Abstract
Deep 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. Seizures are hard to detect, as they vary both inter- and intra-patient. In this article, we use a deep CNN model for seizure detection task on an open-access EEG epilepsy dataset collected at the Boston Children's Hospital. Our deep learning model is able to extract spectral, temporal features from EEG epilepsy data and use them to learn the general structure of a seizure that is less sensitive to variations. For cross-patient EEG data, our method produced an overall sensitivity of 90.00%, specificity of 91.65%, and overall accuracy of 98.05% for the whole dataset of 23 patients. The system can detect seizures with an accuracy of 99.46%. Thus, it can be used as an excellent cross-patient seizure classifier. The results show that our model performs better than the previous state-of-the-art models for patient-specific and cross-patient seizure detection task. The method gave an overall accuracy of 99.65% for patient-specific data. The system can also visualize the special orientation of band power features. We use correlation maps to relate spectral amplitude features to the output in the form of images. By using the results from our deep learning model, this visualization method can be used as an effective multimedia tool for producing quick and relevant brain mapping images that can be used by medical experts for further investigation.
- World Health Organization. 2017. Epilepsy. Retrieved from http://www.who.int/mediacentre/factsheets/fs999/en/.Google Scholar
- B. Litt and J. Echauz. 2002. Prediction of epileptic seizures. The Lancet Neurology 1, 1 (2002), 22--30.Google ScholarCross Ref
- J. Echauz and G. Georgoulas. 2007. Monitoring, signal analysis, and control of epileptic seizures: A paradigm in brain research. In Mediterranean Conference on Control 8 Automation. 1--6.Google Scholar
- L. John Greenfield, James D. Geyer, and Paul R. Carney. 2012. Reading EEGs: A Practical Approach. Lippincott Williams 8 Wilkins.Google Scholar
- F. Mormann, R. G. Andrzejak, and C. E. Elger. 2007. Seizure prediction: The long and winding road. Brain 130, 2 (2007), 314--333.Google ScholarCross Ref
- J. Duun-Henriksen, T. W. Kjaer, R. E. Madsen, and L. S. Remvig. 2012. Channel selection for automatic seizure detection. Clinical Neurophysiology 123, 1 (2012), 84--92.Google ScholarCross Ref
- L. Kuhlmann, A. N. Burkitt, M. J. Cook, and K. Fuller. 2009. Seizure detection using seizure probability estimation: Comparison of features used to detect seizures. Annals of Biomedical Engineering 37, 10 (2009), 2129--2145.Google ScholarCross Ref
- C. Fatichah, A. M. Iliyasu, K. A. Abuhasel, and N. Suciati. 2014. Principal component analysis-based neural network with fuzzy membership function for epileptic seizure detection. In International Conference on Natural Computation. 186--191.Google Scholar
- G. R. Minasyan, J. B. Chatten, and M. J. Chatten. 2010. Patient-specific early seizure detection from scalp EEG. Journal of Clinical Neurophysiology: Official Publication of the American Electroencephalographic Society 27, 3.Google ScholarCross Ref
- I. Osorio and M. Frei. 2009. Real-time detection, quantification, warning, and control of epileptic seizures: The foundations for a scientific epileptology. Epilepsy 8 Behavior 16, 3 (2009), 391--396.Google Scholar
- M. Hills. 2014. Seizure detection using FFT, temporal and spectral correlation coefficients, eigenvalues and random forest. Technical Report. GitHub.Google Scholar
- A. Shoeb, D. Carlson, E. Panken, and D. Timothy. 2009. A micro support vector machine based seizure detection architecture for embedded medical devices. In Proceedings of the Engineering in Medicine and Biology Society, Annual International Conference of the IEEE.Google Scholar
- Y. Park, L. Luo, and K. K. Parhi. 2011. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 52 (2011), 1761--1770.Google ScholarCross Ref
- F. Mormann, K. Lehnertz, and P. David. 2000. Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients. Physica D 144 (2000), 358--369. Google ScholarDigital Library
- M. Le Van Quyen, V. Navarro, and J. Martinerie. 2003. Towards a neurodynamical understanding of ictogenesis. Epilepsia 44 (2003), 30--43.Google ScholarCross Ref
- Mario Chávez, Jacques Martinerie, and Michel Le Van Quyen. 2003. Statistical assessment of nonlinear causality: Application to epileptic EEG signals. Journal of Neuroscience. Methods 124 (2003), 113--128.Google Scholar
- Florian Mormann, Thomas Kreuz, Christoph Rieke, Alexander Kraskov, and Peter David. 2005. On the predictability of epileptic seizures. Clinical Neurophysiology 116 (2005), 569--587.Google ScholarCross Ref
- Quang M. Tieng, Irina Kharatishvili, Min Chen, and David C Reutens. 2016. Mouse EEG spike detection based on the adapted continuous wavelet transform. Journal of Neural Engineering 13, 2 (2016), 026018.Google ScholarCross Ref
- M. Z. Parvez and M. Paul. 2015. Epileptic seizure detection by exploiting temporal correlation of electroencephalogram signals. IET Signal Processing 9, 6 (2015), 467--475.Google ScholarCross Ref
- M. Zabihi, S. Kiranyaz, A. K. Katsaggelos, and T. Ince. 2016. Analysis of high-dimensional phase space via poincare section for patient-specific seizure detection. IEEE Transactions on Neural Systems and Rehabilitation Engineering 24, 3 (2016), 386--398.Google ScholarCross Ref
- Pierre Thodoroff, Joelle Pineau, and Andrew Lim. 2016. Learning robust features using deep learning for automatic seizure detection. Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56 (2016), 178--190.Google Scholar
- Alexandros T. Tzallas, Markos G. Tsipouras, and Dimitrios G. Tsalikakis. 2012. Automated epileptic seizure detection methods: A review study. Epilepsy - Histological, Electroencephalographic and Psychological Aspects (2012).Google Scholar
- C. P. Panayiotopoulos. 2010. A Clinical Guide to Epileptic Syndromes and Their Treatment. Chapter 6, “EEG and Brain Imaging”, Springer.Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (2012), 1097--1105. Google ScholarDigital Library
- Yann LeCun and Yoshua Bengio. 1995. Convolutional networks for images, speech, and timeseries. In The Handbook of Brain Theory and Neural Networks, M. A. Arbib (Ed.). MIT Press. Google ScholarDigital Library
- A. Antoniades, L. Spyrou, C. C. Took, and S. Sanei. 2016. Deep learning for epileptic intracranial EEG data. In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). 1--6.Google Scholar
- P. Bashivan, I. Rish, M. Yeasin, and N. Codella. 2016. Learning representations from EEG with deep recurrent-convolutional neural networks. In ICLR 2016.Google Scholar
- S. Stober. 2016. Learning discriminative features from electroencephalography recordings by encoding similarity constraints. In Bernstein Conference 2016.Google Scholar
- Siddharth Pramod, Adam Page, Tinoosh Mohsenin, and Tim Oates. 2014. Detecting epileptic seizures from EEG data using neural networks. ArXiv Preprint arXiv:1412.6502 (2014).Google Scholar
- J. T. Turner, Adam Page, Tinoosh Mohsenin, and Tim Oates. 2014. Deep belief networks used on high-resolution multichannel electroencephalography data for seizure detection. In 2014 AAAI Spring Symposium Series.Google Scholar
- D. F. Wulsin, J. R. Gupta, R. Mani, J. A. Blanco, and B. Litt. 2011. Modeling electroencephalography waveforms with semi-supervised deep belief nets: Fast classification and anomaly measurement. Journal of Neural Engineering 8, 3 (2011), 036015.Google ScholarCross Ref
- Alexander Rosenberg Johansen, Jing Jin, Tomasz Maszczyk, and Justin Dauwels. 2016. Epileptiform spike detection via convolutional neural networks. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 754--758.Google ScholarDigital Library
- Andreas Antoniades, Loukianos Spyrou, Clive Cheong Took, and Saeid Sanei. 2016. Deep learning for epileptic intracranial EEG data. In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 1--6.Google ScholarCross Ref
- Dazi Li, Guifang Wang, Tianheng Song, and Qibing Jin. 2016. Improving convolutional neural network using accelerated proximal gradient method for epilepsy diagnosis. In 2016 UKACC 11th International Conference on Control (CONTROL). IEEE, 1--6.Google ScholarCross Ref
- Akara Supratak, Ling Li, and Yike Guo. 2014. Feature extraction with stacked autoencoders for epileptic seizure detection. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 4184--4187.Google ScholarCross Ref
- Yu Qi, Yueming Wang, Jianmin Zhang, Junming Zhu, and Xiaoxiang Zheng. 2014. Robust deep network with maximum correntropy criterion for seizure detection. BioMed Research International 2014, Article 703816 (2014), 10 pages.Google Scholar
- Bo Yan, Yong Wang, Yuheng Li, Yejiang Gong, Lu Guan, and Sheng Yu. 2016. An EEG signal classification method based on sparse auto-encoders and support vector machine. In 2016 IEEE/CIC International Conference on Communications in China (ICCC). IEEE, 1--6.Google ScholarCross Ref
- A. Gogna, A. Majumdar, and R. Ward. 2017. Semi-supervised stacked label consistent autoencoder for reconstruction and analysis of biomedical signals. IEEE Transactions on Biomedical Engineering 64, 9 (2017), 2196--2205.Google ScholarCross Ref
- Yann LeCun, Yoshua Bengio, and Geoffrey E. Hinton. 2015. Deep learning. Nature 521 (2015), 436--444.Google ScholarCross Ref
- M. Alhussein et al. 2018. Cognitive IoT-Cloud integration for smart healthcare: Case study for epileptic seizure detection and monitoring. MONET 23, 6 (2018), 1624--1635. Google ScholarDigital Library
- Ali Shoeb. 2009. Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. PhD thesis, Massachusetts Institute of Technology, 2009.Google Scholar
- R. T. Canolty, E. Edwards, S. S. Dalal, M. Soltani, and R. T. Knight. 2006. High gamma power is phase-locked to theta oscillations in human neocortex. Science 313 (2006), 1626--1628.Google ScholarCross Ref
- Djork-Arne Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2016. Fast and accurate deep network learning by exponential linear units (ELUs). ArXiv e-Prints volume 1511:page arXiv:1511.07289.Google Scholar
- N. Srivastava, Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, and R. Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15 (2014), 1929--1958. Google ScholarDigital Library
- S. Ioffe and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning. 448--456. Google ScholarDigital Library
- Christian Szegedy, Vincent Vanhoucke, and Sergey Ioffe. 2015. Rethinking the inception architecture for computer vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818--2826Google Scholar
- Robin Tibor Schirrmeister, Jost Tobias Springenberg, Martin Glasstetter, Katharina Eggensperger, and Tonio Ball. 2017. Deep learning with convolutional neural networks for EEG decoding and visualization. Human Brain Mapping 38 (2017), 5391--5420.Google ScholarCross Ref
- S. Wilson, M. Scheuer, and R. Emerson. 2004. Seizure detection: Evaluation of the reveal algorithm. Clinical Neurophysiology 10 (2004), 228--2291.Google Scholar
- P. Fergus, A. Hussain, David Hignett, Khaled Abdel-Aziz, and Hani Hamdan. 2016. A machine learning system for automated whole-brain seizure detection. Applied Computing and Informatics 12, 1 (2016), 70--89.Google ScholarCross Ref
- A. Supratak, L. Li, and Y. Guo. 2014. Feature extraction with stacked autoencoders for epileptic seizure detection. In 36th annual International Conference of the IEEE Engineering in Medicine and Biology Society. 4184--4187.Google Scholar
- G. Xun, X. Jia, and A. Zhang. 2015. Context-learning based electroencephalogram analysis for epileptic seizure detection. In IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 325--330. Google ScholarDigital Library
- D. Chen, S. Wan, J. Xiang, and F. S. Bao. 2017. A high-performance seizure detection algorithm based on discrete wavelet transform (DWT) and EEG. PLOS ONE 12, 3 (2017), e0173138.Google ScholarCross Ref
Index Terms
- Applying Deep Learning for Epilepsy Seizure Detection and Brain Mapping Visualization
Recommendations
A Multi-view Deep Learning Method for Epileptic Seizure Detection using Short-time Fourier Transform
ACM-BCB '17: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health InformaticsWith the advances in pervasive sensor technologies, physiological signals can be captured continuously to prevent the serious outcomes caused by epilepsy. Detection of epileptic seizure onset on collected multi-channel electroencephalogram (EEG) has ...
Cost-Sensitive Deep Active Learning for Epileptic Seizure Detection
BCB '18: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health InformaticsThe analysis of electroencephalogram (EEG) signal plays a crucial role in epileptic seizure detection. Researchers have proposed many machine learning and deep learning based automatic epileptic seizure detection methods. However, these schemes, ...
An efficient detection of epileptic seizure by differentiation and spectral analysis of electroencephalograms
Epilepsy is a critical neurological disorder resulting from abnormal hyper-excitability of neurons in the brain. Studies have shown that epilepsy can be detected in electroencephalography (EEG) recordings of patients suffering from seizures. The ...
Comments