Elimination of pseudo-HFOs in iEEG using sparse representation and Random Forest classifier.
Elimination of pseudo-HFOs in iEEG using sparse representation and Random Forest classifier.
复制标题
DOI：
10.1109/embc48229.2022.9871447
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
高频振荡（HFO）是一种有前景的致痫区生物标志物。然而，尖锐的伪影可能很容易像真正的 HFO 一样通过传统的 HFO 探测器，并减少癫痫发作区 (SOZ) 定位。我们假设，与源自具有急剧变化或任意波形特征的伪影的伪 HFO 不同，真正的 HFO 可以由有限数量的振荡波形表示。因此，为了区分真实的 HFO 和伪 HFO，我们建立了一种基于候选事件稀疏表示的新分类方法，该方法通过了灵敏度高但特异性低的初始检测器。具体来说，使用正交匹配追踪 (OMP) 和冗余 Gabor 字典，每个事件都以迭代方式稀疏表示。近似误差通过 30 次迭代进行估计，这些迭代被连接起来形成 30 维特征向量并馈送到随机森林分类器。基于所选的字典元素，我们的方法可以进一步将 HFO 分类为 Ripples (R) 和 Fast Ripples (FR)。在该方案中，两名专家目视检查了 5 个不同受试者的 iEEG 记录中捕获的 2075 个事件，并将它们标记为真 HFO 或伪 HFO。与传统的基于幅度阈值的检测器相比，我们在标记事件中达到了 90.22% 的分类准确度，并且 SOZ 定位提高了 21.16%。我们的稀疏表示框架还将检测到的 HFO 分为 R 和 FR 子类别。通过检测到的 R+FR 事件，我们的 SOZ 准确度达到了 91.24%。
High-Frequency Oscillation (HFO) is a promising biomarker of the epileptogenic zone. However, sharp artifacts might easily pass the conventional HFO detectors as real HFOs and reduce the seizure onset zone (SOZ) localization. We hypothesize that, unlike pseudo-HFOs, which originates from artifacts with sharp changes or arbitrary waveform characteristic, real HFOs could be represented by a limited number of oscillatory waveforms. Accordingly, to distinguish true ones from pseudo-HFOs, we established a new classification method based on sparse representation of candidate events that passed an initial detector with high sensitivity but low specificity. Specifically, using the Orthogonal Matching Pursuit (OMP) and a redundant Gabor dictionary, each event was represented sparsely in an iterative fashion. The approximation error was estimated over 30 iterations which were concatenated to form a 30-dimensional feature vector and fed to a random forest classifier. Based on the selected dictionary elements, our method can further classify HFOs into Ripples (R) and Fast Ripples (FR). In this scheme, two experts visually inspected 2075 events captured in iEEG recordings from 5 different subjects and labeled them as true-HFO or Pseudo-HFO. We reached 90.22% classification accuracy in labeled events and a 21.16% SOZ localization improvement compared to the conventional amplitude-threshold-based detector. Our sparse representation framework also classified the detected HFOs into R and FR subcategories. We reached 91.24% SOZ accuracy with the detected R+FR events.