Evaluation of Artifact Subspace Reconstruction for Automatic EEG Artifact Removal

Chang, Che-Wei; Hsu, Sheng-Hsiou; Pion-Tonachini, Luca; Jung, Tzyy-Ping

doi:10.1109/embc.2018.8512547

Cited by 262 publications

(203 citation statements)

References 12 publications

Supporting

Mentioning

198

Contrasting

Order By: Relevance

“…This result indicates that, at a cutoff of 5, ASR cleaning is overly aggressive to the point of significantly modifying the data in the absence of artifacts. These findings are in agreement with what was recently reported by Chang et al (2018). In that paper, the ASR cleaned authors determined that the optimal cutoff parameter of ASR may be between 10 and 100.…”

Section: Data Cleaning Performance: Benchmark Against Asrsupporting

confidence: 93%

“…We ran both algorithms for each subject in the test set and collected the following quantities on subsequent blocks of 40 msec: 1) the correlation between raw and cleaned data (computed as the correlation between the correspondent data blocks vectorized across channels and time points) and 2) the maximum RMS artifact power yielded by RSBL. ASR's performance depends on multiple parameters, but it has been shown that the most critical one is the cutoff (Chang et al, 2018). In this experiment we used a cutoff equal to 5, which was the default value of EEGLAB's ASR plugin at the time of preparing this publication.…”

Section: Data Cleaning Performance: Benchmark Against Asrmentioning

confidence: 99%

See 1 more Smart Citation

A Bayesian framework for unifying data cleaning, source separation and imaging of electroencephalographic signals

Ojeda

Klug

Kreutz-Delgado

et al. 2019

Preprint

View full text Add to dashboard Cite

Electroencephalographic (EEG) source imaging depends upon sophisticated signal processing algorithms to deal with the problems of data cleaning, source separation, and localization. Typically, these problems are sequentially addressed by independent heuristics, limiting the use of EEG images on a variety of applications. Here, we propose a unifying empirical Bayes framework in which these dissimilar problems can be solved using a single algorithm. We use spatial sparsity constraints to adaptively segregate brain sources into maximally independent components with known anatomical support, while minimally overlapping artifactual activity. The framework yields a recursive inverse spatiotemporal filter that can be used for offline and online applications. We call this filter Recursive Sparse Bayesian Learning (RSBL). Of theoretical relevance, we demonstrate the connections between Infomax Independent Component Analysis and RSBL. We use simulations to show that RSBL can separate and localize cortical and artifact components that overlap in space and time from noisy data. On real data, we use RSBL to analyze single-trial error-related potentials, finding sources in the cingulate gyrus. We further benchmark our algorithm on two unrelated EEG studies showing that: 1) it outperforms Infomax for source separation on short time-scales and 2), unlike the popular Artifact Subspace Removal algorithm, it can reduce artifacts without significantly distorting clean epochs. Finally, we analyze mobile brain/body imaging data to characterize the brain dynamics supporting heading computation during full-body rotations, replicating the main findings of previous experimental literature.

show abstract

Section: Data Cleaning Performance: Benchmark Against Asrsupporting

confidence: 93%

Section: Data Cleaning Performance: Benchmark Against Asrmentioning

confidence: 99%

A Bayesian framework for unifying data cleaning, source separation and imaging of electroencephalographic signals

Ojeda

Klug

Kreutz-Delgado

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In this paper, we varied the sensitivity of all correction algorithms by evaluating different hyper-parameter configurations. ASR was evaluated for the cut-off parameter k = {20, 40, 80} according to the recommendations in [15], and the default window size (0.5 s). Based on [13,14], RPCA was evaluated for the regularization parameter λ 0 = {1.0, 1.5, 2.0}.…”

Section: A High-variance Electrode Artifact Removal (Hear)mentioning

confidence: 99%

HEAR to remove pops and drifts: the high-variance electrode artifact removal (HEAR) algorithm

Kobler

Sburlea

Mondini

et al. 2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

A high fraction of artifact-free signals is highly desirable in functional neuroimaging and brain-computer interfacing (BCI). We present the high-variance electrode artifact removal (HEAR) algorithm to remove transient electrode pop and drift (PD) artifacts from electroencephalographic (EEG) signals. Transient PD artifacts reflect impedance variations at the electrode scalp interface that are caused by ion concentration changes. HEAR and its online version (oHEAR) are opensource and publicly available. Both outperformed state of the art offline and online transient, high-variance artifact correction algorithms for simulated EEG signals. (o)HEAR attenuated PD artifacts by approx. 25 dB, and at the same time maintained a high SNR during PD artifact-free periods. For real-world EEG data, (o)HEAR reduced the fraction of outlier trials by half and maintained the waveform of a movement related cortical potential during a center-out reaching task. In the case of BCI training, using oHEAR can improve the reliability of the feedback a user receives through reducing a potential negative impact of PD artifacts.

show abstract

“…Continuous data were then visually inspected, and any sections including excessive electromyogram or other non-stereotyped artifacts were removed. Artifact subspace reconstruction (ASR), a data cleaning method that uses sliding window principal component analysis, was then used to remove high amplitude artifacts relative to artifact-free reference data [44]. ASR is especially useful for retaining maximum data in infants (where the length of EEG recordings is limited), as it allows artifacts to be removed while retaining the co-occurring EEG data that represents neural activity.…”

Section: Eeg Processingmentioning

confidence: 99%

“…ASR is especially useful for retaining maximum data in infants (where the length of EEG recordings is limited), as it allows artifacts to be removed while retaining the co-occurring EEG data that represents neural activity. The eeglab function clean_RawData was used to implement ASR, with default parameters and rejection threshold k=8 [44].…”

Section: Eeg Processingmentioning

confidence: 99%

Functional connectivity differences in early infancy precede autism symptoms: a multivariate pattern analysis

Dickinson

Daniel

Marin

et al. 2019

Preprint

View full text Add to dashboard Cite

Functional brain connectivity is altered in children and adults with autism spectrum disorder (ASD). Mapping pre-symptomatic functional disruptions in ASD could identify infants based on neural risk, providing a crucial opportunity to mediate outcomes before behavioral symptoms emerge.Here we quantify functional connectivity using scalable EEG measures of oscillatory phase coherence (6-12Hz). Infants at high and low familial risk for ASD (N=65) underwent an EEG recording at 3 months of age and were assessed for ASD symptoms at 18 months using the Autism Diagnostic Observation Schedule-Toddler Module. Multivariate pattern analysis was used to examine early functional patterns that are associated with later ASD symptoms. Support vector regression (SVR) algorithms accurately predicted observed ASD symptoms at 18 months from EEG data at 3 months (r=0.76, p=0.02). Specifically, lower frontal connectivity and higher right temporo-parietal connectivity predicted higher ASD symptoms.The SVR model did not predict non-verbal cognitive abilities at 18 months (r=0.15, p=0.36), suggesting specificity of these brain alterations to ASD.These data suggest that frontal and temporo-parietal dysconnectivity play important roles in the early pathophysiology of ASD. Early functional differences in ASD can be captured using EEG during infancy and may inform much-needed advancements in the early detection of ASD.

show abstract

Evaluation of Artifact Subspace Reconstruction for Automatic EEG Artifact Removal

Cited by 262 publications

References 12 publications

A Bayesian framework for unifying data cleaning, source separation and imaging of electroencephalographic signals

A Bayesian framework for unifying data cleaning, source separation and imaging of electroencephalographic signals

HEAR to remove pops and drifts: the high-variance electrode artifact removal (HEAR) algorithm

Functional connectivity differences in early infancy precede autism symptoms: a multivariate pattern analysis

Contact Info

Product

Resources

About