ABSTRACT
Causal connectivity among the brain regions have been recently exploited information for discriminating epileptiforms to detect epileptic seizures. Published investigations to detect ictal, interictal, preictal EEG reported existence of long-range correlations of excitations within a functionally connected brain region and shifting of focus of excitations from one region to another region and increase or decrease of intensity in certain frequency-bands, which can be quantified using suitable measure of Granger causality (GC). Deep neural networks obviated explicit preprocessing and feature extraction. The proposed work employs temporal dilated convolutional network to estimate causal connectivity relations among brain-regions in various frequency-bands in distributed manner. It implicitly learns varying autoregressive-lag-orders using stacked layers and covers long range relationships using exponential update of layer-wise dilation-factor. Model training with several parameter-combinations were conducted over 10 subjects. The proposed model outperformed the existing approaches and baseline model in terms of accuracy, sensitivity, and false positive rate. Class-wise dominating features were obtained using statistical significance analysis followed by family wise error rate correction using Benjamini-Hochberg method.
- Jalil Rasekhi, Mohammad Reza Karami Mollaei, Mojtaba Bandarabadi, César A. Teixeira, and António Dourado. 2015. Epileptic seizure prediction based on ratio and differential linear univariate features. Journal of medical signals and sensors, 5(1), 1.Google Scholar
- Ernesto Pereda, Antoni Gamundi, Rubén Rial, and Julián González. 1998. Non-linear behaviour of human EEG: fractal exponent versus correlation dimension in awake and sleep stages. Neuroscience letters, 250(2), 91-94.Google Scholar
- Klaus Lehnertz, Florian Mormann, Hannes Osterhage, Andy Müller, Jens Prusseit, Anton Chernihovskyi, Matthäus Staniek, Dieter Krug, Stephan Bialonski, and Christian E. Elger. 2007. State-of-the-art of seizure prediction. Journal of Clinical Neurophy., 24(2), 147-153.Google Scholar
- Klaus Lehnertz, Christian Geier, Thorsten Rings, and Kirsten Stahn. 2017. Capturing time-varying brain dynamics. EPJ Nonlinear Biomedical Physics, 5, 2Google Scholar
- Mark P Richardson. 2012. Large scale brain models of epilepsy: dynamics meets connectomics. Journal of Neurology, Neurosurgery & Psychiatry, 83(12), 1238-1248.Google Scholar
- Catalina Alvarado-Rojas, Valderrama, M., Fouad-Ahmed, A., Feldwisch-Drentrup, H., Ihle, M., Teixeira, C.A., Sales, F., Schulze-Bonhage, A., Adam, C., Dourado, A. and Charpier, S. 2014. Slow modulations of high-frequency activity (40-140-Hz) discriminate preictal changes in human focal epilepsy. Sci Rep, 4, 4545.Google Scholar
- Florian Mormann, Ralph G. Andrzejak, Christian E. Elger, and Klaus Lehnertz. 2007. Seizure prediction: the long and winding road. Brain, 130(2), 314-333.Google Scholar
- Etienne Labyt, Paul Frogerais, Laura Uva, Jean-Jacques Bellanger, and Fabrice Wendling. 2007. Modeling of entorhinal cortex and simulation of epileptic activity: insights into the role of inhibition-related parameters. IEEE Transactions on Information Technology in Biomedicine, 11(4), 450-461Google Scholar
- Michel Le Van Quyen, Richard Staba, Anatol Bragin, Clayton Dickson, Mario Valderrama, Itzhak Fried, and Jerome Engel. 2010. Large-scale microelectrode recordings of high-frequency gamma oscillations in human cortex during sleep. J. Neuroscience, 30(23), 7770-7782.Google Scholar
- Mircea Steriade, Florin Amzica, and Diego Contreras. 1996. Synchronization of fast (30-40 Hz) spontaneous cortical rhythms during brain activation. Journal of Neuroscience, 16(1), 392-417.Google Scholar
- Mircea Steriade. 2003. Neuronal substrates of sleep and epilepsy. Cambridge University Press.Google Scholar
- Jean‐Philippe Lachaux, Eugenio Rodriguez, Jacques Martinerie, and Francisco J. Varela. 1999. Measuring phase synchrony in brain signals. Human brain mapping, 8(4), 194-208.Google Scholar
- Florian Mormann, Klaus Lehnertz, Peter David, and Christian E. Elger. 2000. Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients. Physica D: Nonlinear Phenomena, 144(3-4), 358-369.Google Scholar
- María Eugenía López, Ricardo Bruna, Sara Aurtenetxe, José Ángel Pineda-Pardo, Alberto Marcos, Juan Arrazola, Ana Isabel Reinoso, Pedro Montejo, Ricardo Bajo, and Fernando Maestú. 2014. Alpha-band hypersynchronization in progressive mild cognitive impairment: a magnetoencephalography study. Journal of Neuroscience, 34(44), 14551-14559Google Scholar
- Pascal Fries. 2015. Rhythms for cognition: communication through coherence. Neuron, 88(1), 220-235.Google Scholar
- Pilar Garcés, María Carmen Martín-Buro, and Fernando Maestú. 2016. Quantifying the test-retest reliability of magnetoencephalography resting-state functional connectivity. Brain connectivity, 6(6), 448-460.Google Scholar
- Ricardo Bruña, Fernando Maestú, and Ernesto Pereda. 2018. Phase locking value revisited: teaching new tricks to an old dog. Journal of neural engineering, 15(5), 056011.Google Scholar
- Mike X Cohen. 2014. Analyzing neural time series data: theory and practice. MIT press.Google Scholar
- Tsungnan Lin, Bill G. Horne, Peter Tino, and C. Lee Giles. 1996. Learning long-term dependencies in NARX recurrent neural networks. IEEE Transactions on Neural Networks, 7(6), 1329-1338.Google Scholar
- Stefan Haufe, Vadim V. Nikulin, Klaus-Robert Müller, and Guido Nolte. 2013. A critical assessment of connectivity measures for EEG data: a simulation study. Neuroimage, 64, 120-133.Google Scholar
- Tian Guo, and Tao Lin. 2018. Multi-variable LSTM neural network for autoregressive exogenous model. arXiv preprint arXiv:1806.06384.Google Scholar
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, pp. 1–9Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV (2016). p. 770–8.Google Scholar
- Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander Alemi. 2017. Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligenceGoogle ScholarDigital Library
- Colin Lea, Michael D. Flynn, Rene Vidal, Austin Reiter, and Gregory D. Hager. 2017. Temporal convolutional networks for action segmentation and detection. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 156-165).Google Scholar
- Bai, Shaojie, J. Zico Kolter, and Vladlen Koltun. 2018. Convolutional sequence modeling revisited.Google Scholar
- Cheng Tong, Linghua Zhang, Hao Li, and Yin Ding. 2022. Temporal inception convolutional network based on multi‐head attention for ultra‐short‐term load forecasting. IET Generation, Transmission & Distribution.Google Scholar
- Nauta, Meike, Doina Bucur, and Christin Seifert. 2019. Causal discovery with attention-based convolutional neural networks. Machine Learning and Knowledge Extraction, 1(1), 312-340.Google Scholar
- Tank, Alex, Ian Covert, Nicholas Foti, Ali Shojaie, and Emily B. Fox. 2021. Neural granger causality. arXiv preprint arXiv:1802.05842v2.Google Scholar
- Mona Hejazi, and Ali Motie Nasrabadi. 2019. Prediction of epilepsy seizure from multi-channel electroencephalogram by effective connectivity analysis using Granger causality and directed transfer function methods. Cognitive neurodynamics, 13, 461-473.Google Scholar
- Siyi Tang, Jared A. Dunnmon, Khaled Saab, Xuan Zhang, Qianying Huang, Florian Dubost, Daniel L. Rubin, and Christopher Lee-Messer. 2021. Self-supervised graph neural networks for improved electroencephalographic seizure analysis. arXiv preprint arXiv:2104.08336.Google Scholar
- Shinya Ito, Michael E. Hansen, Randy Heiland, Andrew Lumsdaine, Alan M. Litke, and John M. Beggs. (2011). Extending transfer entropy improves identification of effective connectivity in a spiking cortical network model. PloS one, 6(11), e27431.Google Scholar
- Yoav Benjamini, Y., and Yosef Hochberg. 1995. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal statistical society: series B (Methodological), 57(1), 289-300.Google Scholar
Index Terms
- Exploring the Efficacy of Explainable Deep Learning in Identifying Neuromarkers for Precise Prediction of Epilepsy and Causal Connectivity Analysis
Recommendations
Brain Connectivity Feature Mining of Post-Encephalitis Epilepsy
ICCPR '21: Proceedings of the 2021 10th International Conference on Computing and Pattern RecognitionEpilepsy is a common neurological brain disease. Encephalitis is an inflammatory disease of the brain. If patients with encephalitis are not treated in time, some patients will suffer from refractory epilepsy. Since there is no clear medical explanation ...
Causal Connectivity Brain Network: A Novel Method of Motor Imagery Classification for Brain-Computer Interface Applications
CMCSN '12: Proceedings of the 2012 International Conference on Computing, Measurement, Control and Sensor NetworkThe effective connectivity among overlapped core regions recruited by motor imagery (MI) was explored by means of Granger causality and graph-theoretic method, based on Electroencephalography (EEG) data. In this paper, causal connectivity brain network (...
Comments