Augmenting DL with Adversarial Training for Robust Prediction of Epilepsy Seizures

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.

[1]  Francisco Sales,et al.  A Realistic Seizure Prediction Study Based on Multiclass SVM , 2017, Int. J. Neural Syst..

[2]  Zeeshan Syed,et al.  Multi-task seizure detection: addressing intra-patient variation in seizure morphologies , 2016, Machine Learning.

[3]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals , 2017, Comput. Biol. Medicine.

[4]  Ning Wang,et al.  Extracting and Selecting Distinctive EEG Features for Efficient Epileptic Seizure Prediction , 2015, IEEE Journal of Biomedical and Health Informatics.

[5]  Dan Boneh,et al.  The Space of Transferable Adversarial Examples , 2017, ArXiv.

[6]  Sebastian Nowozin,et al.  Adversarially Robust Training through Structured Gradient Regularization , 2018, ArXiv.

[7]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[8]  F. Mormann,et al.  Seizure prediction for therapeutic devices: A review , 2016, Journal of Neuroscience Methods.

[9]  Mohamad Sawan,et al.  Towards accurate prediction of epileptic seizures: A review , 2017, Biomed. Signal Process. Control..

[10]  Yann LeCun,et al.  Classification of patterns of EEG synchronization for seizure prediction , 2009, Clinical Neurophysiology.

[11]  Joseph Picone,et al.  Deep Architectures for Automated Seizure Detection in Scalp EEGs , 2017, ArXiv.

[12]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[14]  Haidar Khan,et al.  Focal Onset Seizure Prediction Using Convolutional Networks , 2018, IEEE Transactions on Biomedical Engineering.

[15]  Joseph Picone,et al.  Deep Architectures for Spatio-Temporal Modeling: Automated Seizure Detection in Scalp EEGs , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[16]  P. Kwan,et al.  Early identification of refractory epilepsy. , 2000, The New England journal of medicine.

[17]  Mei-Yuh Hwang,et al.  Training Augmentation with Adversarial Examples for Robust Speech Recognition , 2018, INTERSPEECH.

[18]  Patrick D. McDaniel,et al.  On the (Statistical) Detection of Adversarial Examples , 2017, ArXiv.

[19]  Rabab K. Ward,et al.  Epileptic Seizure Detection: A Deep Learning Approach , 2018, 1803.09848.

[20]  Jiawei Yang,et al.  Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram , 2018, Neural Networks.

[21]  Stephen M. Myers,et al.  Seizure prediction: Methods , 2011, Epilepsy & Behavior.

[22]  Simon Fong,et al.  Epileptic Seizures Prediction Using Machine Learning Methods , 2017, Comput. Math. Methods Medicine.

[23]  David M. Himes,et al.  Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: a first-in-man study , 2013, The Lancet Neurology.

[24]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[25]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[26]  Uwe Heinemann,et al.  Network activity in hippocampal slice cultures revealed by long-term in vitro recordings , 2013, Journal of Neuroscience Methods.

[27]  J. Gotman,et al.  A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device , 1997, IEEE Transactions on Biomedical Engineering.

[28]  Terence O'Brien,et al.  Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System , 2017, EBioMedicine.

[29]  Mojtaba Bandarabadi,et al.  Epileptic seizure prediction using relative spectral power features , 2015, Clinical Neurophysiology.

[30]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[31]  P. Genton,et al.  Current limitations of antiepileptic drug therapy: a conference review , 2003, Epilepsy Research.