Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome

Tommaso Fedele; Maryse van 't Klooster; Sergey Burnos; Willemiek Zweiphenning; Nicole van Klink; Frans Leijten; Maeike Zijlmans; Johannes Sarnthein

doi:10.1016/j.clinph.2016.06.009

Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome

Tommaso Fedele, Maryse van 't Klooster, Sergey Burnos, Willemiek Zweiphenning, Nicole van Klink, Frans Leijten, Maeike Zijlmans, Johannes Sarnthein

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

OBJECTIVE: High frequency oscillations (HFOs) and in particular fast ripples (FRs) in the post-resection electrocorticogram (ECoG) have recently been shown to be highly specific predictors of outcome of epilepsy surgery. FR visual marking is time consuming and prone to observer bias. We validate here a fully automatic HFO detector against seizure outcome.

METHODS: Pre-resection ECoG dataset (N=14 patients) with visually marked HFOs were used to optimize the detector's parameters in the time-frequency domain. The optimized detector was then applied on a larger post-resection ECoG dataset (N=54) and the output was compared with visual markings and seizure outcome. The analysis was conducted separately for ripples (80-250Hz) and FRs (250-500Hz).

RESULTS: Channel-wise comparison showed a high association between automatic detection and visual marking (p<0.001 for both FRs and ripples). Automatically detected FRs were predictive of clinical outcome with positive predictive value PPV=100% and negative predictive value NPV=62%, while for ripples PPV=43% and NPV=100%.

CONCLUSIONS: Our automatic and fully unsupervised detection of HFO events matched the expert observer's performance in both event selection and outcome prediction.

SIGNIFICANCE: The detector provides a standardized definition of clinically relevant HFOs, which may spread its use in clinical application.

Original language	English
Pages (from-to)	3066-3074
Number of pages	9
Journal	Clinical Neurophysiology
Volume	127
Issue number	9
DOIs	https://doi.org/10.1016/j.clinph.2016.06.009
Publication status	Published - 18 Jun 2016

Keywords

Epilepsy surgery
Intraoperative ECoG
High frequency oscillations
Fast ripples
Automatic detection
Seizure outcome

Access to Document

10.1016/j.clinph.2016.06.009

Cite this

@article{c465399cb8aa4c7e998326b26f2e8ab7,

title = "Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome",

abstract = "OBJECTIVE: High frequency oscillations (HFOs) and in particular fast ripples (FRs) in the post-resection electrocorticogram (ECoG) have recently been shown to be highly specific predictors of outcome of epilepsy surgery. FR visual marking is time consuming and prone to observer bias. We validate here a fully automatic HFO detector against seizure outcome.METHODS: Pre-resection ECoG dataset (N=14 patients) with visually marked HFOs were used to optimize the detector's parameters in the time-frequency domain. The optimized detector was then applied on a larger post-resection ECoG dataset (N=54) and the output was compared with visual markings and seizure outcome. The analysis was conducted separately for ripples (80-250Hz) and FRs (250-500Hz).RESULTS: Channel-wise comparison showed a high association between automatic detection and visual marking (p<0.001 for both FRs and ripples). Automatically detected FRs were predictive of clinical outcome with positive predictive value PPV=100% and negative predictive value NPV=62%, while for ripples PPV=43% and NPV=100%.CONCLUSIONS: Our automatic and fully unsupervised detection of HFO events matched the expert observer's performance in both event selection and outcome prediction.SIGNIFICANCE: The detector provides a standardized definition of clinically relevant HFOs, which may spread its use in clinical application.",

keywords = "Epilepsy surgery, Intraoperative ECoG, High frequency oscillations, Fast ripples, Automatic detection, Seizure outcome",

author = "Tommaso Fedele and {van 't Klooster}, Maryse and Sergey Burnos and Willemiek Zweiphenning and {van Klink}, Nicole and Frans Leijten and Maeike Zijlmans and Johannes Sarnthein",

year = "2016",

month = jun,

day = "18",

doi = "10.1016/j.clinph.2016.06.009",

language = "English",

volume = "127",

pages = "3066--3074",

journal = "Clinical Neurophysiology",

issn = "1388-2457",

publisher = "Elsevier Ireland Ltd",

number = "9",

}

TY - JOUR

T1 - Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome

AU - Fedele, Tommaso

AU - van 't Klooster, Maryse

AU - Burnos, Sergey

AU - Zweiphenning, Willemiek

AU - van Klink, Nicole

AU - Leijten, Frans

AU - Zijlmans, Maeike

AU - Sarnthein, Johannes

PY - 2016/6/18

Y1 - 2016/6/18

N2 - OBJECTIVE: High frequency oscillations (HFOs) and in particular fast ripples (FRs) in the post-resection electrocorticogram (ECoG) have recently been shown to be highly specific predictors of outcome of epilepsy surgery. FR visual marking is time consuming and prone to observer bias. We validate here a fully automatic HFO detector against seizure outcome.METHODS: Pre-resection ECoG dataset (N=14 patients) with visually marked HFOs were used to optimize the detector's parameters in the time-frequency domain. The optimized detector was then applied on a larger post-resection ECoG dataset (N=54) and the output was compared with visual markings and seizure outcome. The analysis was conducted separately for ripples (80-250Hz) and FRs (250-500Hz).RESULTS: Channel-wise comparison showed a high association between automatic detection and visual marking (p<0.001 for both FRs and ripples). Automatically detected FRs were predictive of clinical outcome with positive predictive value PPV=100% and negative predictive value NPV=62%, while for ripples PPV=43% and NPV=100%.CONCLUSIONS: Our automatic and fully unsupervised detection of HFO events matched the expert observer's performance in both event selection and outcome prediction.SIGNIFICANCE: The detector provides a standardized definition of clinically relevant HFOs, which may spread its use in clinical application.

AB - OBJECTIVE: High frequency oscillations (HFOs) and in particular fast ripples (FRs) in the post-resection electrocorticogram (ECoG) have recently been shown to be highly specific predictors of outcome of epilepsy surgery. FR visual marking is time consuming and prone to observer bias. We validate here a fully automatic HFO detector against seizure outcome.METHODS: Pre-resection ECoG dataset (N=14 patients) with visually marked HFOs were used to optimize the detector's parameters in the time-frequency domain. The optimized detector was then applied on a larger post-resection ECoG dataset (N=54) and the output was compared with visual markings and seizure outcome. The analysis was conducted separately for ripples (80-250Hz) and FRs (250-500Hz).RESULTS: Channel-wise comparison showed a high association between automatic detection and visual marking (p<0.001 for both FRs and ripples). Automatically detected FRs were predictive of clinical outcome with positive predictive value PPV=100% and negative predictive value NPV=62%, while for ripples PPV=43% and NPV=100%.CONCLUSIONS: Our automatic and fully unsupervised detection of HFO events matched the expert observer's performance in both event selection and outcome prediction.SIGNIFICANCE: The detector provides a standardized definition of clinically relevant HFOs, which may spread its use in clinical application.

KW - Epilepsy surgery

KW - Intraoperative ECoG

KW - High frequency oscillations

KW - Fast ripples

KW - Automatic detection

KW - Seizure outcome

U2 - 10.1016/j.clinph.2016.06.009

DO - 10.1016/j.clinph.2016.06.009

M3 - Article

C2 - 27472542

SN - 1388-2457

VL - 127

SP - 3066

EP - 3074

JO - Clinical Neurophysiology

JF - Clinical Neurophysiology

IS - 9

ER -

Automatic detection of high frequency oscillations during epilepsy surgery predicts seizure outcome

Abstract

Keywords

Access to Document

Fingerprint

Cite this