Abstract
Electroencephalography produces high-dimensional, stochastic data from which it might be challenging to extract high-level knowledge about the phenomena of interest. We address this challenge by applying the framework of variational auto-encoders to 1) classify multiple pathologies and 2) recover the neurological mechanisms of those pathologies in a data-driven manner. Our framework learns generative factors of data related to pathologies. We provide an algorithm to decode those factors further and discover how different pathologies affect observed data. We illustrate the applicability of the proposed approach to identifying schizophrenia, either followed or not by auditory verbal hallucinations. We further demonstrate the ability of the framework to learn disease-related mechanisms consistent with current domain knowledge. We also compare the proposed framework with several benchmark approaches and indicate its classification performance and interpretability advantages.
S. Steinmann and N. Hoffmann—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Technically, [13] use stacked VAEs that have two connected latent spaces. One of the spaces is connected to label variables. However, the framework can be seen as an instance of conditional VAEs with a non-trivial structure of the latent space.
References
Davatzikos, C.: Machine learning in neuroimaging: progress and challenges. Neuroimage 197, 652–656 (2019)
Zhang, L., Wang, M., Liu, M., Zhang, D.: A survey on deep learning for neuroimaging-based brain disorder analysis. Front. Neurosci. 14, 779 (2020)
Wahlang, I., et al.: Brain magnetic resonance imaging classification using deep learning architectures with gender and age. Sensors 22, 1766 (2022)
Li, Y., et al.: A novel bi-hemispheric discrepancy model for EEG emotion recognition. IEEE Trans. Cogn. Dev. Syst. 13, 354–367 (2021)
Quinn, T.P., Jacobs, S., Senadeera, M., Le, V., Coghlan, S.: The three ghosts of medical AI: can the black-box present deliver? Artif. Intell. Med. 124, 102158 (2022)
Liu, X., Sanchez, P., Thermos, S., O’Neil, A.Q., Tsaftaris, S.A.: Learning disentangled representations in the imaging domain. Med. Image Anal. (2022)
Joy, T., Schmon, S.M., Torr, P.H., Siddharth, N., Rainforth, T.: Capturing label characteristics in VAEs. In: ICLR (2021)
Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)
Kingma, D.P., Welling, M.: Auto-Encoding Variational Bayes. CoRR, abs/1312.6114 (2014)
Locatello, F., Bauer, S., Lucic, M., Gelly, S., Schölkopf, B., Bachem, O.: Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations. arXiv, abs/1811.12359 (2019)
Krishna, G., Tran, C., Carnahan, M., Tewfik, A.H.: Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems. arXiv, abs/2006.02902 (2020)
Li, X., et al.: Latent factor decoding of multi-channel EEG for emotion recognition through autoencoder-like neural networks. Front. Neurosci. 14, 87 (2020)
Chen, J., Yu, Z., Gu, Z.: Semi-supervised Deep Learning in Motor Imagery-Based Brain-Computer Interfaces with Stacked Variational Autoencoder (2020)
Steinmann, S., Leicht, G., Andreou, C., Polomac, N., Mulert, C.: Auditory verbal hallucinations related to altered long-range synchrony of gamma-band oscillations. Sci. Rep. 7(1), 1–10 (2017)
Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: NeurIPS (2018)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational Inference of Disentangled Latent Concepts from Unlabeled Observations. arXiv, abs/1711.00848 (2018)
Jardri, R., Pouchet, A., Pins, D., Thomas, P.: Cortical activations during auditory verbal hallucinations in schizophrenia: a coordinate-based meta-analysis. Am. J. Psychiatry 168(1), 73–81 (2011)
Lavigne, K.M., et al.: Left-dominant temporal-frontal hypercoupling in schizophrenia patients with hallucinations during speech perception. Schizophr. Bull. 41(1), 259–67 (2015)
Hwang, M., et al.: Auditory hallucinations across the psychosis spectrum: evidence of dysconnectivity involving cerebellar and temporal lobe regions. NeuroImage Clin. 32, 102893 (2021)
Papathanassiou, D., Etard, O., Mellet, E., Zago, L., Mazoyer, B., Tzourio-Mazoyer, N.: A common language network for comprehension and production: a contribution to the definition of language epicenters with PET. Neuroimage 11, 347–357 (2000)
Flinker, A., et al.: Redefining the role of Broca’s area in speech. Proc. Natl. Acad. Sci. 112, 2871–2875 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhdanov, M., Steinmann, S., Hoffmann, N. (2022). Learning Generative Factors of EEG Data with Variational Auto-Encoders. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds) Deep Generative Models. DGM4MICCAI 2022. Lecture Notes in Computer Science, vol 13609. Springer, Cham. https://doi.org/10.1007/978-3-031-18576-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-18576-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18575-5
Online ISBN: 978-3-031-18576-2
eBook Packages: Computer ScienceComputer Science (R0)
