Background and Objectives: Epilepsy is a clinical phenomenon caused by sudden abnormal and excessive discharge of brain neurons. It affects around 70 million people all over the world. Seizure detection from Electroencephalography (EEG) has achieved rapid development. However, existing methods often extract features from single channel EEG while ignoring the spatial relationship between different EEG channels. To fill this gap, a novel seizure detection model based on linear graph convolution network (LGCN) was proposed to enhance the feature embedding of raw EEG signals during seizure and non-seizure periods. Method: Pearson correlation matrix of raw EEG signals was calculated to build the input graph of the graph neural network where the coefficients of the matrix models the spatial relations in EEG signals. The last softmax layer makes the final decision (seizure vs. non-seizure). In addition, focal loss was utilized to redefine the loss function of LGCN to deal with the data imbalance problem during seizure detection. Results: Experiments are conducted on the CHB-MIT dataset. The seizure detection accuracy, specificity, sensitivity, F1 and Auc are 99.30%, 98.82%, 99.43%, 98.73% and 98.57% respectively. Conclusions: The proposed approach yields superior performance over the-state-of-the-art in seizure detection tasks on the CHB-MIT dataset. Our method works in an end-to-end manner and it does not need manually designed features. The ability to deal with imbalanced data is also attractive in real seizure detection scenarios where the duration of seizures is much shorter than the lasting time of non-seizure events.

背景与目的：癫痫是由脑神经元突然异常、过度放电引起的一种临床现象。它影响着全世界约 7000 万人。脑电图（EEG）癫痫发作检测已取得快速发展。然而，现有方法往往从单通道脑电图中提取特征，而忽略了不同脑电图通道之间的空间关系。为了填补这一空白，提出了一种基于线性图卷积网络 (LGCN) 的新型癫痫检测模型，以增强癫痫和非癫痫期间原始 EEG 信号的特征嵌入。方法：计算原始 EEG 信号的 Pearson 相关矩阵以构建图神经网络的输入图，其中矩阵的系数模拟 EEG 信号中的空间关系。最后一个 softmax 层做出最终决定（seizure 与 non-seizure）。此外，利用焦点损失重新定义了 LGCN 的损失函数，以处理癫痫检测过程中的数据不平衡问题。结果：实验是在 CHB-MIT 数据集上进行的。癫痫检测准确率、特异性、灵敏度、F1和Auc分别为99.30%、98.82%、99.43%、98.73%和98.57%。结论：所提出的方法在 CHB-MIT 数据集上的癫痫检测任务中产生了优于最先进技术的性能。我们的方法以端到端的方式工作，不需要手动设计的功能。在实际癫痫发作检测场景中，处理不平衡数据的能力也很有吸引力，其中癫痫发作的持续时间比非癫痫发作事件的持续时间短得多。