A sparse representation strategy to eliminate pseudo-HFO events from intracranial EEG for seizure onset zone localization.
A sparse representation strategy to eliminate pseudo-HFO events from intracranial EEG for seizure onset zone localization.
复制标题
DOI：
10.1088/1741-2552/ac8766
复制
发表时间：
2022-08-24
影响因子：
4
通讯作者：
Ince, Nuri F.
中科院分区：
文献类型：
--
作者：
Besheli, Behrang Fazli;Sha, Zhiyi;Gavvala, Jay R.;Gurses, Candan;Karamursel, Sacit;Quach, Michael M.;Curry, Daniel J.;Sheth, Sameer A.;Francis, David J.;Henry, Thomas R.;Ince, Nuri F.
高频振荡（HFO）被认为是颅内EEG记录中致痫区的生物标志物。然而，自动HFO探测器混淆了真实的振荡与伪影的存在所引起的虚假事件。我们假设，与具有尖锐瞬态或任意形状的伪HFO不同，真实的HFO具有可以使用少量振荡基底来表示的信号特性。基于这一假设，使用稀疏表示框架，本研究介绍了一种新的分类方法，以区分真正的HFO的伪事件，误导癫痫发作区（SOZ）定位。此外，我们进一步分类的HFO的波纹和快速波纹通过引入一个自适应的重建方案，使用稀疏表示。通过可视化从16名患者记录的事件的原始波形和时间-频率表示，三位专家标记了6400个通过基于初始幅度阈值的HFO检测器的候选事件。我们形成了一个冗余的分析多尺度字典建立从光滑振荡的Gabor原子和表示每个事件的正交匹配追踪，通过使用少量的字典元素。我们在每次迭代时使用近似误差和残差信号来提取可以将HFO与任何类型的伪影区分开的特征，而不管它们的对应来源。我们在16名受试者身上验证了我们的模型，每个受试者都有30分钟的连续发作间期iEEG记录。我们表明，应用我们的方法后，SOZ检测的准确性显着提高。特别是，我们在标记事件中实现了96.65%的分类准确率，在连续数据上SOZ检测提高了17.57%。我们的稀疏表示框架也可以区分波纹和快速波纹。我们表明，通过使用稀疏表示方法，我们可以从事件池中删除伪HFO，并提高在大数据集中检测到的HFO的可靠性，并最大限度地减少手动消除伪影。
High-frequency oscillations (HFOs) are considered a biomarker of the epileptogenic zone in intracranial EEG recordings. However, automated HFO detectors confound true oscillations with spurious events caused by the presence of artifacts. We hypothesized that, unlike pseudo-HFOs with sharp transients or arbitrary shapes, real HFOs have a signal characteristic that can be represented using a small number of oscillatory bases. Based on this hypothesis using a sparse representation framework, this study introduces a new classification approach to distinguish true HFOs from the pseudo-events that mislead seizure onset zone (SOZ) localization. Moreover, we further classified the HFOs into ripples and fast ripples by introducing an adaptive reconstruction scheme using sparse representation. By visualizing the raw waveforms and time-frequency representation of events recorded from 16 patients, three experts labelled 6400 candidate events that passed an initial amplitude-threshold-based HFO detector. We formed a redundant analytical multiscale dictionary built from smooth oscillatory Gabor atoms and represented each event with orthogonal matching pursuit by using a small number of dictionary elements. We used the approximation error and residual signal at each iteration to extract features that can distinguish the HFOs from any type of artifact regardless of their corresponding source. We validated our model on sixteen subjects with thirty minutes of continuous interictal iEEG recording from each. We showed that the accuracy of SOZ detection after applying our method was significantly improved. In particular, we achieved a 96.65% classification accuracy in labelled events and a 17.57% improvement in SOZ detection on continuous data. Our sparse representation framework can also distinguish between ripples and fast ripples. We show that by using a sparse representation approach we can remove the pseudo-HFOs from the pool of events and improve the reliability of detected HFOs in large data sets and minimize manual artifact elimination.
登录
查看更多内容
影响因子：
4.7
作者：
Amiri, Mina;Lina, Jean-Marc;Gotman, Jean
通讯作者：
Gotman, Jean
影响因子：
5.3
作者：
Cimbalnik J;Brinkmann B;Kremen V;Jurak P;Berry B;Gompel JV;Stead M;Worrell G
通讯作者：
Worrell G
影响因子：
11.2
作者：
Frauscher, Birgit;von Ellenrieder, Nicolas;Gotman, Jean
通讯作者：
Gotman, Jean
DOI：
10.1093/brain/awv073
发表时间：
2015-06
期刊：
Brain : a journal of neurology
影响因子：
--
作者：
Frauscher B;von Ellenrieder N;Ferrari-Marinho T;Avoli M;Dubeau F;Gotman J
通讯作者：
Gotman J
影响因子：
5.7
作者：
Ball, Tonio;Kern, Markus;Schulze-Bonhage, Andreas
通讯作者：
Schulze-Bonhage, Andreas