iEEG Signal Data Augmentation in Convolutional Neural Networks for Epileptic Focus Localization

Abstract

Epileptic focus localization plays a crucial role in the diagnosis and treatment of epilepsy. Convolutional Neural Networks (CNNs) have exhibited promising outcomes in automatically detecting epileptic focus through the analysis of intracranial electroencephalogram (iEEG) signals. However, the limited availability of labeled iEEG dataset, which require specialist annotations, has constrained the effectiveness of CNNs. In this study, data augmentation techniques, including time shifting, amplitude scaling and noise addition, were employed to enhance the diversity and information content of the data. These techniques aimed to enable machine learning models to extract features from various aspects of iEEG data, thereby improving the accuracy of the models. Three deep learning models, namely DeepConvNet, ShallowConvNet and EEGNet, were introduced for the identification of epileptic foci. To evaluate the proposed methods, the Bern-Barcelona iEEG dataset was utilized. The experimental results demonstrated that the augmented dataset, formed by applying the three data augmentation techniques, achieved higher accuracies across all three deep learning models compared to the original dataset. This finding underscores the feasibility and efficacy of the proposed data augmentation and feature extraction methods in automated epilepsy detection.