Advertisement

Exploring Brain Hemodynamic Response Patterns via Deep Recurrent Autoencoder

  • Shijie ZhaoEmail author
  • Yan Cui
  • Yaowu Chen
  • Xin Zhang
  • Wei Zhang
  • Huan Liu
  • Junwei Han
  • Lei Guo
  • Li XieEmail author
  • Tianming Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11846)

Abstract

For decades, task-based functional MRI (tfMRI) has been widely used in exploring functional brain networks and modeling brain activities. A variety of brain activity analysis methods for tfMRI data have been developed. However, these methods are mainly shallow models and are limited in faithfully modeling the complex spatial-temporal diverse and concurrent functional brain activities. Recently, recurrent neural networks (RNNs) demonstrate great superiority in modeling temporal dependency signals and autoencoder models have been proven to be effective in automatically estimating the optimal representations of the original data. These characteristics meet the requirement of modeling hemodynamic response patterns in tfMRI data. In order to take the advantages of both models, we proposed a novel unsupervised framework of deep recurrent autoencoder (DRAE) for modeling tfMRI data in this work. The basic idea of the DRAE model is to combine the deep recurrent neural network and autoencoder to automatically characterize the meaningful functional brain networks and corresponding diverse and complex hemodynamic response patterns underlying tfMRI data simultaneously. The proposed DRAE model has been tested on the motor tfMRI dataset of HCP 900 subjects release and all seven tfMRI datasets of HCP Q1 release. Extensive experimental results demonstrated the great superiority of the proposed method.

Keywords

Task fMRI Brain network Hemodynamic response pattern RNN Autoencoder Deep learning 

Notes

Acknowledgements

This work was supported by the National Science Foundation of China (61806167, 61603399, 31627802 and U1801265), the Fundamental Research Funds for the Central Universities (3102019PJ005), Natural Science Basic Research Plan in Shaanxi Province of China (2019JQ-630) and the China Postdoctoral Science Foundation (2019T120945).

References

  1. 1.
    Logothetis, N.K.: What we can do and what we cannot do with fMRI. Nature 453, 869–878 (2008)CrossRefGoogle Scholar
  2. 2.
    Friston, K.J., Holmes, A.P., Worsley, K.J., Poline, J.P., Frith, C.D., Frackowiak, R.S.: Statistical parametric maps in functional imaging: a general linear approach. Hum. Brain Mapp. 2, 189–210 (1994)CrossRefGoogle Scholar
  3. 3.
    Andersen, A.H., Gash, D.M., Avison, M.J.: Principal component analysis of the dynamic response measured by fMRI: a generalized linear systems framework. Magn. Reson. Imaging 17, 795–815 (1999)CrossRefGoogle Scholar
  4. 4.
    Biswal, B.B., Ulmer, J.L.: Blind source separation of multiple signal sources of fMRI data sets using independent component analysis. J. Comput. Assist. Tomogr. 23, 265–271 (1999)CrossRefGoogle Scholar
  5. 5.
    Lv, J., et al.: Holistic atlases of functional networks and interactions reveal reciprocal organizational architecture of cortical function. IEEE Trans. Biomed. Eng. 62, 1120–1131 (2015)CrossRefGoogle Scholar
  6. 6.
    Zhao, S., et al.: Supervised dictionary learning for inferring concurrent brain networks. IEEE Trans. Med. Imaging 34, 2036–2045 (2015)CrossRefGoogle Scholar
  7. 7.
    Zhang, W., et al.: Experimental comparisons of sparse dictionary learning and independent component analysis for brain network inference from fMRI data. IEEE Trans. Biomed. Eng. 66, 289–299 (2018)CrossRefGoogle Scholar
  8. 8.
    Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. Computer Science (2015)Google Scholar
  9. 9.
    Cui, Y., et al.: Identifying brain networks at multiple time scales via deep recurrent neural network. IEEE J. Biomed. Health Inform. (2018)Google Scholar
  10. 10.
    Bourlard, H., Kamp, Y.: Auto-association by multilayer perceptrons and singular value decomposition. Biol. Cybern. 59, 291–294 (1988)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Barch, D.M., et al.: Function in the human connectome: task-fMRI and individual differences in behavior. Neuroimage 80, 169–189 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Shijie Zhao
    • 1
    Email author
  • Yan Cui
    • 2
  • Yaowu Chen
    • 2
  • Xin Zhang
    • 1
  • Wei Zhang
    • 3
  • Huan Liu
    • 1
  • Junwei Han
    • 1
  • Lei Guo
    • 1
  • Li Xie
    • 2
    Email author
  • Tianming Liu
    • 3
  1. 1.School of AutomationNorthwestern Polytechnical UniversityXi’anChina
  2. 2.College of Biomedical Engineering and Instrument ScienceZhejiang UniversityHangzhouChina
  3. 3.Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research CenterThe University of GeorgiaAthensUSA

Personalised recommendations