fMRI Multiple Missing Values Imputation Regularized by a Recurrent Denoiser

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12721)


Functional Magnetic Resonance Imaging (fMRI) is a neuroimaging technique with pivotal importance due to its scientific and clinical applications. As with any widely used imaging modality, there is a need to ensure the quality of the same, with missing values being highly frequent due to the presence of artifacts or sub-optimal imaging resolutions. Our work focus on missing values imputation on multivariate signal data. To do so, a new imputation method is proposed consisting on two major steps: spatial-dependent signal imputation and time-dependent regularization of the imputed signal. A novel layer, to be used in deep learning architectures, is proposed in this work, bringing back the concept of chained equations for multiple imputation [26]. Finally, a recurrent layer is applied to tune the signal, such that it captures its true patterns. Both operations yield an improved robustness against state-of-the-art alternatives. The code is made available on Github.



This work was supported by national funds through Fundação para a Ciência e Tecnologia (FCT), for the Ph.D. Grant DFA/BD/5762/2020, ILU project DSAIPA/DS/0111/2018 and INESC-ID pluriannual UIDB/50021/2020.


  1. 1.
    Birn, R.M.: The role of physiological noise in resting-state functional connectivity. Neuroimage (2012)Google Scholar
  2. 2.
    Cao, W., Wang, D., Li, J., Zhou, H., Li, L., Li, Y.: Bidirectional recurrent imputation for time series. In: NIPS, Brits (2018)Google Scholar
  3. 3.
    Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Scientific reports (2018)Google Scholar
  4. 4.
    Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv (2014)Google Scholar
  5. 5.
    Conroy, B.R., Walz, J.M., Sajda, P.: Fast bootstrapping and permutation testing for assessing reproducibility and interpretability of multivariate fMRI decoding models. PLoS ONE (2013)Google Scholar
  6. 6.
    Deligianni, F., Carmichael, D.W., Zhang, G.H., Clark, C.A., Clayden, J.D.: Noddi and tensor-based microstructural indices as predictors of functional connectivity. PLoS ONE (2016)Google Scholar
  7. 7.
    Deligianni, F., Centeno, M., Carmichael, D.W., Clayden, J.D.: Relating resting-state fMRI and EEG whole-brain connectomes across frequency bands. Front. Neurosci. (2014)Google Scholar
  8. 8.
    Fortuin, V., Baranchuk, D., Rätsch, G., Mandt, S.: GP-VAE: deep probabilistic time series imputation. arXiv (2019)Google Scholar
  9. 9.
    Goodfellow, I., et al.: Generative adversarial nets. In NIPS, Sherjil Ozair (2014)Google Scholar
  10. 10.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, New York (2001)CrossRefGoogle Scholar
  11. 11.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)Google Scholar
  12. 12.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv (2013)Google Scholar
  13. 13.
    Lu, R., Duan, Z.: Bidirectional GRU for sound event detection. Detection and Classification of Acoustic Scenes and Events (2017)Google Scholar
  14. 14.
    Luo, Y., Cai, X., Zhang, Y., Xu, J., et al.: Multivariate time series imputation with generative adversarial networks. In: NIPS (2018)Google Scholar
  15. 15.
    Luo, Y., Cai, X., Zhang, Y., Xu, J., Xiaojie, Y.: Multivariate time series imputation with generative adversarial networks. In: NIPS (2018)Google Scholar
  16. 16.
    Pan, J.-Y., Yang, H.-J., Faloutsos, C., Duygulu, P.: Automatic multimedia cross-modal correlation discovery. In: ACM SIGKDD (2004)Google Scholar
  17. 17.
    Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)Google Scholar
  18. 18.
    Petitjean, F., Ketterlin, A., Gançarski, P.: A global averaging method for dynamic time warping, with applications to clustering. Pattern Recogn. (2011)Google Scholar
  19. 19.
    Śmieja, M., Struski, Ł., Tabor, J., Zieliński, B., Spurek, P.: Processing of missing data by neural networks. In: NIPS (2018)Google Scholar
  20. 20.
    Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS (2012)Google Scholar
  21. 21.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR (2014)Google Scholar
  22. 22.
    Tran, L., Liu, X., Zhou, J., Jin, R.: Missing modalities imputation via cascaded residual autoencoder. In: CVPR (2017)Google Scholar
  23. 23.
    Walz, J.M., Goldman, R.I., Carapezza, M., Muraskin, J., Brown, T.R., Sajda, P.: Simultaneous EEG-fMRI reveals temporal evolution of coupling between supramodal cortical attention networks and the brainstem. J. Neurosci. (2013)Google Scholar
  24. 24.
    Walz, J.M., Goldman, R.I., Carapezza,, M., Muraskin, J., Brown, T.R., Sajda, P.: Simultaneous eeg-fmri reveals a temporal cascade of task-related and default-mode activations during a simple target detection task. Neuroimage (2014)Google Scholar
  25. 25.
    Wehrl, H.F., et al.: Simultaneous pet-MRI reveals brain function in activated and resting state on metabolic, hemodynamic and multiple temporal scales. Nature Med. (2013)Google Scholar
  26. 26.
    White, I., Royston, P., Wood, A.: Multiple imputation using chained equations: issues and guidance for practice. Stat. Med. (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Instituto Superior TécnicoLisbonPortugal

Personalised recommendations