In this paper, we propose a novel method for automatic k-complex (KC) detection in human sleep EEG, named MT-KCD. KCs are slow oscillations in the EEG signal characterized by a well-delineated, negative, sharp waves immediately followed by a positive component standing out from the background, with high-amplitude and total duration ≥ 0.5 s. Among the important aspects of the KC are its homeostatic and reactive functions in the brain, functioning as a sleep protection mechanism, and its practical use as a marker of N2 sleep stage during sleep studies. Given the importance of the KC, and the effort required from human experts to analyze EEG recordings visually, some recent research works have proposed automatic methods for KC detection. In comparison with existing methods, a key feature and novelty of MT-KCD is the use of multitaper spectral analysis to pre-process the EEG signal and automatically extract candidate KCs from it (characterized as 0-4 Hz power concentrations standing out from the background). After extraction, candidates are accepted/rejected depending on time domain characteristics (peak-to-peak amplitude ≥ 75 µV, duration ≤ 2 s). The method overall time complexity is $\mathcal{O}(N·\log N)$. Regarding effectiveness, we have evaluated MT-KCD by using a public KC database (DREAMS) consisting of ten polysomnographic recordings of healthy patients (6 female and 4 male subjects with age range 20–47 years) partially annotated by two experts. Results have shown that MT-KCD improves detection metrics, especially F1 and F2 scores (harmonic averages of recall and precision), when compared to existing methods. Besides, improving F1 and F2 scores, MT-KCD also contributes to the automatic analysis of sleep EEG multitaper spectrograms, a technique recently proposed by researchers in the area of sleep studies as a complement to the traditional hypnogram (sleep stages diagram).

在本文中，我们提出了一种新的用于人类睡眠脑电图自动k复杂（KC）检测的方法，称为MT-KCD。KC是EEG信号中的缓慢振荡，其特征是轮廓清晰，消极，尖锐的波，紧随其后的是正成分，从背景中突出出来，振幅高，总持续时间≥0.5 s。KC的重要方面包括其在大脑中的稳态和反应功能，作为睡眠保护机制，以及在睡眠研究中作为N2睡眠阶段标志物的实际用途。考虑到KC的重要性，以及人类专家需要进行视觉分析脑电图记录的工作，一些最近的研究工作提出了自动检测KC的方法。与现有方法相比，MT-KCD的关键特征和新颖之处在于使用多锥光谱分析对EEG信号进行预处理，并自动从中提取候选KC（特征为0-4 Hz功率浓度突出于背景）。提取后，将根据时域特性（峰峰值幅度≥75 µV，持续时间≤2 s）接受/拒绝候选对象。该方法的总时间复杂度为$\mathcal{Ø}（ñ·\mathrm{日志}ñ）$。关于有效性，我们通过使用公共KC数据库（DREAMS）评估了MT-KCD，该数据库由十位健康患者（6位女性和4位年龄在20-47岁的男性受试者）的多导睡眠图记录组成，部分由两名专家进行注释。结果表明，与现有方法相比，MT-KCD改善了检测指标，尤其是F1和F2分数（召回率和精确度的谐波平均值）。此外，通过改善F1和F2分数，MT-KCD还有助于自动分析睡眠脑电多谱图，这是研究人员最近在睡眠研究领域提出的一种技术，可作为对传统催眠图（睡眠阶段图）的补充。