Department of Informatics, Faculty of Engineering, Yamagata University, Yonezawa, Yamagata, 992-8510, Japan.
J Neural Eng. 2018 Jun;15(3):036030. doi: 10.1088/1741-2552/aab84c. Epub 2018 Mar 21.
In the current study, we tested a proposed method for fast spike detection in electroencephalography (EEG).
We performed eigenvalue analysis in two-dimensional space spanned by gradients calculated from two neighboring samples to detect high-amplitude negative peaks. We extracted the spike candidates by imposing restrictions on parameters regarding spike shape and eigenvalues reflecting detection characteristics of individual medical doctors. We subsequently performed clustering, classifying detected peaks by considering the amplitude distribution at 19 scalp electrodes. Clusters with a small number of candidates were excluded. We then defined a score for eliminating spike candidates for which the pattern of detected electrodes differed from the overall pattern in a cluster. Spikes were detected by setting the score threshold.
Based on visual inspection by a psychiatrist experienced in EEG, we evaluated the proposed method using two statistical measures of precision and recall with respect to detection performance. We found that precision and recall exhibited a trade-off relationship. The average recall value was 0.708 in eight subjects with the score threshold that maximized the F-measure, with 58.6 ± 36.2 spikes per subject. Under this condition, the average precision was 0.390, corresponding to a false positive rate 2.09 times higher than the true positive rate. Analysis of the required processing time revealed that, using a general-purpose computer, our method could be used to perform spike detection in 12.1% of the recording time. The process of narrowing down spike candidates based on shape occupied most of the processing time.
Although the average recall value was comparable with that of other studies, the proposed method significantly shortened the processing time.
本研究旨在测试一种用于快速检测脑电图（EEG）中尖峰的方法。
我们在由两个相邻样本的梯度计算得到的二维空间中进行特征值分析，以检测高振幅负峰。我们通过对尖峰形状和特征值的参数施加限制，提取尖峰候选者，这些特征值反映了个别医生的检测特征。随后，我们通过考虑 19 个头皮电极处的振幅分布，对检测到的峰进行聚类，对检测到的峰进行分类。排除候选者数量较少的簇。然后，我们定义了一个分数来消除那些检测到的电极模式与簇中总体模式不同的尖峰候选者。通过设置分数阈值来检测尖峰。
根据一位有经验的脑电图精神病学家的视觉检查，我们使用精度和召回率这两个统计指标来评估该方法的检测性能。我们发现精度和召回率之间存在权衡关系。在八个被试中，当分数阈值最大化 F 度量时，平均召回值为 0.708，每个被试的平均召回值为 58.6 ± 36.2 个尖峰。在这种情况下，平均精度为 0.390，对应的假阳性率比真阳性率高 2.09 倍。对所需处理时间的分析表明，使用通用计算机，我们的方法可以在记录时间的 12.1%内进行尖峰检测。根据形状缩小尖峰候选者的过程占据了大部分处理时间。
虽然平均召回值与其他研究相当，但该方法显著缩短了处理时间。
