Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy

O. L. Smart, Gregory Alan Worrell, G. J. Vachtsevanos, B. Litt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

High frequency epileptiform oscillations (HFEOs) have been observed before neocortical seizures on intracranial EEG recordings. There is suggestion that HFEOs may localize epileptic brain regions important to seizure generation in humans, a finding that would be valuable for understanding, diagnosing, and treating epilepsy. In this paper, an automated approach for detecting HFEOs is described. Fuzzy clustering and histograms are used to characterize HFEO events. Compared to neurologist markings, the algorithm detected 87 % of the HFEOs while achieving 68% precision and 90% specificity, without training. Applied to thirty-five minute seizure records obtained from six patients, spatial and temporal localization of HFEOs were observed in 77% and 61% of the segments respectively. Results highlight the potential of the method to identify brain regions vital to seizure generation by tracking the spatio-temporal evolution of high frequency seizure precursors in the epileptic network.

Original languageEnglish (US)
Title of host publication2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop
Pages53-58
Number of pages6
Volume2005
StatePublished - 2005
Event2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop - Boulder, CO, United States
Duration: Apr 7 2005Apr 8 2005

Other

Other2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop
CountryUnited States
CityBoulder, CO
Period4/7/054/8/05

Fingerprint

Electroencephalography
Brain
Fuzzy clustering

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Smart, O. L., Worrell, G. A., Vachtsevanos, G. J., & Litt, B. (2005). Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy. In 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop (Vol. 2005, pp. 53-58). [1614347]

Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy. / Smart, O. L.; Worrell, Gregory Alan; Vachtsevanos, G. J.; Litt, B.

2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop. Vol. 2005 2005. p. 53-58 1614347.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Smart, OL, Worrell, GA, Vachtsevanos, GJ & Litt, B 2005, Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy. in 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop. vol. 2005, 1614347, pp. 53-58, 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop, Boulder, CO, United States, 4/7/05.
Smart OL, Worrell GA, Vachtsevanos GJ, Litt B. Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy. In 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop. Vol. 2005. 2005. p. 53-58. 1614347
Smart, O. L. ; Worrell, Gregory Alan ; Vachtsevanos, G. J. ; Litt, B. / Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy. 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop. Vol. 2005 2005. pp. 53-58
@inproceedings{a3b78ababac54a3fb7319197c0ba4f60,
title = "Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy",
abstract = "High frequency epileptiform oscillations (HFEOs) have been observed before neocortical seizures on intracranial EEG recordings. There is suggestion that HFEOs may localize epileptic brain regions important to seizure generation in humans, a finding that would be valuable for understanding, diagnosing, and treating epilepsy. In this paper, an automated approach for detecting HFEOs is described. Fuzzy clustering and histograms are used to characterize HFEO events. Compared to neurologist markings, the algorithm detected 87 {\%} of the HFEOs while achieving 68{\%} precision and 90{\%} specificity, without training. Applied to thirty-five minute seizure records obtained from six patients, spatial and temporal localization of HFEOs were observed in 77{\%} and 61{\%} of the segments respectively. Results highlight the potential of the method to identify brain regions vital to seizure generation by tracking the spatio-temporal evolution of high frequency seizure precursors in the epileptic network.",
author = "Smart, {O. L.} and Worrell, {Gregory Alan} and Vachtsevanos, {G. J.} and B. Litt",
year = "2005",
language = "English (US)",
isbn = "0780388984",
volume = "2005",
pages = "53--58",
booktitle = "2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop",

}

TY - GEN

T1 - Automatic detection of high frequency epileptiform oscillations from intracranial EEG recordings of patients with neocortical epilepsy

AU - Smart, O. L.

AU - Worrell, Gregory Alan

AU - Vachtsevanos, G. J.

AU - Litt, B.

PY - 2005

Y1 - 2005

N2 - High frequency epileptiform oscillations (HFEOs) have been observed before neocortical seizures on intracranial EEG recordings. There is suggestion that HFEOs may localize epileptic brain regions important to seizure generation in humans, a finding that would be valuable for understanding, diagnosing, and treating epilepsy. In this paper, an automated approach for detecting HFEOs is described. Fuzzy clustering and histograms are used to characterize HFEO events. Compared to neurologist markings, the algorithm detected 87 % of the HFEOs while achieving 68% precision and 90% specificity, without training. Applied to thirty-five minute seizure records obtained from six patients, spatial and temporal localization of HFEOs were observed in 77% and 61% of the segments respectively. Results highlight the potential of the method to identify brain regions vital to seizure generation by tracking the spatio-temporal evolution of high frequency seizure precursors in the epileptic network.

AB - High frequency epileptiform oscillations (HFEOs) have been observed before neocortical seizures on intracranial EEG recordings. There is suggestion that HFEOs may localize epileptic brain regions important to seizure generation in humans, a finding that would be valuable for understanding, diagnosing, and treating epilepsy. In this paper, an automated approach for detecting HFEOs is described. Fuzzy clustering and histograms are used to characterize HFEO events. Compared to neurologist markings, the algorithm detected 87 % of the HFEOs while achieving 68% precision and 90% specificity, without training. Applied to thirty-five minute seizure records obtained from six patients, spatial and temporal localization of HFEOs were observed in 77% and 61% of the segments respectively. Results highlight the potential of the method to identify brain regions vital to seizure generation by tracking the spatio-temporal evolution of high frequency seizure precursors in the epileptic network.

UR - http://www.scopus.com/inward/record.url?scp=33847761078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847761078&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33847761078

SN - 0780388984

SN - 9780780388987

VL - 2005

SP - 53

EP - 58

BT - 2005 IEEE Region 5 and IEEE Denver Section Technical, Professional and Student Development Workshop

ER -