{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T13:44:19Z","timestamp":1794318259868,"version":"4.9.0"},"reference-count":65,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T00:00:00Z","timestamp":1624320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>We present a deep learning solution to the problem of localization of magnetoencephalography (MEG) brain signals. The proposed deep model architectures are tuned to single and multiple time point MEG data, and can estimate varying numbers of dipole sources. Results from simulated MEG data on the cortical surface of a real human subject demonstrated improvements against the popular RAP-MUSIC localization algorithm in specific scenarios with varying SNR levels, inter-source correlation values, and number of sources. Importantly, the deep learning models had robust performance to forward model errors resulting from head translation and rotation and a significant reduction in computation time, to a fraction of 1 ms, paving the way to real-time MEG source localization.<\/jats:p>","DOI":"10.3390\/s21134278","type":"journal-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T22:10:59Z","timestamp":1624399859000},"page":"4278","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["MEG Source Localization via Deep Learning"],"prefix":"10.3390","volume":"21","author":[{"given":"Dimitrios","family":"Pantazis","sequence":"first","affiliation":[{"name":"McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Adler","sequence":"additional","affiliation":[{"name":"McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"},{"name":"Electrical Engineering Department, Braude College of Engineering, Karmiel 2161002, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.neubiorev.2017.10.006","article-title":"Transcranial magnetic stimulation in basic and clinical neuroscience: A comprehensive review of fundamental principles and novel insights","volume":"83","author":"Amengual","year":"2017","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.biopsych.2018.03.009","article-title":"Cortical Paired Associative Stimulation Influences Response Inhibition: Cortico-cortical and Cortico-subcortical Networks","volume":"85","author":"Kohl","year":"2019","journal-title":"Biol. Psychiatry"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/j.neuron.2019.01.019","article-title":"Manipulation of Subcortical and Deep Cortical Activity in the Primate Brain Using Transcranial Focused Ultrasound Stimulation","volume":"101","author":"Folloni","year":"2019","journal-title":"Neuron"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/s13311-018-00691-3","article-title":"Focused Ultrasound for Neuromodulation","volume":"16","author":"Darrow","year":"2019","journal-title":"Neurotherapeutics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.tibtech.2017.03.008","article-title":"Harnessing Prefrontal Cognitive Signals for Brain\u2013Machine Interfaces","volume":"35","author":"Min","year":"2017","journal-title":"Trends Biotechnol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/B978-0-444-63934-9.00009-3","article-title":"Brain-computer interfaces in neurologic rehabilitation practice","volume":"Volume 168","author":"Pichiorri","year":"2020","journal-title":"Handbook of Clinical Neurology"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ilmoniemi, R., and Sarvas, J. (2019). Brain Signals: Physics and Mathematics of MEG and EEG, MIT Press.","DOI":"10.7551\/mitpress\/10745.001.0001"},{"key":"ref_8","unstructured":"Niedermeyer, E., Schomer, D.L., and Lopes da Silva, F.H. (2012). Niedermeyer\u2019s Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincott Williams & Wilkins."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1103\/RevModPhys.65.413","article-title":"Magnetoencephalography\u2014Theory, instrumentation, and applications to noninvasive studies of the working human brain","volume":"65","author":"Hari","year":"1993","journal-title":"Rev. Mod. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1038\/nn.4504","article-title":"Magnetoencephalography for brain electrophysiology and imaging","volume":"20","author":"Baillet","year":"2017","journal-title":"Nat. Neurosci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"S289","DOI":"10.1016\/j.neuroimage.2004.07.014","article-title":"Mapping human brain function with MEG and EEG: Methods and validation","volume":"23","author":"Darvas","year":"2004","journal-title":"NeuroImage"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1534","DOI":"10.1109\/JPROC.2004.833655","article-title":"Superconducting quantum interference devices: State of the art and applications","volume":"92","author":"Kleiner","year":"2004","journal-title":"Proc. IEEE"},{"key":"ref_13","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1440","DOI":"10.1109\/TMI.2018.2832656","article-title":"CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction","volume":"37","author":"Gupta","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep Convolutional Neural Network for Inverse Problems in Imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gjesteby, L., Yang, Q., Xi, Y., Zhou, Y., Zhang, J., and Wang, G. (2017, January 11\u201316). Deep Learning Methods to Guide CT Image Reconstruction and Reduce Metal Artifacts. Proceedings of the SPIE Medical Imaging, Orlando, FL, USA.","DOI":"10.1117\/12.2254091"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2019.2950557","article-title":"Deep Magnetic Resonance Image Reconstruction: Inverse Problems Meet Neural Networks","volume":"37","author":"Liang","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, S., Su, Z., Ying, L., Peng, X., Zhu, S., Liang, F., Feng, D., and Liang, D. (2016, January 13\u201316). Accelerating magnetic resonance imaging via deep learning. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic.","DOI":"10.1109\/ISBI.2016.7493320"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1109\/TMI.2017.2760978","article-title":"A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction","volume":"37","author":"Schlemper","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/TMI.2018.2888491","article-title":"PET Image Reconstruction Using Deep Image Prior","volume":"38","author":"Gong","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1109\/TMI.2018.2832613","article-title":"Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting","volume":"37","author":"Kim","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image Super-Resolution Using Deep Convolutional Networks","volume":"38","author":"Dong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., and Lee, K.M. (July, January 26). Accurate Image Super-Resolution Using Very Deep Convolutional Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., and Lee, K.M. (2017, January 21\u201326). Enhanced Deep Residual Networks for Single Image Super-Resolution. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1109\/TMI.2018.2820382","article-title":"Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography","volume":"37","author":"Hauptmann","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/JSTSP.2017.2784181","article-title":"Deep Learning for Passive Synthetic Aperture Radar","volume":"12","author":"Yonel","year":"2018","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Budillon, A., Johnsy, A.C., Schirinzi, G., and Vitale, S. (August, January 28). Sar Tomography Based on Deep Learning. Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8900616"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1190\/tle37010058.1","article-title":"Deep-learning tomography","volume":"37","author":"Jennings","year":"2018","journal-title":"Lead. Edge"},{"key":"ref_29","unstructured":"Zhang, Q., Yuasa, M., Nagashino, H., and Kinouchi, Y. (1998, January 1). Single dipole source localization from conventional EEG using BP neural networks. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Hong Kong, China."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1142\/S0129065701000813","article-title":"EEG source localization: A comparative study of classical and neural network methods","volume":"11","author":"Abeyratne","year":"2001","journal-title":"Int. J. Neural Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1179\/016164101101198848","article-title":"EEG source localization: a neural network approach","volume":"23","author":"Sclabassi","year":"2001","journal-title":"Neurol. Res."},{"key":"ref_32","unstructured":"Yuasa, M., Zhang, Q., Nagashino, H., and Kinouchi, Y. (1998, January 1). EEG source localization for two dipoles by neural networks. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Hong Kong, China."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"131","DOI":"10.23919\/JCC.2019.07.011","article-title":"EEG source localization using spatio-temporal neural network","volume":"16","author":"Cui","year":"2019","journal-title":"China Commun."},{"key":"ref_34","unstructured":"Dinh, C., Samuelsson, J.G., Hunold, A., H\u00e4m\u00e4l\u00e4inen, M.S., and Khan, S. (2019). Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"533","DOI":"10.3389\/fnins.2021.569918","article-title":"ConvDip: A convolutional neural network for better M\/EEG Source Imaging","volume":"15","author":"Hecker","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1109\/10.141192","article-title":"Multiple dipole modeling and localization from spatio-temporal MEG data","volume":"39","author":"Mosher","year":"1992","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/S0168-5597(97)00091-9","article-title":"Multi-start downhill simplex method for spatio-temporal source localization in magnetoencephalography","volume":"108","author":"Huang","year":"1998","journal-title":"Electroencephalogr. Clin. Neurophysiol. Potentials Sect."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/10.678606","article-title":"Global optimization in the localization of neuromagnetic sources","volume":"45","author":"Uutela","year":"1998","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1109\/10.641335","article-title":"Spatio-temporal EEG source localization using simulated annealing","volume":"44","author":"Khosla","year":"1997","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1080\/0020716022000009255","article-title":"A Comparative Study Of Global Optimization Approaches To Meg Source Localization","volume":"80","author":"Jiang","year":"2003","journal-title":"Int. J. Comput. Math."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1109\/10.623056","article-title":"Localization of brain electrical activity via linearly constrained minimum variance spatial filtering","volume":"44","author":"Drongelen","year":"1997","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1006\/meth.2001.1238","article-title":"Signal Processing in Magnetoencephalography","volume":"25","author":"Vrba","year":"2001","journal-title":"Methods"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1109\/TBME.2006.873752","article-title":"Modified beamformers for coherent source region suppression","volume":"53","author":"Dalal","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1016\/j.neuroimage.2006.11.012","article-title":"Beamformer reconstruction of correlated sources using a modified source","volume":"34","author":"Brookes","year":"2007","journal-title":"NeuroImage"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3161","DOI":"10.1016\/j.neuroimage.2009.10.078","article-title":"Identifying true cortical interactions in MEG using the nulling beamformer","volume":"49","author":"Hui","year":"2010","journal-title":"NeuroImage"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neuroimage.2010.07.023","article-title":"Dual-Core Beamformer for obtaining highly correlated neuronal networks in MEG","volume":"54","author":"Diwakar","year":"2011","journal-title":"NeuroImage"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1918","DOI":"10.1016\/j.neuroimage.2011.03.042","article-title":"Accurate reconstruction of temporal correlation for neuronal sources using the enhanced dual-core MEG beamformer","volume":"56","author":"Diwakar","year":"2011","journal-title":"NeuroImage"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.neuroimage.2011.05.081","article-title":"Application of multi-source minimum variance beamformers for reconstruction of correlated neural activity","volume":"58","author":"Moiseev","year":"2011","journal-title":"NeuroImage"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neuroimage.2012.12.072","article-title":"Multi-core beamformers: Derivation, limitations and improvements","volume":"71","author":"Moiseev","year":"2013","journal-title":"NeuroImage"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TBME.2006.870236","article-title":"Efficient localization of synchronous EEG source activities using a modified RAP-MUSIC algorithm","volume":"53","author":"Hesheng","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1016\/j.neuroimage.2014.07.011","article-title":"Wedge MUSIC: A novel approach to examine experimental differences of brain source connectivity patterns from EEG\/MEG data","volume":"101","author":"Ewald","year":"2014","journal-title":"NeuroImage"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1109\/78.740118","article-title":"Source localization using recursively applied and projected (RAP) MUSIC","volume":"47","author":"Mosher","year":"1999","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.neuroimage.2017.11.013","article-title":"Truncated RAP-MUSIC (TRAP-MUSIC) for MEG and EEG source localization","volume":"167","author":"Stenroos","year":"2018","journal-title":"NeuroImage"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"M\u00e4kel\u00e4, N., Stenroos, M., Sarvas, J., and Ilmoniemi, R.J. (2017). Locating highly correlated sources from MEG with (recursive) (R)DS-MUSIC. Neuroscience, preprint.","DOI":"10.1101\/230672"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/MSP.2017.2760358","article-title":"Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods","volume":"35","author":"Lucas","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation Learning: A Review and New Perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1109\/TASLP.2017.2672401","article-title":"Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition","volume":"25","author":"Sainath","year":"2017","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"S69","DOI":"10.1016\/j.neuroimage.2004.07.016","article-title":"Sequence-independent segmentation of magnetic resonance images","volume":"23","author":"Fischl","year":"2004","journal-title":"NeuroImage"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2011\/879716","article-title":"Brainstorm: a user-friendly application for MEG\/EEG analysis","volume":"2011","author":"Tadel","year":"2011","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1088\/0031-9155\/44\/2\/010","article-title":"A sensor-weighted overlapping-sphere head model and exhaustive head model comparison for MEG","volume":"44","author":"Huang","year":"1999","journal-title":"Phys. Med. Biol."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1109\/10.930901","article-title":"Reconstructing spatio-temporal activities of neural sources using an MEG vector beamformer technique","volume":"48","author":"Sekihara","year":"2001","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_62","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Rey Dean, J., and Hieu Devin, M. (2021, June 22). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, 2015. Available online: tensorflow.org."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.neuroimage.2015.01.043","article-title":"Influence of the head model on EEG and MEG source connectivity analyses","volume":"110","author":"Cho","year":"2015","journal-title":"Neuroimage"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1088\/0031-9155\/49\/5\/004","article-title":"Sensitivity of EEG and MEG measurements to tissue conductivity","volume":"49","author":"Acar","year":"2004","journal-title":"Phys. Med. Biol."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1109\/TSP.2021.3053495","article-title":"Detection of the Number of Signals by Signal Subspace Matching","volume":"69","author":"Wax","year":"2021","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4278\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:21:22Z","timestamp":1760163682000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,22]]},"references-count":65,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["s21134278"],"URL":"https:\/\/doi.org\/10.3390\/s21134278","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,22]]}}}