ICLabel: An automated electroencephalographic independent component classifier, dataset, and website
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
The electroencephalogram (EEG) provides a non-invasive, minimally restrictive, and relatively low-cost measure of mesoscale brain dynamics with high temporal resolution. Although signals recorded in parallel by multiple, near-adjacent EEG scalp electrode channels are highly-correlated and combine signals from many different sources, biological and non-biological, independent component analysis (ICA) has been shown to isolate the various source generator processes underlying those recordings. Independent components (IC) found by ICA decomposition can be manually inspected, selected, and interpreted, but doing so requires both time and practice as ICs have no order or intrinsic interpretations and therefore require further study of their properties. Alternatively, sufficiently-accurate automated IC classifiers can be used to classify ICs into broad source categories, speeding the analysis of EEG studies with many subjects and enabling the use of ICA decomposition in near-real-time applications. While many such classifiers have been proposed recently, this work presents the ICLabel project comprised of (1) the ICLabel dataset containing spatiotemporal measures for over 200,000 ICs from more than 6,000 EEG recordings and matching component labels for over 6,000 of those ICs, all using common average reference, (2) the ICLabel website for collecting crowdsourced IC labels and educating EEG researchers and practitioners about IC interpretation, and (3) the automated ICLabel classifier, freely available for MATLAB. The ICLabel classifier improves upon existing methods in two ways: by improving the accuracy of the computed label estimates and by enhancing its computational efficiency. The classifier outperforms or performs comparably to the previous best publicly available automated IC component classification method for all measured IC categories while computing those labels ten times faster than that classifier as shown by a systematic comparison against other publicly available EEG IC classifiers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delorme, A., & Makeig, S. (2004) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2003.10.009 · Cited by 24,371 · cited 1×
“The end result is made freely and easily available through the ICLabel plugin for the EEGLAB software environment (Delorme and Makeig, 2004; Delorme et al., 2011).”
Self-citationAdvances in neural information processing systems 7
Cios, K., & Shields, M. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,059
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
(2010) · International Conference on Machine Learning · Cited by 13,995
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Welch, P. (1967) · IEEE Transactions on Audio and Electroacoustics · doi:10.1109/tau.1967.1161901 · Cited by 12,277
Cited by
Partial recovery of visual function in a blind patient after optogenetic therapy
Sahel, J.-A., Boulanger-Scemama, E., Pagot, C., Arleo, A., Galluppi, F., Martel, J. N., Esposti, S. D., Delaux, A., de Saint Aubert, J.-B., de Montleau, C., et al. (2021) · Nature Medicine · doi:10.1038/s41591-021-01351-4 · Cited by 700
Chang, C.-Y., Hsu, S.-H., Pion-Tonachini, L., & Jung, T.-P. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2930186 · Cited by 544
Self-citationKlug, M., & Gramann, K. (2021) · European Journal of Neuroscience · doi:10.1111/ejn.14992 · Cited by 268
EEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising
Zhang, H., Zhao, M., Wei, C., Mantini, D., Li, Z., & Liu, Q. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac2bf8 · Cited by 263
Delorme, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-27528-0 · Cited by 260
Moguilner, S., Baez, S., Hernandez, H., Migeot, J., Legaz, A., Gonzalez-Gomez, R., Farina, F. R., Prado, P., Cuadros, J., Tagliazucchi, E., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03209-x · Cited by 128
“ICLabel (a tool for classifying EEG independent components into signals and different noise categories) 66 , and EyeCatch (a tool for identifying eye-related independent component analysis scalp maps) were used 67 .”
MethodChuang, C.-H., Chang, K.-Y., Huang, C.-S., & Jung, T.-P. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119586 · Cited by 88
Billeci, L., Callara, A. L., Guiducci, L., Prosperi, M., Morales, M. A., Calderoni, S., Muratori, F., & Santocchi, E. (2023) · Autism · doi:10.1177/13623613221082710 · Cited by 69
“The use of a high-density system for signals recording allows to have a clearer distinction between signal and noise components, such as those deriving from eye movements (Klug & Gramann, 2021) using appropriate processing methods like independent component analysis (ICA; Pion-Tonachini et al., 2019).”
MethodEmotion assessment using Machine Learning and low-cost wearable devices
Laureanti, R., Bilucaglia, M., Zito, M., Circi, R., Fici, A., Rivetti, F., Valesi, R., Oldrini, C., Mainardi, L. T., & Russo, V. (2020) · 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175221 · Cited by 33
EEG Lempel-Ziv complexity varies with sleep stage, but does not seem to track dream experience
Aamodt, A., Sevenius Nilsen, A., Markhus, R., Kusztor, A., HasanzadehMoghadam, F., Kauppi, N., Thürer, B., Storm, J. F., & Juel, B. E. (2023) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2022.987714 · Cited by 30
EEG Signal Diversity Varies With Sleep Stage and Aspects of Dream Experience
Aamodt, A., Nilsen, A. S., Thürer, B., Moghadam, F. H., Kauppi, N., Juel, B. E., & Storm, J. F. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.655884 · Cited by 23
“2It is less clear whether PCI faithfully reflects variation in richness of experience within (approximately) the same state (Railo et al., 2017; Farnes et al., 2020; Tuominen et al., 2021), or whether it should even be expected to do so, given that ongoing activity is averaged out in the…”
BackgroundStructural inequality and temporal brain dynamics across diverse samples
Baez, S., Hernandez, H., Moguilner, S., Cuadros, J., Santamaria‐Garcia, H., Medel, V., Migeot, J., Cruzat, J., Valdes‐Sosa, P. A., Lopera, F., et al. (2024) · Clinical and Translational Medicine · doi:10.1002/ctm2.70032 · Cited by 21
EEG of the Dancing Brain: Decoding Sensory, Motor, and Social Processes during Dyadic Dance
Bigand, F., Bianco, R., Abalde, S. F., Nguyen, T., & Novembre, G. (2025) · The Journal of Neuroscience · doi:10.1523/jneurosci.2372-24.2025 · Cited by 21
“Finally, eye-movement artifacts were subtracted from the ASR-cleaned data using another automatic artifact correction algorithm (ICA), using EEGlab ’ s IClabel function (Pion-Tonachini et al., 2019).”
Perera, M. P. N., Mallawaarachchi, S., Bailey, N. W., Murphy, O. W., & Fitzgerald, P. B. (2023) · Psychological Medicine · doi:10.1017/s0033291723000843 · Cited by 18
“Artifactual ICA components were detected using ICLabel [47] and these were cleaned with wavelet enhanced ICA (wICA) [48].”
MethodDück, K., Overmeyer, R., Mohr, H., & Endrass, T. (2023) · Psychophysiology · doi:10.1111/psyp.14310 · Cited by 10
Perez, T. M., Glue, P., Adhia, D. B., Navid, M. S., Zeng, J., Dillingham, P., Smith, M., Niazi, I. K., Young, C. K., & De Ridder, D. (2022) · Trials · doi:10.1186/s13063-022-06863-z · Cited by 8
“We will use ICLabel [238] with manual verification to categorize the ICs as brain or other (i.”
MethodElmaghraby, R., Blank, E., Miyakoshi, M., Gilbert, D. L., Wu, S. W., Larsh, T., Westerkamp, G., Liu, Y., Horn, P. S., Erickson, C. A., et al. (2025) · Journal of Child and Adolescent Psychopharmacology · doi:10.1089/cap.2024.0109 · Cited by 5
“EEGLAB plugin ICLabel was applied (Pion-Tonachini et al., 2019) to generate probabilistic class labels for the ICs.”
Brain clocks capture diversity and disparity in aging and dementia
(2024) · doi:10.21203/rs.3.rs-4150225/v1 · Cited by 2
Metadata
- Authors
- Pion-Tonachini, L., Kreutz-Delgado, K., & Makeig, S.
- Venue
- NeuroImage
- Publisher
- Elsevier BV
- Published
- 2019-09
- Volume
- 198
- Pages
- 181-197
- ISSN
- 1053-8119 (ISSN-L)
- OpenAlex
- W2914237854
- Cited by
- 2,267
- References
- 53
- FWCI
- 63.27
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.