Autoreject: Automated artifact rejection for MEG and EEG data

Jas, Mainak; Engemann, Denis A.; Bekhti, Yousra; Raimondo, Federico; Gramfort, Alexandre

doi:10.1016/j.neuroimage.2017.06.030

Cited by 376 publications

(288 citation statements)

References 48 publications

Supporting

Mentioning

263

Contrasting

Unclassified

Order By: Relevance

“…This method learns principal components on data-segments contaminated by artifacts and then projects the signal into to the subspace orthogonal to the artifact. To reliably estimate the signal space dominated by the cardiac and ocular artifacts, we excluded data segments dominated by high-amplitude signals using the 'global' option from autoreject (Jas et al, 2017). To preserve the signal as much as possible, we only considered the first SSP vector based on the first principal component.…”

Section: Mne Model For Regression With Source Localizationmentioning

confidence: 99%

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Sabbagh

Ablin

Varoquaux

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Predicting biomedical outcomes from Magnetoencephalography and Electroencephalography (M/EEG) is central to applications like decoding, brain-computer-interfaces (BCI) or biomarker development and is facilitated by supervised machine learning. Yet most of the literature is concerned with within-subject classification. Here, we focus on predicting continuous outcomes from M/EEG signal power across subjects. Considering different generative mechanisms for M/EEG signals and the biomedical outcome, we propose statistically-consistent predictive models that avoid sourcereconstruction based on the covariance as representation. Our mathematical analysis and ground truth simulations demonstrated that consistent parameter estimation can be obtained with Source Power Comodulation (SPoC) supervised spatial filtering or by embedding with Riemannian geometry. Additional simulations revealed that Riemannian methods were more robust to model violations, in particular geometric distortions induced by individual anatomy. To estimate the relative contribution of brain dynamics and anatomy to prediction performance, we propose a novel model inspection procedure based on biophysical forward modeling. Applied to cross-subject prediction, the analysis revealed that the Riemannian model better exploited anatomical information while sensitivity to brain dynamics was similar across methods. We then probed the robustness of the models across different data cleaning options. Environmental denoising was globally important but Riemannian models were strikingly robust and continued performing even without preprocessing. Our results suggest each method has its niche: SPoC is practical for within-subject prediction while the Riemannian model may enable simple end-to-end learning.

show abstract

Section: Mne Model For Regression With Source Localizationmentioning

confidence: 99%

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Sabbagh

Ablin

Varoquaux

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…For artifact correction most pipelines have implemented an independent component analysis (ICA) (except Autoreject Jas et al 2017). The majority of these pipelines (including Automagic) use MARA (Winkler, Haufe, and Tangermann 2011;Winkler et al 2014) to automatically identify bad independent components.…”

Section: <Insert Table 1 Here>mentioning

confidence: 99%

Automagic: Standardized Preprocessing of Big EEG Data

Pedroni

Bahreini

Langer

2018

Preprint

View full text Add to dashboard Cite

Electroencephalography (EEG) recordings have been rarely included in large-scale studies. This is arguably not due to a lack of information that lies in EEG recordings but mainly on account of methodological issues. In many cases, particularly in clinical, pediatric and aging populations, the EEG has a high degree of artifact contamination and the quality of EEG recordings often substantially differs between subjects. Although there exists a variety of standardized preprocessing methods to clean EEG from artifacts, currently there is no method to objectively quantify the quality of preprocessed EEG.This makes the commonly accepted procedure of excluding subjects from analyses due to exceeding contamination of artifacts highly subjective. As a consequence, P-hacking is fostered, the replicability of results is decreased, and it is difficult to pool data from different study sites. In addition, in largescale studies, data are collected over years or even decades, requiring software that controls and manages the preprocessing of ongoing and dynamically growing studies. To address these challenges, we developed Automagic, an open-source MATLAB toolbox that acts as a wrapper to run currently available preprocessing methods and offers objective standardized quality assessment for growing studies. The software is compatible with the Brain Imaging Data Structure (BIDS) standard and hence facilitates data sharing. In the present paper we outline the functionality of Automagic and examine the effect of applying combinations of methods on a sample of resting EEG data. This examination suggests that applying a pipeline of algorithms to detect artifactual channels in combination with Multiple Artifact Rejection Algorithm (MARA), an independent component analysis (ICA)-based artifact correction method, is sufficient to reduce a large extent of artifacts.

show abstract

“…This method learns principal components on contaminated data-segments and then projects the signal into the sub-space that is not correlated with the artifact. To obtain clean estimates, we excluded bad data segments from the EOG/ECG channels using the 'global' option from autoreject (Jas et al, 2017). We then averaged the artefact-evoked signal (see 'average' option in mne.preprocessing.compute_proj_ecg) to enhance subspace estimation and only considered one single projection vector to preserve as much signal as possible.…”

Section: Physiological Artifactsmentioning

confidence: 99%

“…To avoid contamination with artifacts that were not removed by SSS or SSP, we used the 'global' option from autoreject (Jas et al, 2017). This yielded a data-driven selection of the amplitude range above which data segments were excluded from the analysis.…”

Section: Rejection Of Residual Artifactsmentioning

confidence: 99%

Combining electrophysiology with MRI enhances learning of surrogate-biomarkers

Engemann¹,

Kozynets²,

Sabbagh³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Electrophysiological methods, i.e., M/EEG provide unique views into brain health. Yet, when building predictive models from brain data, it is often unclear how electrophysiology should be combined with other neuroimaging methods. Information can be redundant, useful common representations of multimodal data may not be obvious and multimodal data collection can be medically contraindicated, which reduces applicability. Here, we propose a multimodal model to robustly combine MEG, MRI and fMRI for prediction. We focus on age prediction as surrogate biomarker in 674 subjects from the Cam-CAN. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by source-topography of power spectra between 8 and 30 Hz. Finally, we demonstrate that the model maintains benefits of stacking when data is missing. The proposed framework hence enables multimodal learning for a wide range of biomarkers from diverse types of brain signals.

show abstract

Autoreject: Automated artifact rejection for MEG and EEG data

Cited by 376 publications

References 48 publications

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Automagic: Standardized Preprocessing of Big EEG Data

Combining electrophysiology with MRI enhances learning of surrogate-biomarkers

Contact Info

Product

Resources

About