Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Multidimensional clinical data denoising via Bayesian CP factorization

  • 44 Accesses

Abstract

CANDECOMP/PARAFAC (CP) tensor factorization is an efficient technique for incomplete tensor-data processing through capturing the multilinear latent factors. Based on the incorporate a sparsity-inducing prior over multiple latent factors and appropriate hyper-priors over all hyper-parameters, a Bayesian-based hierarchical probabilistic CP factorization model could be formed. By this way, the rank of the incomplete tensor can be determined automatically. In this paper, we explored the tensor completion method in processing incomplete multidimensional electroencephalogram (EEG) and magnetic resonance imaging (MRI) clinical data. The empirical results indicated that the Bayesian CP tensor factorization of incomplete data method can effectively recover EEG signal with missing data and denoised the noisy MRI data.

This is a preview of subscription content, log in to check access.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

References

  1. 1

    Acar E, Rasmussen M A, Savorani F, et al. Understanding data fusion within the framework of coupled matrix and tensor factorizations. Chemometr Intell Lab Syst, 2013, 129: 53–63

  2. 2

    Jafari M G, Chambers J A. Fetal electrocardiogram extraction by sequential source separation in the wavelet domain. IEEE Trans Biomed Eng, 2005, 52: 390–400

  3. 3

    Kolda T G, Bader B W. Tensor decompositions and applications. SIAM Rev, 2009, 51: 455–500

  4. 4

    Zhou G, Cichocki A, Zhao Q, et al. Nonnegative matrix and tensor factorizations: An algorithmic perspective. IEEE Signal Process Mag, 2014, 31: 54–65

  5. 5

    Cichocki A, Washizawa Y, Rutkowski T, et al. Noninvasive BCIs: Multiway signal-processing array decompositions. Computer, 2008, 41: 34–42

  6. 6

    Cichocki A, Zdunek R, Phan A H, et al. Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-Way Data Analysis and Blind Source Separation. Chichester: John Wiley & Sons, 2009

  7. 7

    Basser P J, Pajevic S. Spectral decomposition of a 4th-order covariance tensor: Applications to diffusion tensor MRI. Signal Process, 2007, 87: 220–236

  8. 8

    Zhao Q, Zhang L, Cichocki A. Bayesian sparse Tucker models for dimension reduction and tensor completion. arXiv: 1505.02343

  9. 9

    Cichocki A. Tensor networks for big data analytics and large-scale optimization problems. arXiv: 1407.3124

  10. 10

    Papalexakis E E, Faloutsos C, Mitchell T M, et al. Turbo-SMT: Accelerating coupled sparse matrix-tensor factorizations by 200x. In: Proceedings of the 2014 SIAM International Conference on Data Mining. Philadelphia: Society for Industrial and Applied Mathematics, 2014. 118–126

  11. 11

    Yokota T, Zhao Q, Cichocki A. Smooth PARAFAC decomposition for tensor completion. IEEE Trans Signal Process, 2016, 64: 5423–5436

  12. 12

    Gastaldo P, Pinna L, Seminara L, et al. A tensor-based approach to touch modality classification by using machine learning. Robot Autonom Syst, 2015, 63: 268–278

  13. 13

    Levine Y, Yakira D, Cohen N, et al. Deep learning and quantum entanglement: Fundamental connections with implications to network design. arXiv: 1704.01552

  14. 14

    Zhou G, Zhao Q, Zhang Y, et al. Linked component analysis from matrices to high-order tensors: Applications to biomedical data. Proc IEEE, 2016, 104: 310–331

  15. 15

    Cong F, Lin Q H, Kuang L D, et al. Tensor decomposition of EEG signals: A brief review. J Neurosci Methods, 2015, 248: 59–69

  16. 16

    Kim Y D, Choi S. Nonnegative tucker decomposition. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007. 1–8

  17. 17

    Karami A, Yazdi M, Mercier G. Compression of hyperspectral images using discerete wavelet transform and tucker decomposition. IEEE J Sel Top Appl Earth Obs Remote Sens, 2012, 5: 444–450

  18. 18

    Stegeman A, Sidiropoulos N D. On Kruskal’s uniqueness condition for the CANDECOMP/PARAFAC decomposition. Linear Algebra Appl, 2007, 420: 540–552

  19. 19

    Jiang T, Sidiropoulos N D. Kruskal’s permutation lemma and the identification of CANDECOMP/PARAFAC and bilinear models with constant modulus constraints. IEEE Trans Signal Process, 2004, 52: 2625–2636

  20. 20

    Novikov A, Podoprikhin D, Osokin A, et al. Tensorizing neural networks. In: Advances in Neural Information Processing Systems. Montreal, 2015. 442–450

  21. 21

    Oseledets I V. Tensor-train decomposition. SIAM J Sci Comput, 2011, 33: 2295–2317

  22. 22

    Zhao Q, Zhou G, Xie S, et al. Tensor ring decomposition. arXiv: 1606.05535

  23. 23

    Zhao Q, Sugiyama M, Cichocki A. Learning efficient tensor representations with ring structure networks. arXiv: 1705.08286

  24. 24

    Yuan L, Li C, Mandic D, et al. Rank minimization on tensor ring: A new paradigm in scalable tensor decomposition and completion. arXiv: 1805.08468

  25. 25

    McConnell A J. Applications of Tensor Analysis. New York: Courier Corporation, 2014

  26. 26

    Mori S, Zhang J. Principles of diffusion tensor imaging and its applications to basic neuroscience research. Neuron, 2006, 51: 527–539

  27. 27

    Sundgren P C, Dong Q, Gómez-Hassan D, et al. Diffusion tensor imaging of the brain: review of clinical applications. Neuroradiology, 2004, 46: 339–350

  28. 28

    Rajwade A, Rangarajan A, Banerjee A. Image denoising using the higher order singular value decomposition. IEEE Trans Pattern Anal Mach Intell, 2013, 35: 849–862

  29. 29

    Zhang X, Xu Z, Jia N, et al. Denoising of 3D magnetic resonance images by using higher-order singular value decomposition. Med Image Anal, 2015, 19: 75–86

  30. 30

    Ding C, Huang H, Luo D. Tensor reduction error analysis—Applications to video compression and classification. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008. 1–8

  31. 31

    Lei C, Yang Y H. Tri-focal tensor-based multiple video synchronization with subframe optimization. IEEE Trans Image Process, 2006, 15: 2473–2480

  32. 32

    Gandy S, Recht B, Yamada I. Tensor completion and low-n-rank tensor recovery via convex optimization. Inverse Problems, 2011, 27: 025010

  33. 33

    Cichocki A. Tensor decompositions: A new concept in brain data analysis? arXiv: 1305.0395

  34. 34

    Zhao Q, Zhang L, Cichocki A. Bayesian CP factorization of incomplete tensors with automatic rank determination. IEEE Trans Pattern Anal Mach Intell, 2015, 37: 1751–1763

  35. 35

    Kolda T G, Sun J. Scalable tensor decompositions for multi-aspect data mining. In: 2008 Eighth IEEE International Conference on Data Mining. Pisa: IEEE, 2008. 363–372

  36. 36

    Sobral A, Javed S, Ki Jung S, et al. Online stochastic tensor decomposition for background subtraction in multispectral video sequences. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. Santiago du Chili, 2015. 106–113

  37. 37

    Calhoun V D, Adali T. Unmixing fMRI with independent component analysis. IEEE Eng Med Biol Mag, 2006, 25: 79–90

Download references

Author information

Correspondence to QiBin Zhao or JianHai Zhang or JianTing Cao.

Additional information

This work was supported by the JSPS KAKENHI, Japan (Grant Nos. 17K00326 and 18K04178), the National Natural Science Foundation of China (Grant Nos. 61773129, 61633010) and the JST CREST, Japan (Grant No. JPMJCR1784).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cui, G., Zhu, L., Gui, L. et al. Multidimensional clinical data denoising via Bayesian CP factorization. Sci. China Technol. Sci. 63, 249–254 (2020). https://doi.org/10.1007/s11431-018-9493-9

Download citation

Keywords

  • electroencephalogram (EEG)
  • magnetic resonance imaging (MRI)
  • Bayesian
  • tensor factorization
  • CANDECOMP/PARAFAC (CP)