Advertisement

Maximum Mean Discrepancy Based Multiple Kernel Learning for Incomplete Multimodality Neuroimaging Data

  • Xiaofeng Zhu
  • Kim-Han Thung
  • Ehsan Adeli
  • Yu Zhang
  • Dinggang ShenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10435)

Abstract

It is challenging to use incomplete multimodality data for Alzheimer’s Disease (AD) diagnosis. The current methods to address this challenge, such as low-rank matrix completion (i.e., imputing the missing values and unknown labels simultaneously) and multi-task learning (i.e., defining one regression task for each combination of modalities and then learning them jointly), are unable to model the complex data-to-label relationship in AD diagnosis and also ignore the heterogeneity among the modalities. In light of this, we propose a new Maximum Mean Discrepancy (MMD) based Multiple Kernel Learning (MKL) method for AD diagnosis using incomplete multimodality data. Specifically, we map all the samples from different modalities into a Reproducing Kernel Hilbert Space (RKHS), by devising a new MMD algorithm. The proposed MMD method incorporates data distribution matching, pair-wise sample matching and feature selection in an unified formulation, thus alleviating the modality heterogeneity issue and making all the samples comparable to share a common classifier in the RKHS. The resulting classifier obviously captures the nonlinear data-to-label relationship. We have tested our method using MRI and PET data from Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset for AD diagnosis. The experimental results show that our method outperforms other methods.

References

  1. 1.
    Adeli, E., et al.: Joint feature-sample selection and robust diagnosis of parkinson’s disease from MRI data. NeuroImage 141, 206–219 (2016)CrossRefGoogle Scholar
  2. 2.
    Adeli, E., et al.: Kernel-based joint feature selection and max-margin classification for early diagnosis of parkinson disease. Sci. Reports 7 (2017)Google Scholar
  3. 3.
    Bach, F.R., et al.: Multiple kernel learning, conic duality, and the SMO algorithm. In: ICML, p. 6 (2004)Google Scholar
  4. 4.
    Borgwardt, K.M., et al.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14), e49–e57 (2006)CrossRefGoogle Scholar
  5. 5.
    Hor, S., Moradi, M.: Learning in data-limited multimodal scenarios: scandent decision forests and tree-based features. Med. Image Anal. 34, 30–41 (2016)CrossRefGoogle Scholar
  6. 6.
    Hu, R., et al.: Graph self-representation method for unsupervised feature selection. Neurocomputing 220, 130–137 (2017)CrossRefGoogle Scholar
  7. 7.
    Rakotomamonjy, A., et al.: SimpleMKL. J. Mach. Learn. Res. 9, 2491–2521 (2008)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Thung, K., et al.: Neurodegenerative disease diagnosis using incomplete multi-modality data via matrix shrinkage and completion. NeuroImage 91, 386–400 (2014)CrossRefGoogle Scholar
  9. 9.
    Thung, K.-H., Adeli, E., Yap, P.-T., Shen, D.: Stability-weighted matrix completion of incomplete multi-modal data for disease diagnosis. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 88–96. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_11 CrossRefGoogle Scholar
  10. 10.
    Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Royal Stat. Soc. Ser. B (Methodol.) 58, 267–288 (1996)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Yuan, L., et al.: Multi-source feature learning for joint analysis of incomplete multiple heterogeneous neuroimaging data. NeuroImage 61(3), 622–632 (2012)CrossRefGoogle Scholar
  12. 12.
    Zhang, S., et al.: Learning k for kNN classification. ACM TIST 8(3), 43:1–43:19 (2017)Google Scholar
  13. 13.
    Zhu, X., et al.: Subspace regularized sparse multitask learning for multiclass neurodegenerative disease identification. IEEE Trans. Biomed. Eng. 63(3), 607–618 (2016)CrossRefGoogle Scholar
  14. 14.
    Zhu, X., et al.: A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. Med. Image Anal. 38, 205–214 (2017)CrossRefGoogle Scholar
  15. 15.
    Zhu, X., et al.: Robust joint graph sparse coding for unsupervised spectral feature selection. IEEE Trans. Neural Netw. Learning Syst. 28(6), 1263–1275 (2017)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Zhu, Y., et al.: Early diagnosis of Alzheimer disease by joint feature selection and classification on temporally structured support vector machine. In: MICCAI, pp. 264–272 (2016)Google Scholar
  17. 17.
    Zhu, Y., Zhu, X., Zhang, H., Gao, W., Shen, D., Wu, G.: Reveal consistent spatial-temporal patterns from dynamic functional connectivity for autism spectrum disorder identification. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 106–114. Springer, Cham (2016). doi: 10.1007/978-3-319-46720-7_13 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Xiaofeng Zhu
    • 1
  • Kim-Han Thung
    • 1
  • Ehsan Adeli
    • 1
  • Yu Zhang
    • 1
  • Dinggang Shen
    • 1
    Email author
  1. 1.Department of Radiology and BRICUniversity of North Carolina at Chapel HillChapel HillUSA

Personalised recommendations