Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering

Yogatheesan Varatharajah, Brent M. Berry, Zbigniew T. Kalbarczyk, Benjamin Brinkmann, Gregory Alan Worrell, Ravishankar K. Iyer

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

2 Citations (Scopus)

Abstract

Surgical removal of seizure-generating brain tissue can cure epilepsy in patients who do not respond to medications. However, identifying seizure-generating regions is difficult and fails in many cases. In this paper, we report a fully unsupervised and automated approach to seizure focus localization using a Bayesian filter. This method uses a spectral domain feature, Power in Bands (PIB). PIB is extracted from inter-ictal (non-seizure) intracranial EEG recordings of patients with focal epilepsy to differentiate normal and abnormal brain regions. This study was carried out using data collected from 34 patients with focal epilepsy at the Mayo Clinic. Experiments show that using a Bayesian filter for capturing temporal properties of the iEEGs recorded from epileptic brains remarkably improves localization accuracy (AUC: 0.63 → 0.72). Our study also reaffirms that high-frequency oscillations and inter-ictal spikes are useful inter-ictal biomarkers of the epileptic brain, and PIB, which could be implemented with relatively low computational burden, performs as well as the standard bio-markers when used in this setting.We conclude that the technique of extracting spectral features from inter-ictal iEEGs and capturing their temporal properties via a Bayesian filter markedly improves our ability to localize seizure onset zones.

Original languageEnglish (US)
Title of host publication8th International IEEE EMBS Conference on Neural Engineering, NER 2017
PublisherIEEE Computer Society
Pages533-539
Number of pages7
ISBN (Electronic)9781538619162
DOIs
StatePublished - Aug 10 2017
Event8th International IEEE EMBS Conference on Neural Engineering, NER 2017 - Shanghai, China
Duration: May 25 2017May 28 2017

Other

Other8th International IEEE EMBS Conference on Neural Engineering, NER 2017
CountryChina
CityShanghai
Period5/25/175/28/17

Fingerprint

Brain
Biomarkers
Electroencephalography
Tissue
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Mechanical Engineering

Cite this

Varatharajah, Y., Berry, B. M., Kalbarczyk, Z. T., Brinkmann, B., Worrell, G. A., & Iyer, R. K. (2017). Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering. In 8th International IEEE EMBS Conference on Neural Engineering, NER 2017 (pp. 533-539). [8008407] IEEE Computer Society. https://doi.org/10.1109/NER.2017.8008407

Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering. / Varatharajah, Yogatheesan; Berry, Brent M.; Kalbarczyk, Zbigniew T.; Brinkmann, Benjamin; Worrell, Gregory Alan; Iyer, Ravishankar K.

8th International IEEE EMBS Conference on Neural Engineering, NER 2017. IEEE Computer Society, 2017. p. 533-539 8008407.

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

Varatharajah, Y, Berry, BM, Kalbarczyk, ZT, Brinkmann, B, Worrell, GA & Iyer, RK 2017, Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering. in 8th International IEEE EMBS Conference on Neural Engineering, NER 2017., 8008407, IEEE Computer Society, pp. 533-539, 8th International IEEE EMBS Conference on Neural Engineering, NER 2017, Shanghai, China, 5/25/17. https://doi.org/10.1109/NER.2017.8008407
Varatharajah Y, Berry BM, Kalbarczyk ZT, Brinkmann B, Worrell GA, Iyer RK. Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering. In 8th International IEEE EMBS Conference on Neural Engineering, NER 2017. IEEE Computer Society. 2017. p. 533-539. 8008407 https://doi.org/10.1109/NER.2017.8008407
Varatharajah, Yogatheesan ; Berry, Brent M. ; Kalbarczyk, Zbigniew T. ; Brinkmann, Benjamin ; Worrell, Gregory Alan ; Iyer, Ravishankar K. / Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering. 8th International IEEE EMBS Conference on Neural Engineering, NER 2017. IEEE Computer Society, 2017. pp. 533-539
@inproceedings{ec52e9fbc7f8447ebc6810c27d7126be,
title = "Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering",
abstract = "Surgical removal of seizure-generating brain tissue can cure epilepsy in patients who do not respond to medications. However, identifying seizure-generating regions is difficult and fails in many cases. In this paper, we report a fully unsupervised and automated approach to seizure focus localization using a Bayesian filter. This method uses a spectral domain feature, Power in Bands (PIB). PIB is extracted from inter-ictal (non-seizure) intracranial EEG recordings of patients with focal epilepsy to differentiate normal and abnormal brain regions. This study was carried out using data collected from 34 patients with focal epilepsy at the Mayo Clinic. Experiments show that using a Bayesian filter for capturing temporal properties of the iEEGs recorded from epileptic brains remarkably improves localization accuracy (AUC: 0.63 → 0.72). Our study also reaffirms that high-frequency oscillations and inter-ictal spikes are useful inter-ictal biomarkers of the epileptic brain, and PIB, which could be implemented with relatively low computational burden, performs as well as the standard bio-markers when used in this setting.We conclude that the technique of extracting spectral features from inter-ictal iEEGs and capturing their temporal properties via a Bayesian filter markedly improves our ability to localize seizure onset zones.",
author = "Yogatheesan Varatharajah and Berry, {Brent M.} and Kalbarczyk, {Zbigniew T.} and Benjamin Brinkmann and Worrell, {Gregory Alan} and Iyer, {Ravishankar K.}",
year = "2017",
month = "8",
day = "10",
doi = "10.1109/NER.2017.8008407",
language = "English (US)",
pages = "533--539",
booktitle = "8th International IEEE EMBS Conference on Neural Engineering, NER 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Inter-ictal Seizure Onset Zone localization using unsupervised clustering and Bayesian Filtering

AU - Varatharajah, Yogatheesan

AU - Berry, Brent M.

AU - Kalbarczyk, Zbigniew T.

AU - Brinkmann, Benjamin

AU - Worrell, Gregory Alan

AU - Iyer, Ravishankar K.

PY - 2017/8/10

Y1 - 2017/8/10

N2 - Surgical removal of seizure-generating brain tissue can cure epilepsy in patients who do not respond to medications. However, identifying seizure-generating regions is difficult and fails in many cases. In this paper, we report a fully unsupervised and automated approach to seizure focus localization using a Bayesian filter. This method uses a spectral domain feature, Power in Bands (PIB). PIB is extracted from inter-ictal (non-seizure) intracranial EEG recordings of patients with focal epilepsy to differentiate normal and abnormal brain regions. This study was carried out using data collected from 34 patients with focal epilepsy at the Mayo Clinic. Experiments show that using a Bayesian filter for capturing temporal properties of the iEEGs recorded from epileptic brains remarkably improves localization accuracy (AUC: 0.63 → 0.72). Our study also reaffirms that high-frequency oscillations and inter-ictal spikes are useful inter-ictal biomarkers of the epileptic brain, and PIB, which could be implemented with relatively low computational burden, performs as well as the standard bio-markers when used in this setting.We conclude that the technique of extracting spectral features from inter-ictal iEEGs and capturing their temporal properties via a Bayesian filter markedly improves our ability to localize seizure onset zones.

AB - Surgical removal of seizure-generating brain tissue can cure epilepsy in patients who do not respond to medications. However, identifying seizure-generating regions is difficult and fails in many cases. In this paper, we report a fully unsupervised and automated approach to seizure focus localization using a Bayesian filter. This method uses a spectral domain feature, Power in Bands (PIB). PIB is extracted from inter-ictal (non-seizure) intracranial EEG recordings of patients with focal epilepsy to differentiate normal and abnormal brain regions. This study was carried out using data collected from 34 patients with focal epilepsy at the Mayo Clinic. Experiments show that using a Bayesian filter for capturing temporal properties of the iEEGs recorded from epileptic brains remarkably improves localization accuracy (AUC: 0.63 → 0.72). Our study also reaffirms that high-frequency oscillations and inter-ictal spikes are useful inter-ictal biomarkers of the epileptic brain, and PIB, which could be implemented with relatively low computational burden, performs as well as the standard bio-markers when used in this setting.We conclude that the technique of extracting spectral features from inter-ictal iEEGs and capturing their temporal properties via a Bayesian filter markedly improves our ability to localize seizure onset zones.

UR - http://www.scopus.com/inward/record.url?scp=85028591892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028591892&partnerID=8YFLogxK

U2 - 10.1109/NER.2017.8008407

DO - 10.1109/NER.2017.8008407

M3 - Conference contribution

AN - SCOPUS:85028591892

SP - 533

EP - 539

BT - 8th International IEEE EMBS Conference on Neural Engineering, NER 2017

PB - IEEE Computer Society

ER -