Abstract Deep brain stimulation (DBS) is an internationally accepted form of treatment option for selected patients with Parkinson’s disease and dystonia. Intraoperative extracellular microelectrode recordings (MER) are considered as the standard electrophysiological method for the precise positioning of the DBS electrode into the target brain structure. Pre-processing of MERs is a key phase in clinical analysis, with intraoperative microelectrode recordings being prone to several artifact groups (up to 25 %). The aim of this methodological article is to provide a convolutional neural network (CNN) processing pipeline for the detection of artifacts in an MER. We applied continuous wavelet transform (CWT) to generate an over-complete time–frequency representation. We demonstrated that when attempting to find artifacts in an MER, the new CNN + CWT provides a high level of accuracy (ACC = 88.1 %), identifies individual classes of artifacts (ACC = 75.3 %) and also offers artifact time onset detail, which can lead to a reduction in false positives/negatives. In summary, the presented methodology is capable of identifying and removing various artifacts in a comprehensive database of MER and represents a substantial improvement over the existing methodology. We believe that this approach will assist in the proposal of interesting clinical hypotheses and will have neurologically relevant effects.

中文翻译：

---

使用小波分析和卷积神经网络识别微记录伪像：一种图像识别方法

摘要 脑深部电刺激 (DBS) 是国际公认的帕金森病和肌张力障碍患者的一种治疗选择。术中细胞外微电极记录 (MER) 被认为是将 DBS 电极精确定位到目标大脑结构中的标准电生理方法。MER 的预处理是临床分析的关键阶段，术中微电极记录容易出现几个伪影组（高达 25%）。这篇方法论文章的目的是提供一个卷积神经网络 (CNN) 处理管道，用于检测 MER 中的伪影。我们应用连续小波变换 (CWT) 来生成过完备的时频表示。我们证明了在尝试在 MER 中查找工件时，新的 CNN + CWT 提供了高水平的准确度 (ACC = 88.1 %)，识别各个类别的伪影 (ACC = 75.3 %) 并提供伪影发生时间的细节，这可以减少假阳性/阴性。总之，所提出的方法能够识别和删除 MER 综合数据库中的各种工件，并且代表了对现有方法的重大改进。我们相信这种方法将有助于提出有趣的临床假设，并将产生神经学相关的影响。所提出的方法能够识别和删除 MER 综合数据库中的各种工件，并且是对现有方法的重大改进。我们相信这种方法将有助于提出有趣的临床假设，并将产生神经学相关的影响。所提出的方法能够识别和删除 MER 综合数据库中的各种工件，并且是对现有方法的重大改进。我们相信这种方法将有助于提出有趣的临床假设，并将产生神经学相关的影响。