Abstract
In recent studies, we have witnessed the applicability of deep learning methods on resting-state functional Magnetic Resonance Image (rs-fMRI) analysis and on its use for brain disease diagnosis, e.g., early Mild Cognitive Impairment (eMCI) identification. However, to our best knowledge, many of the existing methods are generally limited from improving the performance in a target task, e.g., eMCI diagnosis, by the unexpected information loss in transforming an input into hierarchical or compressed representations. In this paper, we propose a novel network architecture that discovers enriched representations of the spatio-temporal patterns in rs-fMRI such that the most compressed or latent representations include the maximal amount of information to recover the original input, but are decomposed into diagnosis-relevant and diagnosis-irrelevant features. In order to learn those favourable representations, we utilize a self-attention mechanism to explore spatially more informative patterns over time and information-oriented techniques to maintain the enriched but decomposed representations. In our experiments over the ADNI dataset, we validated the effectiveness of the proposed network architecture by comparing its performance with that of the counterpart methods as well as the competing methods in the literature.
Keywords
E. Jeon and E. Kang—Equally contributed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
- 4.
The hyperparameter was determined in \(\{10^{-5},10^{-2},\dots ,10^{4}\}\).
- 5.
It is the most typical pipeline in brain disease diagnosis with rs-fMRI [3].
References
Belghazi, M.I., et al.: Mutual information neural estimation. In: International Conference on Machine Learning, pp. 531–540 (2018)
Calhoun, V.D., Miller, R., Pearlson, G., Adalı, T.: The chronnectome: time-varying connectivity networks as the next frontier in fMRI data discovery. Neuron 84(2), 262–274 (2014)
Dadi, K., et al.: Benchmarking functional connectome-based predictive models for resting-state fMRI. NeuroImage 192, 115–134 (2019)
Donsker, M.D., Varadhan, S.S.: Asymptotic evaluation of certain Markov process expectations for large time. IV. Commun. Pure Appl. Math. 36(2), 183–212 (1983)
Dvornek, N.C., Li, X., Zhuang, J., Duncan, J.S.: Jointly discriminative and generative recurrent neural networks for learning from fMRI. In: Suk, H.-I., Liu, M., Yan, P., Lian, C. (eds.) MLMI 2019. LNCS, vol. 11861, pp. 382–390. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32692-0_44
Fedorov, A., et al.: Prediction of progression to Alzheimer’s disease with deep infoMax. In: 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), pp. 1–5. IEEE (2019)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Hjelm, R.D., Calhoun, V.D., Salakhutdinov, R., Allen, E.A., Adali, T., Plis, S.M.: Restricted Boltzmann machines for neuroimaging: an application in identifying intrinsic networks. NeuroImage 96, 245–260 (2014)
Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: International Conference on Learning Representations (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Hu, X., et al.: Latent source mining in fMRI via restricted Boltzmann machine. Hum. Brain Mapp. 39(6), 2368–2380 (2018)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Jeon, E., Ko, W., Yoon, J.S., Suk, H.I.: Mutual information-driven subject-invariant and class-relevant deep representation learning in BCI. arXiv preprint arXiv:1910.07747 (2019)
Kam, T.E., Suk, H.I., Lee, S.W.: Multiple functional networks modeling for autism spectrum disorder diagnosis. Hum. Brain Mapp. 38(11), 5804–5821 (2017)
Kang, E., Suk, H.-I.: Probabilistic source separation on resting-state fMRI and its use for early MCI identification. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 275–283. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_32
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Suk, H.I., Wee, C.Y., Lee, S.W., Shen, D.: State-space model with deep learning for functional dynamics estimation in resting-state fMRI. NeuroImage 129, 292–307 (2016)
Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp. 1–5. IEEE (2015)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Yan, C.G., Wang, X.D., Zuo, X.N., Zang, Y.F.: DPABI: data processing & analysis for (resting-state) brain imaging. Neuroinformatics 14(3), 339–351 (2016)
Yeo, B.T., et al.: The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J. Neurophysiol. 106(3), 1125 (2011)
Yoon, J.S., Ko, W., Suk, H.I.: A plug-in method for representation factorization. arXiv preprint arXiv:1905.11088 (2019)
Acknowledgement
This work was supported by National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A2C1006543) and partially by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program (Korea University)).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Jeon, E., Kang, E., Lee, J., Lee, J., Kam, TE., Suk, HI. (2020). Enriched Representation Learning in Resting-State fMRI for Early MCI Diagnosis. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12267. Springer, Cham. https://doi.org/10.1007/978-3-030-59728-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-59728-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59727-6
Online ISBN: 978-3-030-59728-3
eBook Packages: Computer ScienceComputer Science (R0)