Montreal Neurological Institute and Hospital, McGill University, Montreal, Québec, Canada.
Clin Neurophysiol. 2012 Jan;123(1):106-16. doi: 10.1016/j.clinph.2011.06.006. Epub 2011 Jul 16.
High frequency oscillations (HFOs) are a biomarker of epileptogenicity. Visual marking of HFOs is highly time-consuming and inevitably subjective, making automatic detection necessary. We compare four existing detectors on the same dataset.
HFOs and baselines were identified by experienced reviewers in intracerebral EEGs from 20 patients. A new feature of our detector to deal with channels where baseline cannot be found is presented. The original and an optimal configuration are implemented. Receiver operator curves, false discovery rate, and channel ranking are used to evaluate performance.
All detectors improve performance with the optimal configuration. Our detector had higher sensitivity, lower false positives than the others, and similar false detections. The main difference in performance was in very active channels.
Each detector was developed for different recordings and with different aims. Our detector performed better in this dataset, but was developed on data similar to the test data. Moreover, optimizing on a particular data type improves performance in any detector.
Automatic HFO detection is crucial to propel their clinical use as biomarkers of epileptogenic tissue. Comparing detectors on a single dataset is important to analyze their performance and to emphasize the issues involved in validation.
高频振荡（HFOs）是致痫性的生物标志物。HFOs 的视觉标记非常耗时且不可避免地具有主观性，因此需要自动检测。我们在同一数据集上比较了四种现有的检测器。
通过 20 名患者的颅内 EEG 中的有经验的审查者来识别 HFOs 和基线。我们提出了一种新的检测器特征，用于处理无法找到基线的通道。实现了原始配置和最佳配置。使用接收者操作曲线、假发现率和通道排序来评估性能。
所有检测器都通过最佳配置提高了性能。我们的检测器比其他检测器具有更高的灵敏度、更低的假阳性率和相似的假检测。性能的主要差异在于非常活跃的通道。
每个检测器都是为不同的记录和不同的目的而开发的。我们的检测器在这个数据集上表现更好，但它是在类似于测试数据的数据上开发的。此外，针对特定数据类型进行优化可以提高任何检测器的性能。
自动 HFO 检测对于推动其作为致痫性组织的生物标志物的临床应用至关重要。在单个数据集上比较检测器对于分析其性能以及强调验证中涉及的问题非常重要。
