A Toolbox and Crowdsourcing Platform for Automatic Labeling of Independent Components in Electroencephalography

Soghoyan, Gurgen; Nekrashevich, Maxim; Ledovsky, Alexander; Martynova, Olga; Rebreikina, Anna; Sysoeva, Olga; Sharaev, Maxim

doi:10.3389/fninf.2021.720229

Cited by 22 publications

(12 citation statements)

References 25 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, MARA indicated that the ICA results always improved with more cleaning because MARA quantifies only the probability of a component containing an artifact, not the probability of a component being brain-like. Meanwhile, metrics such as ICLabel and ALICE [ 37 ] attempt to also label brain-like components. We decided to use ICLabel as our main component labeling method, combined with residual variance (from dipole fitting).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

iCanClean Improves Independent Component Analysis of Mobile Brain Imaging with EEG

Gonsisko

Ferris

Downey

2023

Sensors

View full text Add to dashboard Cite

Motion artifacts hinder source-level analysis of mobile electroencephalography (EEG) data using independent component analysis (ICA). iCanClean is a novel cleaning algorithm that uses reference noise recordings to remove noisy EEG subspaces, but it has not been formally tested in a parameter sweep. The goal of this study was to test iCanClean’s ability to improve the ICA decomposition of EEG data corrupted by walking motion artifacts. Our primary objective was to determine optimal settings and performance in a parameter sweep (varying the window length and r2 cleaning aggressiveness). High-density EEG was recorded with 120 + 120 (dual-layer) EEG electrodes in young adults, high-functioning older adults, and low-functioning older adults. EEG data were decomposed by ICA after basic preprocessing and iCanClean. Components well-localized as dipoles (residual variance < 15%) and with high brain probability (ICLabel > 50%) were marked as ‘good’. We determined iCanClean’s optimal window length and cleaning aggressiveness to be 4-s and r2 = 0.65 for our data. At these settings, iCanClean improved the average number of good components from 8.4 to 13.2 (+57%). Good performance could be maintained with reduced sets of noise channels (12.7, 12.2, and 12.0 good components for 64, 32, and 16 noise channels, respectively). Overall, iCanClean shows promise as an effective method to clean mobile EEG data.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This would provide important information regarding the situations in which different methods should be used. Finally, other recent component labeling algorithms such as ALICE [ 37 ] can be introduced when comparing different cleaning approaches to limit bias.…”

Section: Discussionmentioning

confidence: 99%

iCanClean Improves Independent Component Analysis of Mobile Brain Imaging with EEG

Gonsisko

Ferris

Downey

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…We analyzed EEG fragment 1756 s of eyes open condition for the patient and 1550–2000 s of eyes open condition for each child of the control group (1803 ± 79 s). Independent component analysis (ICA) was used when needed to subtract the most evident artifacts [ 20 ]. The three separate neurologists (including GP) with expert certification identified and interpreted the EEG data, reaching common decisions.…”

Section: Methodsmentioning

confidence: 99%

Does the Potocki–Lupski Syndrome Convey the Autism Spectrum Disorder Phenotype? Case Report and Scoping Review

Talantseva

Portnova

Romanova

et al. 2023

JPM

View full text Add to dashboard Cite

Potocki–Lupski Syndrome (PTLS) is a rare condition associated with a duplication of 17p11.2 that may underlie a wide range of congenital abnormalities and heterogeneous behavioral phenotypes. Along with developmental delay and intellectual disability, autism-specific traits are often reported to be the most common among patients with PTLS. To contribute to the discussion of the role of autism spectrum disorder (ASD) in the PTLS phenotype, we present a case of a female adolescent with a de novo dup(17) (p11.2p11.2) without ASD features, focusing on in-depth clinical, behavioral, and electrophysiological (EEG) evaluations. Among EEG features, we found the atypical peak–slow wave patterns and a unique saw-like sharp wave of 13 Hz that was not previously described in any other patient. The power spectral density of the resting state EEG was typical in our patient with only the values of non-linear EEG dynamics: Hjorth complexity and fractal dimension were drastically attenuated compared with the patient’s neurotypical peers. Here we also summarize results from previously published reports of PTLS that point to the approximately 21% occurrence of ASD in PTLS that might be biased, taking into account methodological limitations. More consistent among PTLS patients were intellectual disability and speech and language disorders.

show abstract

“…Bad channel interpolation was applied when necessary (0-2 channels per participant). Automatic raw data inspection with ± 400µV thresholds was used for rejecting EEG segments with large artifacts, then for artifact rejection, the independent component analysis (ICA) was performed, in particular the ALICE platform was used [19]. The data were segmented into epochs starting 200 ms before a stimuli onset and lasting 500 ms after the onset.…”

Section: Data Processingmentioning

confidence: 99%

Effect of presentation rate on auditory processing in Rett Syndrome: ERP study

Kostanian

Rebreikina

Nekrashevich

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Rett Syndrome (RS) is a rare neurodevelopmeтtal disorder characterized by mutations in the MECP2 gene. Patients with RS have severe motor abnormalities and are often unable to walk, use hands and speak. The preservation of perceptual and cognitive functions is hard to assess, while clinicians and care-givers point out that these patients need more time to process information than typically developing peers. Here we examine neurophysiological correlates of auditory processing in RS as a function of presentation rate. From previous literature we knew that auditory event-related potential (ERP) is increased with prolongation of interstimulus interval (ISI). We presented a repetitive stimulus (1000Hz) at three different ISI of 900 ms, 1800 ms, and 3600 ms in children with RS and their typical development peers (TD) aged 2.5–16 years while recording 28-channels electroencephalogram, EEG. The amplitude of N1 and P2 components of event-related potential (ERP) was smaller at ISI 900 than at longer ISIs in both groups, pointing out that the basic mechanism of adaptation in the auditory system is preserved in Rett Syndrome. At the same time the latency of these components was significantly delayed in the RS than in TD. Moreover, late components (P2 and N2) were drastically reduced in Rett Syndrome irrespective of the ISI, suggesting a severely affected mechanism of integration of upcoming sensory input with memory. Based on these ERP measures it was possible to differentiate RS from TD with great accuracy (0.922 ± 0.047), being maximal with shortest ISI, supporting its implication as potential output measures in clinical trials as well as pointing to the diminishing of the neurophysiological differences between RS and TD with slowing down the presentation rate.

show abstract

A Toolbox and Crowdsourcing Platform for Automatic Labeling of Independent Components in Electroencephalography

Cited by 22 publications

References 25 publications

iCanClean Improves Independent Component Analysis of Mobile Brain Imaging with EEG

iCanClean Improves Independent Component Analysis of Mobile Brain Imaging with EEG

Does the Potocki–Lupski Syndrome Convey the Autism Spectrum Disorder Phenotype? Case Report and Scoping Review

Effect of presentation rate on auditory processing in Rett Syndrome: ERP study

Contact Info

Product

Resources

About