Time-Frequency Decomposition of Scalp Electroencephalograms Improves Deep Learning-Based Epilepsy Diagnosis

Time-Frequency Decomposition of Scalp Electroencephalograms Improves Deep Learning-Based Epilepsy Diagnosis

Thangavel, Prasanth (Nanyang Technological University)
Thomas, John (Nanyang Technological University)
Peh, Wei Yan (Nanyang Technological University)
Jing, Jin (Harvard Medical School)
Yuvaraj, Rajamanickam (Nanyang Technological University; National Institute of Education)
Cash, Sydney S. (Harvard Medical School)
Chaudhari, Rima (Fortis Hospital Mulund, Mumbai)
Saini, Vinay (Indian Institute of Technology Bombay)
Dauwels, J.H.G. (TU Delft Signal Processing Systems; Nanyang Technological University)

2021

Epilepsy diagnosis based on Interictal Epileptiform Discharges (IEDs) in scalp electroencephalograms (EEGs) is laborious and often subjective. Therefore, it is necessary to build an effective IED detector and an automatic method to classify IED-free versus IED EEGs. In this study, we evaluate features that may provide reliable IED detection and EEG classification. Specifically, we investigate the IED detector based on convolutional neural network (ConvNet) with different input features (temporal, spectral, and wavelet features). We explore different ConvNet architectures and types, including 1D (one-dimensional) ConvNet, 2D (two-dimensional) ConvNet, and noise injection at various layers. We evaluate the EEG classification performance on five independent datasets. The 1D ConvNet with preprocessed full-frequency EEG signal and frequency bands (delta, theta, alpha, beta) with Gaussian additive noise at the output layer achieved the best IED detection results with a false detection rate of 0.23/min at 90% sensitivity. The EEG classification system obtained a mean EEG classification Leave-One-Institution-Out (LOIO) cross-validation (CV) balanced accuracy (BAC) of 78.1% (area under the curve (AUC) of 0.839) and Leave-One-Subject-Out (LOSO) CV BAC of 79.5% (AUC of 0.856). Since the proposed classification system only takes a few seconds to analyze a 30-min routine EEG, it may help in reducing the human effort required for epilepsy diagnosis.

convolutional neural networks
Deep learning
EEG classification
interictal epileptiform discharges
multiple features
noise injection

http://resolver.tudelft.nl/uuid:14264baf-3fa4-4cc7-8028-0f817f4e0bed

https://doi.org/10.1142/S0129065721500325

2022-01-31

0129-0657

International Journal of Neural Systems, 31 (8), 2150032-1 2150032-16

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2021 Prasanth Thangavel, John Thomas, Wei Yan Peh, Jin Jing, Rajamanickam Yuvaraj, Sydney S. Cash, Rima Chaudhari, Vinay Saini, J.H.G. Dauwels, More Authors