ARTIST: A fully automated artifact rejection algorithm for single-pulse TMS-EEG data

Wei Wu, Corey J. Keller, Nigel Rogasch, Parker Longwell, Emmanuel Shpigel, Camarin E. Rolle, Amit Etkin

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Concurrent single-pulse TMS-EEG (spTMS-EEG) is an emerging noninvasive tool for probing causal brain dynamics in humans. However, in addition to the common artifacts in standard EEG data, spTMS-EEG data suffer from enormous stimulation-induced artifacts, posing significant challenges to the extraction of neural information. Typically, neural signals are analyzed after a manual time-intensive and often subjective process of artifact rejection. Here we describe a fully automated algorithm for spTMS-EEG artifact rejection. A key step of this algorithm is to decompose the spTMS-EEG data into statistically independent components (ICs), and then train a pattern classifier to automatically identify artifact components based on knowledge of the spatio-temporal profile of both neural and artefactual activities. The autocleaned and hand-cleaned data yield qualitatively similar group evoked potential waveforms. The algorithm achieves a 95% IC classification accuracy referenced to expert artifact rejection performance, and does so across a large number of spTMS-EEG data sets (n = 90 stimulation sites), retains high accuracy across stimulation sites/subjects/populations/montages, and outperforms current automated algorithms. Moreover, the algorithm was superior to the artifact rejection performance of relatively novice individuals, who would be the likely users of spTMS-EEG as the technique becomes more broadly disseminated. In summary, our algorithm provides an automated, fast, objective, and accurate method for cleaning spTMS-EEG data, which can increase the utility of TMS-EEG in both clinical and basic neuroscience settings.

LanguageEnglish
Pages1607-1625
Number of pages19
JournalHuman Brain Mapping
Volume39
Issue number4
DOIs
Publication statusPublished - 1 Apr 2018
Externally publishedYes

Keywords

  • artifact rejection
  • electroencephalogram
  • transcranial magnetic stimulation

ASJC Scopus subject areas

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

Wu, W., Keller, C. J., Rogasch, N., Longwell, P., Shpigel, E., Rolle, C. E., & Etkin, A. (2018). ARTIST: A fully automated artifact rejection algorithm for single-pulse TMS-EEG data. Human Brain Mapping, 39(4), 1607-1625. https://doi.org/10.1002/hbm.23938
Wu, Wei ; Keller, Corey J. ; Rogasch, Nigel ; Longwell, Parker ; Shpigel, Emmanuel ; Rolle, Camarin E. ; Etkin, Amit. / ARTIST : A fully automated artifact rejection algorithm for single-pulse TMS-EEG data. In: Human Brain Mapping. 2018 ; Vol. 39, No. 4. pp. 1607-1625.
@article{f65990318a21479bbdafadd9f94094d0,
title = "ARTIST: A fully automated artifact rejection algorithm for single-pulse TMS-EEG data",
abstract = "Concurrent single-pulse TMS-EEG (spTMS-EEG) is an emerging noninvasive tool for probing causal brain dynamics in humans. However, in addition to the common artifacts in standard EEG data, spTMS-EEG data suffer from enormous stimulation-induced artifacts, posing significant challenges to the extraction of neural information. Typically, neural signals are analyzed after a manual time-intensive and often subjective process of artifact rejection. Here we describe a fully automated algorithm for spTMS-EEG artifact rejection. A key step of this algorithm is to decompose the spTMS-EEG data into statistically independent components (ICs), and then train a pattern classifier to automatically identify artifact components based on knowledge of the spatio-temporal profile of both neural and artefactual activities. The autocleaned and hand-cleaned data yield qualitatively similar group evoked potential waveforms. The algorithm achieves a 95{\%} IC classification accuracy referenced to expert artifact rejection performance, and does so across a large number of spTMS-EEG data sets (n = 90 stimulation sites), retains high accuracy across stimulation sites/subjects/populations/montages, and outperforms current automated algorithms. Moreover, the algorithm was superior to the artifact rejection performance of relatively novice individuals, who would be the likely users of spTMS-EEG as the technique becomes more broadly disseminated. In summary, our algorithm provides an automated, fast, objective, and accurate method for cleaning spTMS-EEG data, which can increase the utility of TMS-EEG in both clinical and basic neuroscience settings.",
keywords = "artifact rejection, electroencephalogram, transcranial magnetic stimulation",
author = "Wei Wu and Keller, {Corey J.} and Nigel Rogasch and Parker Longwell and Emmanuel Shpigel and Rolle, {Camarin E.} and Amit Etkin",
year = "2018",
month = "4",
day = "1",
doi = "10.1002/hbm.23938",
language = "English",
volume = "39",
pages = "1607--1625",
journal = "Human Brain Mapping",
issn = "1065-9471",
number = "4",

}

Wu, W, Keller, CJ, Rogasch, N, Longwell, P, Shpigel, E, Rolle, CE & Etkin, A 2018, 'ARTIST: A fully automated artifact rejection algorithm for single-pulse TMS-EEG data', Human Brain Mapping, vol. 39, no. 4, pp. 1607-1625. https://doi.org/10.1002/hbm.23938

ARTIST : A fully automated artifact rejection algorithm for single-pulse TMS-EEG data. / Wu, Wei; Keller, Corey J.; Rogasch, Nigel; Longwell, Parker; Shpigel, Emmanuel; Rolle, Camarin E.; Etkin, Amit.

In: Human Brain Mapping, Vol. 39, No. 4, 01.04.2018, p. 1607-1625.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ARTIST

T2 - Human Brain Mapping

AU - Wu, Wei

AU - Keller, Corey J.

AU - Rogasch, Nigel

AU - Longwell, Parker

AU - Shpigel, Emmanuel

AU - Rolle, Camarin E.

AU - Etkin, Amit

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Concurrent single-pulse TMS-EEG (spTMS-EEG) is an emerging noninvasive tool for probing causal brain dynamics in humans. However, in addition to the common artifacts in standard EEG data, spTMS-EEG data suffer from enormous stimulation-induced artifacts, posing significant challenges to the extraction of neural information. Typically, neural signals are analyzed after a manual time-intensive and often subjective process of artifact rejection. Here we describe a fully automated algorithm for spTMS-EEG artifact rejection. A key step of this algorithm is to decompose the spTMS-EEG data into statistically independent components (ICs), and then train a pattern classifier to automatically identify artifact components based on knowledge of the spatio-temporal profile of both neural and artefactual activities. The autocleaned and hand-cleaned data yield qualitatively similar group evoked potential waveforms. The algorithm achieves a 95% IC classification accuracy referenced to expert artifact rejection performance, and does so across a large number of spTMS-EEG data sets (n = 90 stimulation sites), retains high accuracy across stimulation sites/subjects/populations/montages, and outperforms current automated algorithms. Moreover, the algorithm was superior to the artifact rejection performance of relatively novice individuals, who would be the likely users of spTMS-EEG as the technique becomes more broadly disseminated. In summary, our algorithm provides an automated, fast, objective, and accurate method for cleaning spTMS-EEG data, which can increase the utility of TMS-EEG in both clinical and basic neuroscience settings.

AB - Concurrent single-pulse TMS-EEG (spTMS-EEG) is an emerging noninvasive tool for probing causal brain dynamics in humans. However, in addition to the common artifacts in standard EEG data, spTMS-EEG data suffer from enormous stimulation-induced artifacts, posing significant challenges to the extraction of neural information. Typically, neural signals are analyzed after a manual time-intensive and often subjective process of artifact rejection. Here we describe a fully automated algorithm for spTMS-EEG artifact rejection. A key step of this algorithm is to decompose the spTMS-EEG data into statistically independent components (ICs), and then train a pattern classifier to automatically identify artifact components based on knowledge of the spatio-temporal profile of both neural and artefactual activities. The autocleaned and hand-cleaned data yield qualitatively similar group evoked potential waveforms. The algorithm achieves a 95% IC classification accuracy referenced to expert artifact rejection performance, and does so across a large number of spTMS-EEG data sets (n = 90 stimulation sites), retains high accuracy across stimulation sites/subjects/populations/montages, and outperforms current automated algorithms. Moreover, the algorithm was superior to the artifact rejection performance of relatively novice individuals, who would be the likely users of spTMS-EEG as the technique becomes more broadly disseminated. In summary, our algorithm provides an automated, fast, objective, and accurate method for cleaning spTMS-EEG data, which can increase the utility of TMS-EEG in both clinical and basic neuroscience settings.

KW - artifact rejection

KW - electroencephalogram

KW - transcranial magnetic stimulation

UR - http://www.scopus.com/inward/record.url?scp=85040613356&partnerID=8YFLogxK

U2 - 10.1002/hbm.23938

DO - 10.1002/hbm.23938

M3 - Article

VL - 39

SP - 1607

EP - 1625

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 4

ER -