LNCS (LNAI), vol. 7263, pp. 124–131. Springer, Heidelberg (2012)Google Scholar
  7. 7.
    Hinrichs, C., Singh, V., Xu, G., Johnson, S.C.: Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population. Neuroimage 55, 574–589 (2011)CrossRefGoogle Scholar
  8. 8.
    Holland, D., McEvoy, L.K., Dale, A.M.: Unbiased comparison of sample size estimates from longitudinal structural measures in ADNI. Human Brain Mapping 33(11), 2586–2602 (2012)CrossRefGoogle Scholar
  9. 9.
    Kohannim, O., Hua, X., Hibar, D.P., Lee, S., Chou, Y.Y., Toga, A.W., Jack Jr., C.R., Weiner, M.W., Thompson, P.M.: Boosting power for clinical trials using classifiers based on multiple biomarkers. Neurobiology of Aging 31, 1429–1442 (2010)CrossRefGoogle Scholar
  10. 10.
    Plis, S.M., Hjelm, D.R., Salakhutdinov, R., Calhoun, V.D.: Deep learning for neuroimaging: a validation study. arXiv preprint arXiv:1312.5847 (2013)Google Scholar
  11. 11.
    Sakpal, T.V.: Sample size estimation in clinical trial. Perspectives in Clinical Research 1(2), 67–69 (2010)Google Scholar
  12. 12.
    Suk, H.-I., Shen, D.: Deep learning-based feature representation for AD/MCI classification. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 583–590. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  13. 13.
    Tatsuoka, C., Tseng, H., Jaeger, J., Varadi, F., Smith, M.A., Yamada, T., et al.: Modeling the heterogeneity in risk of progression to Alzheimer’s disease across cognitive profiles in mild cognitive impairment. Alzheimers Res. Ther. 5, 14 (2013)CrossRefGoogle Scholar
  14. 14.
    Teipel, S.J., Born, C., Ewers, M., Bokde, A.L., Reiser, M.F., Möller, H.J., Hampel, H.: Multivariate deformation-based analysis of brain atrophy to predict Alzheimer’s disease in mild cognitive impairment. Neuroimage 38, 13–24 (2007)CrossRefGoogle Scholar
  15. 15.
    Vemuri, P., Wiste, H., et al.: MRI and CSF biomarkers in normal, MCI, and AD subjects predicting future clinical change. Neurology 73(4), 294–301 (2009)CrossRefGoogle Scholar
  16. 16.
    Zhang, D., Wang, Y., Zhou, L., et al.: Multimodal classification of Alzheimer’s disease and mild cognitive impairment. Neuroimage 55(3), 856–867 (2011)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Vamsi K. Ithapu
    • 1
  • Vikas Singh
    • 1
  • Ozioma Okonkwo
    • 1
  • Sterling C. Johnson
    • 1
    • 2
  1. 1.University of WisconsinMadisonUSA
  2. 2.William S. Middleton Memorial VA HospitalUSA

Personalised recommendations