Abstract
Manual seizure detection in clinical electroencephalography (EEG) is time consuming and requires extensive training. In addition, the seizure origin and spreading pattern is valuable for therapeutic planning but cannot always be manually disambiguated. Prior work in automated seizure detection has focused on engineering new features that better capture the seizure activity. However, these methods ignore crucial information in the data and are not sensitive enough to track the seizure propagation. In this work we introduce a hybrid Probabilistic Graphical Model-Convolutional Neural Network (PGM-CNN) for seizure tracking in multichannel EEG. Our model leverages the power of deep learning for data driven analysis of the raw EEG time series while retaining clinically relevant information through the latent PGM prior. We validate our hybrid model on clinical EEG data from two hospitals with distinct patient populations. Our system achieves better detection performance than baseline methods, which exclusively use PGMs or neural networks.
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
References
Zach, M., et al.: National and state estimates of the numbers of adults and children with active epilepsy - United States, 2015. CDC MMWR 66, 821–825 (2017)
French, J.A.: Refractory epilepsy: clinical overview. Epilepsia 48, 3–7 (2007)
Osorio, I., Zaveri, H.P., Frei, M.G., Arthurs, S.: Epilepsy: the Intersection of Neurosciences, Biology, Mathematics, Engineering, and Physics. CRC Press, Boca Raton (2016)
Shoeb, A.H., Guttag, J.V.: Application of machine learning to epileptic seizure detection. In: International Conference on Machine Learning, pp. 975–982 (2010)
Andrzejak, R.G., et al.: Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys. Rev. E 64(6), 061907 (2001)
Güler, N.F., et al.: Recurrent neural networks employing Lyapunov exponents for EEG signals classification. Expert Syst. Appl. 29(3), 506–514 (2005)
Craley, J., Johnson, E., Venkataraman, A.: A novel method for epileptic seizure detection using coupled hidden markov models. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 482–489. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_55
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)
Murphy, K.P.: Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge (2012)
Acknowledgments
This work was supported by a JHMI Synergy Award (Venkataraman/Johnson) and NSF CAREER 1845430 (Venkataraman).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Craley, J., Johnson, E., Venkataraman, A. (2019). Integrating Convolutional Neural Networks and Probabilistic Graphical Modeling for Epileptic Seizure Detection in Multichannel EEG. In: Chung, A., Gee, J., Yushkevich, P., Bao, S. (eds) Information Processing in Medical Imaging. IPMI 2019. Lecture Notes in Computer Science(), vol 11492. Springer, Cham. https://doi.org/10.1007/978-3-030-20351-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-20351-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20350-4
Online ISBN: 978-3-030-20351-1
eBook Packages: Computer ScienceComputer Science (R0)