Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network

Electromagnetic source imaging (ESI) requires solving a highly ill-posed inverse problem. To seek a unique solution, traditional ESI methods impose various forms of priors that may not accurately reflect the actual source properties, which may hinder their broad applications. To overcome this limita...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Gexin, Liang, Jiawen, Liu, Ke, Cai, Chang, Gu, ZhengHui, Qi, Feifei, Li, Yuan Qing, Yu, Zhu Liang, Wu, Wei
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Huang, Gexin
Liang, Jiawen
Liu, Ke
Cai, Chang
Gu, ZhengHui
Qi, Feifei
Li, Yuan Qing
Yu, Zhu Liang
Wu, Wei
description Electromagnetic source imaging (ESI) requires solving a highly ill-posed inverse problem. To seek a unique solution, traditional ESI methods impose various forms of priors that may not accurately reflect the actual source properties, which may hinder their broad applications. To overcome this limitation, in this paper a novel data-synthesized spatio-temporally convolutional encoder-decoder network method termed DST-CedNet is proposed for ESI. DST-CedNet recasts ESI as a machine learning problem, where discriminative learning and latent-space representations are integrated in a convolutional encoder-decoder network (CedNet) to learn a robust mapping from the measured electroencephalography/magnetoencephalography (E/MEG) signals to the brain activity. In particular, by incorporating prior knowledge regarding dynamical brain activities, a novel data synthesis strategy is devised to generate large-scale samples for effectively training CedNet. This stands in contrast to traditional ESI methods where the prior information is often enforced via constraints primarily aimed for mathematical convenience. Extensive numerical experiments as well as analysis of a real MEG and Epilepsy EEG dataset demonstrate that DST-CedNet outperforms several state-of-the-art ESI methods in robustly estimating source signals under a variety of source configurations.
doi_str_mv 10.48550/arxiv.2010.12876
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2010_12876</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2010_12876</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-1d3b977d3c1979b2586a160f2cefb7bb72df23f2dadee6760ebaefbd08edf3a13</originalsourceid><addsrcrecordid>eNotj8tOwzAURLNhgQofwAr_gIsfJE6WkBaoVMGi3UfX9nWxSG3kuIH-PSGwGumMZqRTFDecLe_rsmR3kL79uBRsAlzUqrosunWPJqd4hEPA7A3ZxVMySDYT8OFARg8EyAoy0N055Hcc_EAfYUBL2hjG2J-yjwF6sg4mWkx0hXOSV8xfMX1cFRcO-gGv_3NR7J_W-_aFbt-eN-3DlkKlKsqt1I1SVhreqEaLsq6AV8wJg04rrZWwTkgnLFjEacBQw9RYVqN1ErhcFLd_t7Nh95n8EdK5-zXtZlP5A-umULk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network</title><source>arXiv.org</source><creator>Huang, Gexin ; Liang, Jiawen ; Liu, Ke ; Cai, Chang ; Gu, ZhengHui ; Qi, Feifei ; Li, Yuan Qing ; Yu, Zhu Liang ; Wu, Wei</creator><creatorcontrib>Huang, Gexin ; Liang, Jiawen ; Liu, Ke ; Cai, Chang ; Gu, ZhengHui ; Qi, Feifei ; Li, Yuan Qing ; Yu, Zhu Liang ; Wu, Wei</creatorcontrib><description>Electromagnetic source imaging (ESI) requires solving a highly ill-posed inverse problem. To seek a unique solution, traditional ESI methods impose various forms of priors that may not accurately reflect the actual source properties, which may hinder their broad applications. To overcome this limitation, in this paper a novel data-synthesized spatio-temporally convolutional encoder-decoder network method termed DST-CedNet is proposed for ESI. DST-CedNet recasts ESI as a machine learning problem, where discriminative learning and latent-space representations are integrated in a convolutional encoder-decoder network (CedNet) to learn a robust mapping from the measured electroencephalography/magnetoencephalography (E/MEG) signals to the brain activity. In particular, by incorporating prior knowledge regarding dynamical brain activities, a novel data synthesis strategy is devised to generate large-scale samples for effectively training CedNet. This stands in contrast to traditional ESI methods where the prior information is often enforced via constraints primarily aimed for mathematical convenience. Extensive numerical experiments as well as analysis of a real MEG and Epilepsy EEG dataset demonstrate that DST-CedNet outperforms several state-of-the-art ESI methods in robustly estimating source signals under a variety of source configurations.</description><identifier>DOI: 10.48550/arxiv.2010.12876</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2020-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2010.12876$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2010.12876$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Huang, Gexin</creatorcontrib><creatorcontrib>Liang, Jiawen</creatorcontrib><creatorcontrib>Liu, Ke</creatorcontrib><creatorcontrib>Cai, Chang</creatorcontrib><creatorcontrib>Gu, ZhengHui</creatorcontrib><creatorcontrib>Qi, Feifei</creatorcontrib><creatorcontrib>Li, Yuan Qing</creatorcontrib><creatorcontrib>Yu, Zhu Liang</creatorcontrib><creatorcontrib>Wu, Wei</creatorcontrib><title>Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network</title><description>Electromagnetic source imaging (ESI) requires solving a highly ill-posed inverse problem. To seek a unique solution, traditional ESI methods impose various forms of priors that may not accurately reflect the actual source properties, which may hinder their broad applications. To overcome this limitation, in this paper a novel data-synthesized spatio-temporally convolutional encoder-decoder network method termed DST-CedNet is proposed for ESI. DST-CedNet recasts ESI as a machine learning problem, where discriminative learning and latent-space representations are integrated in a convolutional encoder-decoder network (CedNet) to learn a robust mapping from the measured electroencephalography/magnetoencephalography (E/MEG) signals to the brain activity. In particular, by incorporating prior knowledge regarding dynamical brain activities, a novel data synthesis strategy is devised to generate large-scale samples for effectively training CedNet. This stands in contrast to traditional ESI methods where the prior information is often enforced via constraints primarily aimed for mathematical convenience. Extensive numerical experiments as well as analysis of a real MEG and Epilepsy EEG dataset demonstrate that DST-CedNet outperforms several state-of-the-art ESI methods in robustly estimating source signals under a variety of source configurations.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURLNhgQofwAr_gIsfJE6WkBaoVMGi3UfX9nWxSG3kuIH-PSGwGumMZqRTFDecLe_rsmR3kL79uBRsAlzUqrosunWPJqd4hEPA7A3ZxVMySDYT8OFARg8EyAoy0N055Hcc_EAfYUBL2hjG2J-yjwF6sg4mWkx0hXOSV8xfMX1cFRcO-gGv_3NR7J_W-_aFbt-eN-3DlkKlKsqt1I1SVhreqEaLsq6AV8wJg04rrZWwTkgnLFjEacBQw9RYVqN1ErhcFLd_t7Nh95n8EdK5-zXtZlP5A-umULk</recordid><startdate>20201024</startdate><enddate>20201024</enddate><creator>Huang, Gexin</creator><creator>Liang, Jiawen</creator><creator>Liu, Ke</creator><creator>Cai, Chang</creator><creator>Gu, ZhengHui</creator><creator>Qi, Feifei</creator><creator>Li, Yuan Qing</creator><creator>Yu, Zhu Liang</creator><creator>Wu, Wei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201024</creationdate><title>Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network</title><author>Huang, Gexin ; Liang, Jiawen ; Liu, Ke ; Cai, Chang ; Gu, ZhengHui ; Qi, Feifei ; Li, Yuan Qing ; Yu, Zhu Liang ; Wu, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-1d3b977d3c1979b2586a160f2cefb7bb72df23f2dadee6760ebaefbd08edf3a13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Huang, Gexin</creatorcontrib><creatorcontrib>Liang, Jiawen</creatorcontrib><creatorcontrib>Liu, Ke</creatorcontrib><creatorcontrib>Cai, Chang</creatorcontrib><creatorcontrib>Gu, ZhengHui</creatorcontrib><creatorcontrib>Qi, Feifei</creatorcontrib><creatorcontrib>Li, Yuan Qing</creatorcontrib><creatorcontrib>Yu, Zhu Liang</creatorcontrib><creatorcontrib>Wu, Wei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Huang, Gexin</au><au>Liang, Jiawen</au><au>Liu, Ke</au><au>Cai, Chang</au><au>Gu, ZhengHui</au><au>Qi, Feifei</au><au>Li, Yuan Qing</au><au>Yu, Zhu Liang</au><au>Wu, Wei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network</atitle><date>2020-10-24</date><risdate>2020</risdate><abstract>Electromagnetic source imaging (ESI) requires solving a highly ill-posed inverse problem. To seek a unique solution, traditional ESI methods impose various forms of priors that may not accurately reflect the actual source properties, which may hinder their broad applications. To overcome this limitation, in this paper a novel data-synthesized spatio-temporally convolutional encoder-decoder network method termed DST-CedNet is proposed for ESI. DST-CedNet recasts ESI as a machine learning problem, where discriminative learning and latent-space representations are integrated in a convolutional encoder-decoder network (CedNet) to learn a robust mapping from the measured electroencephalography/magnetoencephalography (E/MEG) signals to the brain activity. In particular, by incorporating prior knowledge regarding dynamical brain activities, a novel data synthesis strategy is devised to generate large-scale samples for effectively training CedNet. This stands in contrast to traditional ESI methods where the prior information is often enforced via constraints primarily aimed for mathematical convenience. Extensive numerical experiments as well as analysis of a real MEG and Epilepsy EEG dataset demonstrate that DST-CedNet outperforms several state-of-the-art ESI methods in robustly estimating source signals under a variety of source configurations.</abstract><doi>10.48550/arxiv.2010.12876</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2010.12876
ispartof
issn
language eng
recordid cdi_arxiv_primary_2010_12876
source arXiv.org
subjects Computer Science - Learning
title Electromagnetic Source Imaging via a Data-Synthesis-Based Convolutional Encoder-Decoder Network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T17%3A54%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Electromagnetic%20Source%20Imaging%20via%20a%20Data-Synthesis-Based%20Convolutional%20Encoder-Decoder%20Network&rft.au=Huang,%20Gexin&rft.date=2020-10-24&rft_id=info:doi/10.48550/arxiv.2010.12876&rft_dat=%3Carxiv_GOX%3E2010_12876%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true