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

Journal Article (2021)
Author(s)

Prasanth Thangavel (Nanyang Technological University)

John Thomas (Nanyang Technological University)

Wei Yan Peh (Nanyang Technological University)

Jin Jing (Harvard Medical School)

Rajamanickam Yuvaraj (National Institute of Education, Nanyang Technological University)

Sydney S. Cash (Harvard Medical School)

Rima Chaudhari (Fortis Hospital Mulund, Mumbai)

Vinay Saini (Indian Institute of Technology Bombay)

Justin Dauwels (Nanyang Technological University, TU Delft - Electrical Engineering, Mathematics and Computer Science)

undefined More Authors (External organisation)

Research Group
Signal Processing Systems
DOI related publication
https://doi.org/10.1142/S0129065721500325 Final published version
More Info
expand_more
Publication Year
2021
Language
English
Research Group
Signal Processing Systems
Issue number
8
Volume number
31
Article number
2150032
Pages (from-to)
2150032-1 2150032-16
Downloads counter
423
Collections
Institutional Repository
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

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.

Files

S0129065721500325.pdf
(pdf | 2.28 Mb)
- Embargo expired in 31-01-2022
License info not available