{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:36:15Z","timestamp":1776314175673,"version":"3.50.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>A challenge when applying an artificial intelligence (AI) deep learning (DL) approach to novel electroencephalography (EEG) data, is the DL architecture's lack of adaptability to changing numbers of EEG channels. That is, the number of channels cannot vary neither in the training data, nor upon deployment. Such highly specific hardware constraints put major limitations on the clinical usability and scalability of the DL models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this work, we propose a technique for handling such varied numbers of EEG channels by splitting the EEG montages into distinct regions and merge the channels within the same region to a region representation. The solution is termed <jats:italic>Region Based Pooling<\/jats:italic> (RBP). The procedure of splitting the montage into regions is performed repeatedly with different region configurations, to minimize potential loss of information. As RBP maps a varied number of EEG channels to a fixed number of region representations, both current and future DL architectures may apply RBP with ease. To demonstrate and evaluate the adequacy of RBP to handle a varied number of EEG channels, sex classification based solely on EEG was used as a test example. The DL models were trained on 129 channels, and tested on 32, 65, and 129-channels versions of the data using the same channel positions scheme. The baselines for comparison were zero-filling the missing channels and applying spherical spline interpolation. The performances were estimated using 5-fold cross validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>For the 32-channel system version, the mean AUC values across the folds were: RBP (93.34%), spherical spline interpolation (93.36%), and zero-filling (76.82%). Similarly, on the 65-channel system version, the performances were: RBP (93.66%), spherical spline interpolation (93.50%), and zero-filling (85.58%). Finally, the 129-channel system version produced the following results: RBP (94.68%), spherical spline interpolation (93.86%), and zero-filling (91.92%).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>In conclusion, RBP obtained similar results to spherical spline interpolation, and superior results to zero-filling. We encourage further research and development of DL models in the cross-dataset setting, including the use of methods such as RBP and spherical spline interpolation to handle a varied number of EEG channels.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fninf.2023.1272791","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T04:16:31Z","timestamp":1706588191000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Introducing Region Based Pooling for handling a varied number of EEG channels for deep learning models"],"prefix":"10.3389","volume":"17","author":[{"given":"Thomas","family":"Tveitst\u00f8l","sequence":"first","affiliation":[]},{"given":"Mats","family":"Tveter","sequence":"additional","affiliation":[]},{"given":"Ana S.","family":"P\u00e9rez T.","sequence":"additional","affiliation":[]},{"given":"Christoffer","family":"Hatlestad-Hall","sequence":"additional","affiliation":[]},{"given":"Anis","family":"Yazidi","sequence":"additional","affiliation":[]},{"given":"Hugo L.","family":"Hammer","sequence":"additional","affiliation":[]},{"given":"Ira R. J.","family":"Hebold Haraldsen","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"75","DOI":"10.3390\/brainsci11010075","article-title":"Hybrid deep learning (hdl)-based brain-computer interface (bci) systems: a systematic review","volume":"11","author":"Abo Alzahab","year":"2021","journal-title":"Brain Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"6486570","DOI":"10.1155\/2022\/6486570","article-title":"Eeg-based epileptic seizure detection via machine\/deep learning approaches: a systematic review","volume":"2022","author":"Ahmad","year":"2022","journal-title":"Intell. Neurosci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"170181","DOI":"10.1101\/149369","article-title":"An open resource for transdiagnostic research in pediatric mental health and learning disorders","volume":"4","author":"Alexander","year":"2017","journal-title":"Sci. Data"},{"key":"B4","doi-asserted-by":"publisher","first-page":"46020","DOI":"10.1088\/1741-2552\/abca18","article-title":"Uncovering the structure of clinical EEG signals with self-supervised learning","volume":"18","author":"Banville","year":"2021","journal-title":"J. Neural Eng"},{"key":"B5","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","article-title":"Algorithmic fairness in artificial intelligence for medicine and healthcare","volume":"7","author":"Chen","year":"2023","journal-title":"Nat. Biomed. Eng"},{"key":"B6","doi-asserted-by":"publisher","first-page":"108117","DOI":"10.1016\/j.biopsycho.2021.108117","article-title":"Deep learning applied to electroencephalogram data in mental disorders: a systematic review","volume":"162","author":"de Bardeci","year":"2021","journal-title":"Biol. Psychol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"116356","DOI":"10.1016\/j.neuroimage.2019.116356","article-title":"Zapline: a simple and effective method to remove power line artifacts","volume":"207","author":"de Cheveign\u00e9","year":"2020","journal-title":"Neuroimage"},{"key":"B8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","article-title":"Eeglab: an open source toolbox for analysis of single-trial eeg dynamics including independent component analysis","volume":"134","author":"Delorme","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Min. Knowl. Discov"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3552","DOI":"10.1109\/JSEN.2020.3026830","article-title":"Classification of alcoholic eeg signals using a deep learning method","volume":"21","author":"Farsi","year":"2021","journal-title":"IEEE Sens. J"},{"key":"B11","article-title":"\u201cGenerative adversarianets,\u201d","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems, Vol. 27"},{"key":"B12","first-page":"85","volume-title":"Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems","author":"Grieves","year":"2017"},{"key":"B13","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","article-title":"Dynamic neural networks: a survey","volume":"44","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.clinph.2023.03.002","article-title":"Reliable evaluation of functional connectivity and graph theory measures in source-level eeg: how many electrodes are enough?","volume":"150","author":"Hatlestad-Hall","year":"2023","journal-title":"Clin. Neurophysiol"},{"key":"B15","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","article-title":"\u201cSpatial pyramid pooling in deep convolutional networks for visual recognition,\u201d","author":"He","year":"2014","journal-title":"Computer Vision-ECCV 2014"},{"key":"B16","first-page":"2712","article-title":"\u201cUsing pre-training can improve model robustness and uncertainty,\u201d","author":"Hendrycks","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1001\/jama.2018.11100","article-title":"Deep learning\u2014a technology with the potential to transform health care","volume":"320","author":"Hinton","year":"2018","journal-title":"JAMA"},{"key":"B18","doi-asserted-by":"publisher","first-page":"12527","DOI":"10.1007\/s00521-022-07292-4","article-title":"Human emotion recognition from eeg-based brain\u2013computer interface using machine learning: a comprehensive review","volume":"34","author":"Houssein","year":"2022","journal-title":"Neural Comp. Appl"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: Finding alexnet for time series classification","volume":"34","author":"Ismail Fawaz","year":"2020","journal-title":"Data Min. Knowl. Discov"},{"key":"B20","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"B21","first-page":"7","article-title":"\u201cAdam: a method for stochastic optimization,\u201d","author":"Kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings"},{"key":"B22","doi-asserted-by":"publisher","first-page":"653659","DOI":"10.3389\/fnhum.2021.653659","article-title":"Bendr: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data","volume":"15","author":"Kostas","year":"2021","journal-title":"Front. Hum. Neurosci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1007\/s10548-018-0658-3","article-title":"High frequency oscillations in the ripple band (80-250 hz) in scalp EEG: Higher density of electrodes allows for better localization of the seizure onset zone","volume":"31","author":"Kuhnke","year":"2018","journal-title":"Brain Topogr"},{"key":"B24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B25","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/978-3-030-99948-3_17","article-title":"\u201cSPP-EEGNET: an input-agnostic self-supervised EEG representation model for inter-dataset transfer learning,\u201d","volume-title":"Proceedings of the 18th International Conference on Computing and Information Technology (IC2IT 2022)","author":"Li","year":"2022"},{"key":"B26","doi-asserted-by":"publisher","first-page":"031005","DOI":"10.1088\/1741-2552\/aab2f2","article-title":"A review of classification algorithms for EEG-based brain\u2013computer interfaces: a 10 year update","volume":"15","author":"Lotte","year":"2018","journal-title":"J. Neural Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10255842.2022.2112574","article-title":"Driver drowsiness detection methods using eeg signals: a systematic review","volume":"26","author":"Mohammed","year":"2022","journal-title":"Comp. Methods Biomech. Biomed. Eng"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2870","DOI":"10.3390\/app9142870","article-title":"Deep convolutional neural network model for automated diagnosis of schizophrenia using eeg signals","volume":"9","author":"Oh","year":"2019","journal-title":"Appl. Sci"},{"key":"B29","volume-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","author":"Paszke","year":"2019"},{"key":"B30","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/0013-4694(89)90180-6","article-title":"Spherical splines for scalp potential and current density mapping","volume":"72","author":"Perrin","year":"1989","journal-title":"Electroencephalogr. Clin. Neurophysiol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"Ai in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat. Med"},{"key":"B32","doi-asserted-by":"publisher","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: a systematic review","volume":"16","author":"Roy","year":"2019","journal-title":"J. Neural Eng"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10618-020-00727-3","article-title":"The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances","volume":"35","author":"Ruiz","year":"2021","journal-title":"Data Min. Knowl. Discov"},{"key":"B34","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1093\/cercor\/bhj127","article-title":"Small-world networks and functional connectivity in Alzheimer's disease","volume":"17","author":"Stam","year":"2006","journal-title":"Cereb. Cortex"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3786","DOI":"10.3390\/s21113786","article-title":"A review of eeg signal features and their application in driver drowsiness detection systems","volume":"21","author":"Stancin","year":"2021","journal-title":"Sensors"},{"key":"B36","doi-asserted-by":"publisher","first-page":"e524","DOI":"10.1016\/S2214-109X(20)30062-0","article-title":"Prediction of dementia risk in low-income and middle-income countries (the 10\/66 study): an independent external validation of existing models","volume":"8","author":"Stephan","year":"2020","journal-title":"Lancet Global Health"},{"key":"B37","first-page":"205","article-title":"\u201c2021 beetl competition: advancing transfer learning for subject independence & heterogenous eeg data sets,\u201d","author":"Wei","year":"2022","journal-title":"Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, volume 176 of Proceedings of Machine Learning Research"},{"key":"B38","doi-asserted-by":"publisher","first-page":"106007","DOI":"10.1016\/j.cmpb.2021.106007","article-title":"Eeg based major depressive disorder and bipolar disorder detection using neural networks:a review","volume":"202","author":"Yasin","year":"2021","journal-title":"Comput. Methods Programs Biomed"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1272791\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T04:16:38Z","timestamp":1706588198000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1272791\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":38,"alternative-id":["10.3389\/fninf.2023.1272791"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2023.1272791","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]},"article-number":"1272791"}}