School of Microelectronics, Shandong University, Jinan 250100, P. R. China.
Int J Neural Syst. 2023 Nov;33(11):2350054. doi: 10.1142/S0129065723500545. Epub 2023 Sep 7.
Early seizure prediction is crucial for epilepsy patients to reduce accidental injuries and improve their quality of life. Identifying pre-ictal EEG from the inter-ictal state is particularly challenging due to their nonictal nature and remarkable similarities. In this study, a novel epileptic seizure prediction method is proposed based on multi-head attention (MHA) augmented convolutional neural network (CNN) to address the issue of CNN's limit of capturing global information of input signals. First, data enhancement is performed on original EEG recordings to balance the pre-ictal and inter-ictal EEG data, and the EEG recordings are sliced into 6-second-long EEG segments. Subsequently, EEG time-frequency distribution is obtained using Stockwell transform (ST), and the attention augmented convolutional network is employed for feature extraction and classification. Finally, post-processing is utilized to reduce the false prediction rate (FPR). The CHB-MIT EEG database was used to evaluate the system. The validation results showed a segment-based sensitivity of 98.24% and an event-based sensitivity of 94.78% with a FPR of 0.05/h were yielded, respectively. The satisfying results of the proposed method demonstrate its possible potential for clinical applications.
早期发作预测对于减少癫痫患者的意外伤害和提高生活质量至关重要。由于其非发作性质和显著的相似性，从发作间期状态中识别发作前期脑电图 (EEG) 特别具有挑战性。在这项研究中，提出了一种基于多头注意力 (MHA) 增强卷积神经网络 (CNN) 的新型癫痫发作预测方法，以解决 CNN 捕获输入信号全局信息的局限性问题。首先，对原始 EEG 记录进行数据增强，以平衡发作前期和发作间期 EEG 数据，并将 EEG 记录切成 6 秒长的 EEG 段。随后，使用 Stockwell 变换 (ST) 获得 EEG 时频分布，并采用注意力增强卷积网络进行特征提取和分类。最后，进行后处理以降低假阳性预测率 (FPR)。使用 CHB-MIT EEG 数据库来评估系统。验证结果分别产生了基于段的敏感性为 98.24%，基于事件的敏感性为 94.78%，假阳性预测率 (FPR) 为 0.05/h。该方法的令人满意的结果表明其在临床应用中具有潜在的应用价值。
