A robust deep learning approach for automatic classification of seizures against non-seizures
A robust deep learning approach for automatic classification of seizures against non-seizures
复制标题
DOI：
10.1016/j.bspc.2020.102215
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Xinghua Yao;Xiaojin Li;Qiang Ye;Y. Huang;Q. Cheng;Guoqiang Zhang
中科院分区：
文献类型：
--
作者：
Xinghua Yao;Xiaojin Li;Qiang Ye;Y. Huang;Q. Cheng;Guoqiang Zhang
通过分析脑电(EEG)信号来识别癫痫发作已成为诊断癫痫的标准方法。由训练有素的神经科医生对脑电进行人工癫痫发作识别耗时、费力，需要一种可靠的癫痫发作/非癫痫发作自动分类方法。癫痫发作/非癫痫发作自动分类的挑战之一是癫痫发作形态表现出相当大的多样性。为了捕捉基本的癫痫发作模式，本文利用注意机制和双向长短期记忆(BiLSTM)来利用空间和时间区分特征并克服癫痫发作的变异性。注意机制根据不同脑区对癫痫发作的贡献来捕捉空间特征。BiLSTM提取正向和反向可区分的时间特征。对CHB-MIT的噪声数据进行了交叉验证实验和交叉患者实验。交叉验证实验获得的平均灵敏度为87.30%，特异度为88.30%，精确度为88.29%，高于目前最先进的方法，标准偏差较低。这些结果表明，我们的方法与当前最先进的方法相比表现得很好，并且在患者中更加健壮。
Identifying epileptic seizures through analysis of the electroencephalography (EEG) signal becomes a standard method for the diagnosis of epilepsy. Manual seizure identification on EEG by trained neurologists is time-consuming, labor-intensive and a reliable automatic seizure/non-seizure classification method is needed. One of the challenges in automatic seizure/non-seizure classification 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) to exploit both spatial and temporal discriminating features and overcome seizure variabilities. The attention mechanism captures spatial features according to the contributions of different brain regions to seizures. BiLSTM extracts discriminating temporal features in forward and backward directions. Cross-validation experiments and cross-patient experiments over the noisy data of CHB-MIT were performed. We obtained average sensitivity of 87.30%, specificity of 88.30% and precision of 88.29% in cross-validation experiments, higher than using the current state-of-the-art methods, and the standard deviations were lower. These results indicate that our approach performs well against current state-of-the-art methods and is more robust across patients.