Progress and remaining challenges in the application of high frequency oscillations as biomarkers of epileptic brain

Khadjevand, Fatemeh; Cimbálník, Jan; Worrell, Gregory A.

doi:10.1016/j.cobme.2017.09.006

Cited by 17 publications

(12 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the employed detectors suffer from high specificity and are not able to distinguish physiological HFOs, high-frequency artifacts, false oscillations due to the filtering of sharp transient from pathological HFOs that is a category consisting itself in different possible groups (e.g., ripples, fast ripples, and fast ripples during ripples). In general, thanks to the employment of machine learning, it is not necessary to assume that HFOs are rare events and to define manually a threshold, therefore the typical high number of false positive of traditional automatic detectors decreases [53]. Moreover, recently, it has been highlighted that it is necessary to further refine HFO identification, differentiating HFOs with respect to the baseline from HFOs occurring during spikes, and defining different thresholds for SOZ identification, varying according to brain regions [54].…”

Section: Discussionmentioning

confidence: 99%

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

Sciaraffa

Klados²,

Borghini

et al. 2020

Brain Sciences

View full text Add to dashboard Cite

The need for automatic detection and classification of high-frequency oscillations (HFOs) as biomarkers of the epileptogenic tissue is strongly felt in the clinical field. In this context, the employment of artificial intelligence methods could be the missing piece to achieve this goal. This work proposed a double-step procedure based on machine learning algorithms and tested it on an intracranial electroencephalogram (iEEG) dataset available online. The first step aimed to define the optimal length for signal segmentation, allowing for an optimal discrimination of segments with HFO relative to those without. In this case, binary classifiers have been tested on a set of energy features. The second step aimed to classify these segments into ripples, fast ripples and fast ripples occurring during ripples. Results suggest that LDA applied to 10 ms segmentation could provide the highest sensitivity (0.874) and 0.776 specificity for the discrimination of HFOs from no-HFO segments. Regarding the three-class classification, non-linear methods provided the highest values (around 90%) in terms of specificity and sensitivity, significantly different to the other three employed algorithms. Therefore, this machine-learning-based procedure could help clinicians to automatically reduce the quantity of irrelevant data.

show abstract

Section: Discussionmentioning

confidence: 99%

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

Sciaraffa

Klados²,

Borghini

et al. 2020

Brain Sciences

View full text Add to dashboard Cite

show abstract

“…The gold standard is visual identification, 7,14,15 but automated detectors are increasingly being implemented to save time and improve reliability and reproducibility 16,17 . Automatic detection algorithms generally follow a standard procedure: They identify a period of increased high‐frequency energy (measured with root‐mean‐square (RMS) amplitude, 15,18,19 amplitude of rectified filtered data, 20,21 line length, 22,23 Hilbert envelope, 3,24 or as a peak in the time‐frequency decomposition 25 ), then verify that the event exceeds a minimum duration or a minimum number of oscillations. Many algorithms include additional steps to merge consecutive events if they occur in close temporal proximity 3,18,26 and reject false positives 3,27,28 .…”

Section: Introductionmentioning

confidence: 99%

“…First, visual and automated detection rely on the empirical definition of an HFO derived from visual observation 12 . There is currently no physiological definition that can guide the selection of detection parameters such as amplitude, duration, and number of cycles, as studies have shown significant overlap between pathological and physiological HFOs 23,25,30‐32 . However, the optimization of such parameters is critical to the accuracy of the detector 15,20,21 .…”

Section: Introductionmentioning

confidence: 99%

Detection of anomalous high‐frequency events in human intracranial EEG

et al. 2020

View full text Add to dashboard Cite

This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made. AbstractObjective: High-frequency oscillations (HFOs) are a promising biomarker for the epileptogenic zone. However, no physiological definition of an HFO has been established, so detection relies on the empirical definition of an HFO derived from visual observation. This can bias estimates of HFO features such as amplitude and duration, thereby hindering their utility as biomarkers. Therefore, we set out to develop an algorithm that detects high-frequency events in the intracranial EEG that are morphologically distinct from background without requiring assumptions about event amplitude or shape. Method: We propose the anomaly detection algorithm (ADA), which uses unsupervised machine learning to identify segments of data that are distinct from the background. We apply ADA and a standard HFO detector using a root mean square amplitude threshold to intracranial EEG from 11 patients undergoing evaluation for epilepsy surgery. The rate, amplitude, and duration of the detected events and the percent overlap between the two detectors are compared. Result: In the seizure onset zone (SOZ), ADA detected a subset of conventional HFOs. In non-SOZ channels, ADA detected at least twice as many events as the standard approach, including some conventional HFOs; however, ADA also identified many low and intermediate amplitude events missed by the standard amplitudebased method. The rate of ADA events was similar across all channels; however, the amplitude of ADA events was significantly higher in SOZ channels (P < .0045), and the amplitude measurement was more stable over time than the HFO rate, as indicated by a lower coefficient of variation (P < .0125). Significance: ADA does not require human supervision, parameter optimization, or prior assumptions about event shape, amplitude, or duration. Our results suggest that the algorithm's estimate of event amplitude may differentiate SOZ and non-SOZ channels. Further studies will examine the utility of HFO amplitude as a biomarker for epilepsy surgical outcome. |

show abstract

“…The gold standard for detection is visual identification, 8,[16][17][18] but automated detectors are increasingly being implemented to save time and improve reliability and reproducibility. 19,20 Automatic detection algorithms generally consist of the same basic steps: they identify a period of increased high frequency energy (measured with root-mean-square (RMS) amplitude, 17,21,22 amplitude of rectified filtered data, 23,24 line length, 25,26 Hilbert envelope, 3,4,27 or as a peak in the time-frequency decomposition 28 ), then verify that the event exceeds a minimum duration or a minimum number of oscillations. Many detection algorithms include additional steps to merge consecutive events and reject false positives.…”

Section: Introductionmentioning

confidence: 99%

“…14 There is currently no clear physiological definition that can be used to guide the selection of detection parameters such as amplitude, duration, and number of cycles, as studies have shown significant overlap between pathological and physiological HFOs. 26,[28][29][30][31] However, the optimization of such parameters is critical to the accuracy of the detector. 17,23,24 This is directly related to the second challenge: existing detection methods require complex optimization procedures.…”

Section: Introductionmentioning

confidence: 99%

Detection of anomalous high frequency events in human intracranial EEG

Charupanit¹,

Sen‐Gupta²,

Lin³

et al. 2019

Preprint

View full text Add to dashboard Cite

SummaryObjectiveHigh-frequency oscillations (HFOs) are a promising biomarker for the epileptogenic zone. However, no physiological definition of an HFO has been established, so detection relies on the empirical definition of an HFO derived from visual observation. This can bias estimates of HFO features such as amplitude and duration, thereby hindering their utility as biomarkers. Therefore, we set out to develop an algorithm that detects high frequency events in the intracranial EEG that stand out from the background and does not require assumptions about event amplitude or morphology.MethodWe propose the anomaly detection algorithm (ADA), which integrates several unsupervised machine learning techniques to identify segments of data that are distinct from the background. We apply ADA and a standard HFO detector using a root-mean-square amplitude threshold to intracranial EEG from 11 patients undergoing evaluation for epilepsy surgery. The rate, amplitude, and duration of the detected events and the percent overlap between the two detectors are compared.ResultIn the seizure onset zone (SOZ), ADA detected a subset of conventional HFOs. In non-SOZ channels, ADA detected at least twice as many events as the standard approach, including some conventional HFOs; however, ADA also identified many low and intermediate amplitude events missed by the standard amplitude-based method. The rate of ADA events was similar across all channels; however, the amplitude of ADA events was significantly higher in SOZ channels, and the threshold between SOZ and non-SOZ channels was relatively consistent across patients.SignificanceADA does not require human supervision, parameter optimization, or prior assumptions about event shape, amplitude, or duration. It provides an unbiased estimate of HFO features, and our results suggest that amplitude may differentiate SOZ and non-SOZ channels. Further studies will examine the utility of HFO amplitude as a biomarker for epilepsy surgical outcome.

show abstract

Progress and remaining challenges in the application of high frequency oscillations as biomarkers of epileptic brain

Cited by 17 publications

References 87 publications

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

Detection of anomalous high‐frequency events in human intracranial EEG

Detection of anomalous high frequency events in human intracranial EEG

Contact Info

Product

Resources

About