Abstract
Epilepsy is a chronic medical condition that involves abnormal brain activity causing patients to lose control of awareness or motor activity. As a result, detection of pre-ictal states, before the onset of a seizure, can be lifesaving. The problem is challenging because it is difficult to discern between electroencephalogram signals in pre-ictal states versus signals in normal inter-ictal states. There are three key challenges that have not been addressed previously: (1) the inconsistent performance of prediction models across patients, (2) the lack of perfect prediction to protect patients from any episode, and (3) the limited amount of pre-ictal labeled data for advancing machine learning methods. This article addresses these limitations through a novel approach that uses adversarial examples with optimized tuning of a combined convolutional neural network and gated recurrent unit. Compared to the state of the art, the results showed an improvement of 3x in model robustness as measured in reduced variations and superior accuracy of the area under the curve, with an average increase of 6.7%. The proposed method also exhibited superior performance with other advances in the field of machine learning and customized for epilepsy prediction including data augmentation with Gaussian noise and multitask learning.
- U. Rajendra Acharya, Shu Lih Oh, Yuki Hagiwara, Jen Hong Tan, and Hojjat Adeli. 2018. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine 100 (2018), 270--278.Google Scholar
Digital Library
- Elie Bou Assi, Dang K. Nguyen, Sandy Rihana, and Mohamad Sawan. 2017. Towards accurate prediction of epileptic seizures: A review. Biomedical Signal Processing and Control 34 (2017), 144--157.Google Scholar
Cross Ref
- Mojtaba Bandarabadi, César A. Teixeira, Jalil Rasekhi, and António Dourado. 2015. Epileptic seizure prediction using relative spectral power features. Clinical Neurophysiology 126, 2 (2015), 237--248.Google Scholar
Cross Ref
- Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP’17). IEEE, Los Alamitos, CA, 39--57.Google Scholar
Cross Ref
- Paul R. Carney, Stephen Myers, and James D. Geyer. 2011. Seizure prediction: Methods. Epilepsy 8 Behavior 22 (2011), S94--S101.Google Scholar
- Mark J. Cook, Terence J. O’Brien, Samuel F. Berkovic, Michael Murphy, Andrew Morokoff, Gavin Fabinyi, Wendyl D’Souza, et al. 2013. Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: A first-in-man study. Lancet Neurology 12, 6 (2013), 563--571.Google Scholar
Cross Ref
- Anindya Bijoy Das, Mohammed Imamul Hassan Bhuiyan, and S. M. Shafiul Alam. 2014. A statistical method for automatic detection of seizure and epilepsy in the dual tree complex wavelet transform domain. In Proceedings of the 2014 International Conference on Informatics, Electronics, and Vision (ICIEV’14). IEEE, Los Alamitos, CA, 1--6.Google Scholar
- C. L. P. Deckers, P. Genton, G. J. Sills, and D. Schmidt. 2003. Current limitations of antiepileptic drug therapy: A conference review. Epilepsy Research 53, 1--2 (2003), 1--17.Google Scholar
- David A. Dickey and Wayne A. Fuller. 1979. Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association 74, 366a (1979), 427--431.Google Scholar
- Bruno Direito, César A. Teixeira, Francisco Sales, Miguel Castelo-Branco, and António Dourado. 2017. A realistic seizure prediction study based on multiclass SVM. International Journal of Neural Systems 27, 03 (2017), 1750006.Google Scholar
Cross Ref
- Firat Duman, Nilüfer Özdemir, and Esen Yildirim. 2012. Patient specific seizure prediction algorithm using Hilbert-Huang transform. In Proceedings of the 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE, Los Alamitos, CA, 705--708.Google Scholar
- Kais Gadhoumi, Jean-Marc Lina, Florian Mormann, and Jean Gotman. 2016. Seizure prediction for therapeutic devices: A review. Journal of Neuroscience Methods 260 (2016), 270--282.Google Scholar
Cross Ref
- Meysam Golmohammadi, Saeedeh Ziyabari, Vinit Shah, Silvia Lopez de Diego, Iyad Obeid, and Joseph Picone. 2017. Deep architectures for automated seizure detection in scalp EEGs. arXiv:1712.09776.Google Scholar
- Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572.Google Scholar
- Kathrin Grosse, Praveen Manoharan, Nicolas Papernot, Michael Backes, and Patrick McDaniel. 2017. On the (statistical) detection of adversarial examples. arXiv:1702.06280.Google Scholar
- Ramy Hussein, Hamid Palangi, Rabab Ward, and Z. Jane Wang. 2018. Epileptic seizure detection: A deep learning approach. arXiv:1803.09848.Google Scholar
- Leon D. Iasemidis. 2011. Seizure prediction and its applications. Neurosurgery Clinics 22, 4 (2011), 489--506.Google Scholar
- Haidar Khan, Lara Marcuse, Madeline Fields, Kalina Swann, and Bülent Yener. 2017. Focal onset seizure prediction using convolutional networks. IEEE Transactions on Biomedical Engineering 65, 9 (2017), 2109--2118.Google Scholar
Cross Ref
- Isabell Kiral-Kornek, Subhrajit Roy, Ewan Nurse, Benjamin Mashford, Philippa Karoly, Thomas Carroll, Daniel Payne, et al. 2018. Epileptic seizure prediction using big data and deep learning: Toward a mobile system. EBioMedicine 27 (2018), 103--111.Google Scholar
Cross Ref
- Patrick Kwan and Martin J. Brodie. 2000. Early identification of refractory epilepsy. New England Journal of Medicine 342, 5 (2000), 314--319.Google Scholar
Cross Ref
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (Nov. 2008), 2579--2605.Google Scholar
- Piotr Mirowski, Deepak Madhavan, Yann LeCun, and Ruben Kuzniecky. 2009. Classification of patterns of EEG synchronization for seizure prediction. Clinical Neurophysiology 120, 11 (2009), 1927--1940.Google Scholar
Cross Ref
- Anh Nguyen, Jason Yosinski, and Jeff Clune. 2015. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 427--436.Google Scholar
Cross Ref
- University of Freiburg. 2019. Seizure Prediction Project Freiburg. Retrieved June 15, 2019 from http://epilepsy.uni-freiburg.de.Google Scholar
- Francisco Ordóñez and Daniel Roggen. 2016. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16, 1 (2016), 115.Google Scholar
Cross Ref
- World Health Organization. 2019. Epilepsy. Retrieved June 15, 2019 from https://www.who.int/news-room/fact-sheets/detail/epilepsy.Google Scholar
- Hao Qu and Jean Gotman. 1997. A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: Possible use as a warning device. IEEE Transactions on Biomedical Engineering 44, 2 (1997), 115--122.Google Scholar
Cross Ref
- Jalil Rasekhi, Mohammad Reza Karami Mollaei, Mojtaba Bandarabadi, Cesar A. Teixeira, and Antonio Dourado. 2013. Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods. Journal of Neuroscience Methods 217, 1--2 (2013), 9--16.Google Scholar
- Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, and Thomas Hofmann. 2018. Adversarially robust training through structured gradient regularization. arXiv:1805.08736.Google Scholar
- Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv:1706.05098.Google Scholar
- Ali H. Shoeb and John V. Guttag. 2010. Application of machine learning to epileptic seizure detection. In Proceedings of the 27th International Conference on Machine Learning (ICML’10). 975--982.Google Scholar
- Susan S. Spencer, Dang K. Nguyen, and Robert B. Duckrow. 2009. Invasive EEG in presurgical evaluation of epilepsy. Treatment of Epilepsy 3 (2009), 767--98.Google Scholar
- Sining Sun, Ching-Feng Yeh, Mari Ostendorf, Mei-Yuh Hwang, and Lei Xie. 2018. Training augmentation with adversarial examples for robust speech recognition. arXiv:1806.02782.Google Scholar
- Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv:1312.6199.Google Scholar
- Florian Tramèr, Nicolas Papernot, Ian Goodfellow, Dan Boneh, and Patrick McDaniel. 2017. The space of transferable adversarial examples. arXiv:1704.03453.Google Scholar
- Nhan Duy Truong, Anh Duy Nguyen, Levin Kuhlmann, Mohammad Reza Bonyadi, Jiawei Yang, Samuel Ippolito, and Omid Kavehei. 2018. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Networks 105 (2018), 104--111.Google Scholar
Digital Library
- Syed Muhammad Usman, Muhammad Usman, and Simon Fong. 2017. Epileptic seizures prediction using machine learning methods. Computational and Mathematical Methods in Medicine 2017 (2017), 9074759.Google Scholar
- Alex Van Esbroeck, Landon Smith, Zeeshan Syed, Satinder Singh, and Zahi Karam. 2016. Multi-task seizure detection: Addressing intra-patient variation in seizure morphologies. Machine Learning 102, 3 (2016), 309--321.Google Scholar
Digital Library
- Ning Wang and Michael R. Lyu. 2014. Extracting and selecting distinctive EEG features for efficient epileptic seizure prediction. IEEE Journal of Biomedical and Health Informatics 19, 5 (2014), 1648--1659.Google Scholar
- Zhiguang Wang, Weizhong Yan, and Tim Oates. 2017. Time series classification from scratch with deep neural networks: A strong baseline. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN’17). IEEE, Los Alamitos, CA, 1578--1585.Google Scholar
Index Terms
Augmenting DL with Adversarial Training for Robust Prediction of Epilepsy Seizures
Recommendations
Applying Deep Learning for Epilepsy Seizure Detection and Brain Mapping Visualization
Special Section on Deep Learning for Intelligent Multimedia Analytics and Special Section on Multi-Modal Understanding of Social, Affective and Subjective Attributes of DataDeep Convolutional Neural Network (CNN) has achieved remarkable results in computer vision tasks for end-to-end learning. We evaluate here the power of a deep CNN to learn robust features from raw Electroencephalogram (EEG) data to detect seizures. ...
Personalized attention-based EEG channel selection for epileptic seizure prediction
AbstractEpilepsy is a neurological disorder, characterized by intractable seizures with severe consequences. To predict these seizures, electroencephalogram (EEG) data has to be collected in a continuous manner. EEG signals are recorded ...
Highlights- It is possible to use only two or three EEG channels for epileptic seizure prediction.
Epileptic Seizure Prediction by Synthesizing EEG Signals through GPT
AIPR '21: Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern RecognitionEpileptic seizures have a serious impact on the normal life of patients with epilepsy. Epileptic seizure prediction can effectively reduce the mental pressure of patients with epilepsy and improve patients' quality of life. It is a key and challenging ...






Comments