Detecting epileptic seizure through analysis of the electroencephalography (EEG) signal becomes a standard method for the diagnosis of epilepsy. In a manual way, monitoring of long term EEG is tedious and error prone. Therefore, a reliable automatic seizure detection method is desirable. A critical challenge to automatic seizure detection is that seizure morphologies exhibit considerable variabilities. In order to capture essential seizure patterns, this paper leverages an attention mechanism and a bidirectional long short-term memory (BiLSTM) model to exploit both spatially and temporally discriminating features and account for seizure variabilities. The attention mechanism is to capture spatial features more effectively according to the contributions of brain areas to seizures. The BiLSTM model is to extract more discriminating temporal features in the forward and the backward directions. By accounting for both spatial and temporal variations of seizures, the proposed method is more robust across subjects. The testing results over the noisy real data of CHB-MIT show that the proposed method outperforms the current state-of-the-art methods. In both mixing-patients and cross-patient experiments, the average sensitivity and specificity are both higher while their corresponding standard deviations are lower than the methods in comparison.
翻译:通过分析电脑造影学(EEG)信号检测癫痫癫痫癫痫症状成为诊断癫痫病发病的标准方法。用人工方法,长期的EEG监测是乏味和容易出错的。因此,一个可靠的自动缉获检测方法是可取的。自动缉获检测的关键挑战是,缉获形态表现出相当大的差异性。为了捕捉基本缉获模式,本文件利用了一个关注机制和双向长期短期内存(BILSTM)模型,在空间和时间上区别性特征和缉获变异性账户中加以利用。关注机制是根据脑区对缉获的贡献更有效地捕捉空间特征。BILSTM模型是为了在前向和后向提取更多区别性时间特征。考虑到缉获的时空变化,拟议方法在多个学科之间更为牢固。对CHB-MIT的噪音真实数据的测试结果表明,拟议方法在目前状态方法上都超过了现有的方法。在混合住院病人和跨住院实验中,平均敏感度和具体性都高于相应的偏差性。