Magnetoencephalography (MEG) is a useful tool for clinically evaluating the localization of interictal spikes. Neurophysiologists visually identify spikes from the MEG waveforms and estimate the equivalent current dipoles (ECD). However, presently, these analyses are manually performed by neurophysiologists and are time-consuming. Another problem is that spike identification from MEG waveforms largely depends on neurophysiologists’ skills and experiences. These problems cause poor cost-effectiveness in clinical MEG examination. To overcome these problems, we fully automated spike identification and ECD estimation using a deep learning approach fully automated AI-based MEG interictal epileptiform discharge identification and ECD estimation (FAMED). We applied a semantic segmentation method, which is an image processing technique, to identify the appropriate times between spike onset and peak and to select appropriate sensors for ECD estimation. FAMED was trained and evaluated using clinical MEG data acquired from 375 patients. FAMED training was performed in two stages: in the first stage, a classification network was learned, and in the second stage, a segmentation network that extended the classification network was learned. The classification network had a mean AUC of 0.9868 (10-fold patient-wise cross-validation); the sensitivity and specificity were 0.7952 and 0.9971, respectively. The median distance between the ECDs estimated by the neurophysiologists and those using FAMED was 0.63 cm. Thus, the performance of FAMED is comparable to that of neurophysiologists, and it can contribute to the efficiency and consistency of MEG ECD analysis.

中文翻译：

---

使用深度学习对癫痫 MEG 进行全自动尖峰检测和偶极子分析


脑磁图（MEG）是临床评估发作间期尖峰定位的有用工具。神经生理学家直观地识别 MEG 波形中的尖峰并估计等效电流偶极子 (ECD)。然而，目前这些分析是由神经生理学家手动进行的，并且非常耗时。另一个问题是，从 MEG 波形中识别尖峰很大程度上取决于神经生理学家的技能和经验。这些问题导致临床MEG检查成本效益较差。为了克服这些问题，我们使用深度学习方法完全自动化的尖峰识别和 ECD 估计，基于人工智能的 MEG 发作间期癫痫样放电识别和 ECD 估计 (FAMED)。我们应用语义分割方法（一种图像处理技术）来识别尖峰开始和峰值之间的适当时间，并选择适当的传感器进行 ECD 估计。 FAMED 使用从 375 名患者获得的临床 MEG 数据进行了培训和评估。 FAMED训练分两个阶段进行：第一阶段学习分类网络，第二阶段学习扩展分类网络的分割网络。分类网络的平均 AUC 为 0.9868（10 倍患者交叉验证）；敏感性和特异性分别为 0.7952 和 0.9971。神经生理学家估计的 ECD 与使用 FAMED 估计的 ECD 之间的中位距离为 0.63 厘米。因此，FAMED 的性能可与神经生理学家的性能相媲美，并且有助于提高 MEG ECD 分析的效率和一致性。