Cheng Chenchen, Liu Yan, You Bo, Zhou Yuanfeng, Gao Fei, Yang Liling, Dai Yakang
IEEE Trans Neural Syst Rehabil Eng. 2022;30:2506-2516. doi: 10.1109/TNSRE.2022.3193666. Epub 2022 Sep 8.
Interictal epileptiform spike (referred to as spike) detected from electroencephalograms lasting only 20- to 200-ms can provide a reliable evidence-based indicator for clinical seizure type diagnosis. Recent feature representation approaches focus either on the concrete-level or abstract-level information mining of the spike, thus demonstrating suboptimal detection performance. Additionally, existing abstract-level information mining methods of the spike based deep learning networks have not realized the effective feature representation of long-term dependent distinguished information within similar waveform cycles caused by morphological heterogeneity, which affects detection performance. Thus, a multilevel feature learning method for accurate spike detection was proposed in this study. Specifically, the spatio-temporal-frequency multidomain information in concrete-level first are inferred the common mimetic properties of the spike using the multidomain feature extractors. Then, the effective feature representation of long-term dependent distinguished information within similar waveform cycles caused by morphological heterogeneity is suitably captured using the temporal convolutional network. Finally, the spatio-temporal-frequency multidomain long-term dependent feature representation of spike is calculated using the element-wise manner to fuse the feature representation in concrete- and abstract-levels. The experimental results indicate that the proposed method can achieve an accuracy of 90.62±1.38%, sensitivity of 90.38±1.52%, specificity of 91.00±1.60%, precision of 90.33±4.71%, and the false detection rate per minute is [Formula: see text], which are higher than when using the feature representation in the concrete-or abstract-level alone. Additionally, the detection results indicate that the proposed method avoids the subjectivity and inefficiency of visual inspection, and it enables a highly accurate detection of the spike.
从脑电图中检测到的发作间期癫痫样棘波（简称棘波），其持续时间仅为20至200毫秒，可为临床癫痫发作类型诊断提供可靠的循证指标。近期的特征表示方法要么侧重于棘波的具体层面信息挖掘，要么侧重于抽象层面信息挖掘，因此检测性能欠佳。此外，现有的基于深度学习网络的棘波抽象层面信息挖掘方法，尚未实现对由形态异质性导致的相似波形周期内长期依赖的显著信息的有效特征表示，这影响了检测性能。因此，本研究提出了一种用于准确检测棘波的多级特征学习方法。具体而言，首先利用多域特征提取器在具体层面推断棘波的时空频率多域信息，以得出其共同的模拟特性。然后，使用时间卷积网络适当地捕捉由形态异质性导致的相似波形周期内长期依赖的显著信息的有效特征表示。最后，采用逐元素方式计算棘波的时空频率多域长期依赖特征表示，以融合具体层面和抽象层面的特征表示。实验结果表明，所提方法的准确率可达90.62±1.38%，灵敏度为90.38±1.52%，特异性为91.00±1.60%，精确率为90.33±4.71%，每分钟误检率为[公式：见原文]，均高于单独使用具体层面或抽象层面特征表示时的情况。此外，检测结果表明，所提方法避免了目视检查的主观性和低效性，能够实现对棘波的高精度检测。
