Automatic seizure detection plays a significant role in monitoring and diagnosis of epilepsy. This paper presents an efficient automatic seizure detection method based on Stockwell transform (S-transform) and bidirectional long short-term memory (BiLSTM) neural networks for intracranial EEG recordings. First, S-transform is applied to raw EEG segments, and the obtained matrix is grouped into time-frequency blocks as the inputs fed into BiLSTM for feature selecting and classification. Afterwards, postprocessing is adopted to improve detection performance, which includes moving average filter, threshold judgment, multichannel fusion, and collar technique. A total of 689 h intracranial EEG recordings from 20 patients are used for evaluation of the proposed system. Segment-based assessment results show that our system achieves a sensitivity of 98.09% and specificity of 98.69%. For the event-based evaluation, a sensitivity of 96.3% and a false detection rate of 0.24/h are yielded. The satisfactory results indicate that this seizure detection approach possess promising potential for clinical practice.

中文翻译：

---

基于Stockwell变换和双向长时短期记忆的癫痫发作检测。

自动癫痫发作检测在癫痫的监测和诊断中起着重要作用。本文提出了一种基于Stockwell变换（S-transform）和双向长短期记忆（BiLSTM）神经网络的高效自动发作检测方法，用于颅内脑电图记录。首先，将S变换应用于原始EEG片段，并将获得的矩阵分组为时频块，作为输入到BiLSTM中以进行特征选择和分类的输入。之后，采用后处理来提高检测性能，包括移动平均滤波器，阈值判断，多通道融合和项圈技术。来自20位患者的总共689小时的颅内EEG记录用于评估所提议的系统。基于细分的评估结果表明，我们的系统达到了98的灵敏度。09％，特异性为98.69％。对于基于事件的评估，灵敏度为96.3％，错误检测率为0.24 / h。令人满意的结果表明，这种癫痫发作检测方法在临床实践中具有广阔的应用前景。