Utilization of independent component analysis for accurate pathological ripple detection in intracranial EEG recordings recorded extra- and intra-operatively
Introduction
Approximately 30% of patients with epilepsy continue to have disabling seizures despite treatment with multiple antiepileptic drugs (Kwan and Brodie, 2000). Of those patients with focal epilepsy that are resistant to multiple medications, resective surgery is an intervention that has been proven to reduce the seizure burden, improve the patients’ quality of life, and reduce mortality rate (Wiebe et al., 2001, Sperling et al., 2016). The goal of resective epilepsy surgery is to identify and remove epileptogenic brain regions while minimizing residual neurological deficits. High frequency oscillations (HFOs), which consist of brief bursts of energy with spectral content ranging between 80 and 600 Hz, have shown significant promise as a potential biomarker of epileptogenic tissue (Engel et al., 2009, Gotman, 2010, Jacobs et al., 2012). HFOs with a spectral content in the 80–250 Hz band are commonly referred to as ripples, while those in the 250–600 Hz band are termed fast ripples (Staba et al., 2002, Bragin et al., 2002).
HFOs can be identified by visual inspection of intracranial EEG (iEEG), or using automated and unsupervised detection software (Zelmann et al., 2012, Burnos et al., 2014, Gliske et al., 2016). One barrier to utilizing HFOs for clinical decision making is that inter-reader agreement on what constitutes an event is often poor (Spring et al., 2017). Therefore, it is difficult to validate automated HFO detectors. Furthermore, HFO detectors may generate clinically informative results (Weiss et al., 2013, Weiss et al., 2015), in the absence of a gold standard comparison biomarker that can be confirmed visually. This paradox can perhaps be solved by developing a procedure to allow experts to code HFOs from iEEG signals using classes (Jacobs et al., 2008) that generate an agreed upon gold standard for evaluating automated procedures.
HFO detection is performed using recordings in bipolar montage in order to reduce artifact, originating from muscle or the reference electrode, that can mimic HFO events. There are no previously published studies that utilize an automated HFO detector to define events in macroelectrode recordings recorded in referential montage. In theory, performing HFO detection in referential montage provides two advantages. First, referential montage increases the spatial resolution of the iEEG as compared with bipolar montage by increasing the total number of recordings. Second, referential montage could improve HFO detection by increasing the signal to noise ratio, since the dipole generators of the HFO could be distributed across multiple macro-electrode sites, which could obscure the HFO due to in phase cancellation (de la Prida et al., 2016).
In order to identify HFOs in referential montage using an automated detector, it is essential to develop a strategy for reducing or eliminating artifact, that would otherwise be eliminated by a bipolar montage. Independent component analysis (ICA) is a signal processing approach that can separate signal sources based on minimizing mutual information, and assuring that each component has a non-Gaussian distribution (Bell and Sejnowski, 1995, Cardoso, 1997). ICA has been utilized to reduce artifact in scalp EEG (Delorme et al., 2007, McMenamin et al., 2010), and has also been used to remove the scalp reference signal from iEEG recordings (Hu et al., 2007). In this paper, we tested the hypothesis that applying ICA to band-pass filtered iEEG recordings in referential montage could be utilized to accurately detect ripple events even when the recordings are contaminated by artifact.
Section snippets
Patients
Recordings were selected from 11 patients who underwent intracranial monitoring with depth electrodes between 2014 and 2016 at University of California Los Angeles (UCLA) and from five patients at Thomas Jefferson University (TJU) in 2016–2017 for the purpose of localization of the seizure onset zone. The inclusion criteria were at least one night and day of intracranial recording with 2000 Hz sampling rate and at least 4 h of interictal EEG uninterrupted by seizures for the UCLA patients. For
Patient description
The recordings were selected from eleven patients who underwent intracranial monitoring with depth electrodes during sleep, and five patients in which the intracranial monitoring was performed in the operating room using depth electrodes. Among the patients in whom the sleep recordings were selected, three had unilateral mesial temporal lobe epilepsy (MTLE), three patients had bilateral MTLE, three patients had MTLE plus the involvement of neocortical regions, and two patients had neocortical
Discussion
In summary, herein we report that (1) by processing band-pass filtered (80–600 Hz) iEEG signals recorded in referential montage with Infomax ICA we could reduce or eliminate muscle artifact, and demarcate artefactual HFOs, (2) manual validation demonstrated that when a Hilbert detector was used to detect the ripple events in the post-ICA processed referential recordings, it was moderately sensitive and very precise, (3) both the true and false ripple on spike events defined using the detector
Conclusions
We report a novel approach to identify and classify ripple events in iEEG recordings in the referential montage that eliminates or dramatically reduces artifact using Infomax ICA. The detector could also separate true ripple on spike events from false ripple on spike events that result from filter ringing, and accurately define the magnitude and spectral content of the true events. The true and false ripple on spike rates defined by the detector accurately classified the SOZ in a diverse group
Acknowledgements
The authors would like to thank Mr. Dale Wyeth and Mr. Edmund Wyeth at Thomas Jefferson University, and Mr. Kirk Shattuck at University of California Los Angeles for their technical assistance with the experiments.
Conflict of interest statement
The author(s) declare(s) that there is no conflict of interest regarding the publication of this article.
Funding
This work was supported by NIH/NINDS K23NS094633 (SAW).
References (41)
- et al.
Ictal clinical and scalp-EEG findings differentiating temporal lobe epilepsies from temporal 'plus' epilepsies
Brain
(2007) - et al.
Temporal plus epilepsy is a major determinant of temporal lobe surgery failures
Brain
(2016) - et al.
Information-maximization approach to blind separation and blind deconvolution
Technology
(1995) - et al.
Local generation of fast ripples in epileptic brain
J Neurosci
(2002) - et al.
Pitfalls of high-pass filtering for detecting epileptic oscillations: a technical note on “false” ripples
Clin Neurophysiol
(2010) - et al.
Human intracranial high frequency oscillations detected by automatic time-frequency analysis
PLoS ONE
(2014) - et al.
The morphology of high frequency oscillations does not improve delineating the epileptogenic zone
Clin Neurophysiol
(2016) Infomax and maximum likelihood for blind source separation
IEEE Signal Process Lett
(1997)- et al.
Brain oscillations and the importance of waveform shape
Trends Cognitive Sci
(2016) - Davis J, Goadrich M. The relationship between precision-recall and ROC curves. In: ICML '06 proceedings of the 23rd...
Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis
Neuroimage
High-frequency oscillations: what is normal and what is not?
Epilepsia
Universal automated high frequency oscillation detector for real-time, long term EEG
Clin Neurophysiol
High frequency oscillations: the new EEG frontier?
Epilepsia
Automatic identification and removal of scalp reference signal for intracranial eegs based on independent component analysis
IEEE Trans Biomed Eng
Interictal high-frequency oscillations (80–500 Hz) are an indicator of seizure onset areas independent of spikes in the human epileptic brain
Epilepsia
High frequency oscillations (80–500 Hz) in the preictal period in patients with focal seizures
Epilepsia
High-frequency oscillations (HFOs) in clinical epilepsy
Prog Neurobiol
Early identification of refractory epilepsy
N Engl J Med
Cited by (29)
Delta oscillation coupled propagating fast ripples precede epileptiform discharges in patients with focal epilepsy
2022, Neurobiology of DiseaseMEG detection of high frequency oscillations and intracranial-EEG validation in pediatric epilepsy surgery
2021, Clinical NeurophysiologyCitation Excerpt :Secondly, in the study by Velmurugan and colleagues every spike epoch in every virtual sensor was visually evaluated, which is extremely time-consuming and may be impractical in clinical practice. Algorithms for the automatic detection of HFOs have been developed to address this issue and have been applied to both invasive and non-invasive recordings with varying success (Migliorelli et al., 2017; Navarrete et al., 2016; Quitadamo et al., 2018a; Shimamoto et al., 2018; van Klink et al., 2017). The novel aspect of the HFO detection algorithm applied in the present study is the use of a kurtosis-based metric to select a subset of channels that are most likely to be related to the SOZ, rather than relying on a priori knowledge of seizure onset location in the implanted electrodes.
Patient phenotypes and clinical outcomes in invasive monitoring for epilepsy: An individual patient data meta-analysis
2020, Epilepsy and BehaviorCitation Excerpt :A mixed-effects meta-analysis model was applied to the included studies to assess heterogeneity between studies (Fig. 2). This analysis includes 33 [19–51] studies reporting IPD on 595 patients (Table 1). Of these patients, 345 (58.0%) underwent SEEG and 250 (42.0%) underwent SDE.
Graph index complexity as a novel surrogate marker of high frequency oscillations in delineating the seizure onset zone
2020, Clinical NeurophysiologyCitation Excerpt :Many algorithms explicitly or implicitly incorporate multiple features using machine learning (Dumpelmann et al., 2012), pattern matching (Salami et al., 2012; von Ellenrieder et al., 2012; Zelmann et al., 2012; Chen-Wei et al., 2016), empirical mode decomposition (Huang et al., 2017), Gaussian mixture model clustering (Liu et al., 2016), Gabor atoms (Jrad et al., 2017), or independent component analysis (Shimamoto et al., 2018) to identify HFOs. Some even integrate data from multiple channels simultaneously (Chen-Wei et al., 2016; Fedele et al., 2016), incorporate topographic analysis (Shimamoto et al., 2018; Waldman et al., 2018), are subject to subsequent visual validation (Spring et al., 2017; Spring et al., 2018; Weiss et al., 2018), or include a rigorous artifact rejection step (Gliske et al., 2016; Jiang et al., 2018) to further refine the automated detection of HFOs. Rather than identifying discrete HFO events, algorithms may also be used to estimate the high frequency oscillatory activity within each channel, such as through employing non-linear metrics as surrogate markers for HFO activity.
Does data cleaning improve brain state classification?
2019, Journal of Neuroscience Methods