{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:56:33Z","timestamp":1790769393914,"version":"4.1.0"},"reference-count":92,"publisher":"Wiley","issue":"15","license":[{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["18078"],"award-info":[{"award-number":["18078"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Human Brain Mapping"],"published-print":{"date-parts":[[2023,10,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Magnetic resonance electrical properties tomography (MR\u2010EPT) is a non\u2010invasive measurement technique that derives the electrical properties (EPs, e.g., conductivity or permittivity) of tissues in the radiofrequency range (64\u2009MHz for 1.5\u2009T and 128\u2009MHz for 3\u2009T MR systems). Clinical studies have shown the potential of tissue conductivity as a biomarker. To date, model\u2010based conductivity reconstructions rely on numerical assumptions and approximations, leading to inaccuracies in the reconstructed maps. To address such limitations, we propose an artificial neural network (ANN)\u2010based non\u2010linear conductivity estimator trained on simulated data for conductivity brain imaging. Network training was performed on 201 synthesized T2\u2010weighted spin\u2010echo (SE) data obtained from the finite\u2010difference time\u2010domain (FDTD) electromagnetic (EM) simulation. The dataset was composed of an approximated T2\u2010w SE magnitude and transceive phase information. The proposed method was tested three in\u2010silico and in\u2010vivo on two volunteers and three patients' data. For comparison purposes, various conventional phase\u2010based EPT reconstruction methods were used that ignore  magnitude information, such as Savitzky\u2013Golay kernel combined with Gaussian filter (S\u2010G Kernel), phase\u2010based convection\u2010reaction EPT (cr\u2010EPT), magnitude\u2010weighted polynomial\u2010fitting phase\u2010based EPT (Poly\u2010Fit), and integral\u2010based phase\u2010based EPT (Integral\u2010based). From the in\u2010silico experiments, quantitative analysis showed that the proposed method provides more accurate and improved quality (e.g., high structural preservation) conductivity maps compared to conventional reconstruction methods. Representatively, in the healthy brain in\u2010silico phantom experiment, the proposed method yielded mean conductivity values of 1.97\u2009\u00b1\u20090.20\u2009S\/m for CSF, 0.33\u2009\u00b1\u20090.04\u2009S\/m for WM, and 0.52\u2009\u00b1\u20090.08\u2009S\/m for GM, which were closer to the ground\u2010truth conductivity (2.00, 0.30, 0.50\u2009S\/m) than the integral\u2010based method (2.56\u2009\u00b1\u20092.31, 0.39\u2009\u00b1\u20090.12, 0.68\u2009\u00b1\u20090.33\u2009S\/m). In\u2010vivo ANN\u2010based conductivity reconstructions were also of improved quality compared to conventional reconstructions and demonstrated network generalizability and robustness to in\u2010vivo data and pathologies. The reported in\u2010vivo brain conductivity values were in agreement with literatures. In addition, the proposed method was observed for various SNR levels (SNR levels\u2009=\u200910, 20, 40, and 58) and repeatability conditions (the eight acquisitions with the number of signal averages\u2009=\u20091). The preliminary investigations on brain tumor patient datasets suggest that the network trained on simulated dataset can generalize to unforeseen in\u2010vivo pathologies, thus demonstrating its potential for clinical applications.<\/jats:p>","DOI":"10.1002\/hbm.26421","type":"journal-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T08:45:10Z","timestamp":1689756310000},"page":"4986-5001","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Data\u2010driven electrical conductivity brain imaging using\n                    <scp>3\u2009T MRI<\/scp>"],"prefix":"10.1002","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2842-1707","authenticated-orcid":false,"given":"Kyu\u2010Jin","family":"Jung","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering Yonsei University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4612-5509","authenticated-orcid":false,"given":"Stefano","family":"Mandija","sequence":"additional","affiliation":[{"name":"Computational Imaging Group for MR Therapy and Diagnostics University Medical Center Utrecht  Utrecht The Netherlands"},{"name":"Department of Radiotherapy University Medical Center Utrecht  Utrecht The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8927-8271","authenticated-orcid":false,"given":"Chuanjiang","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering Yonsei University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8382-0589","authenticated-orcid":false,"given":"Jun\u2010Hyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering Yonsei University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1548-965X","authenticated-orcid":false,"given":"Mohammed A.","family":"Al\u2010masni","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence College of Software &amp; Convergence Technology, Daeyang AI Center, Sejong University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5736-1038","authenticated-orcid":false,"given":"Thierry G.","family":"Meerbothe","sequence":"additional","affiliation":[{"name":"Computational Imaging Group for MR Therapy and Diagnostics University Medical Center Utrecht  Utrecht The Netherlands"},{"name":"Department of Radiotherapy University Medical Center Utrecht  Utrecht The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2005-7560","authenticated-orcid":false,"given":"Mina","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Radiology, Gangnam Severance Hospital Yonsei University College of Medicine  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5565-6889","authenticated-orcid":false,"given":"Cornelis A. T.","family":"van den Berg","sequence":"additional","affiliation":[{"name":"Computational Imaging Group for MR Therapy and Diagnostics University Medical Center Utrecht  Utrecht The Netherlands"},{"name":"Department of Radiotherapy University Medical Center Utrecht  Utrecht The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6717-7770","authenticated-orcid":false,"given":"Dong\u2010Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering Yonsei University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,7,19]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/tomography9010034"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2005.02.018"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/4\/1596"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2404944"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-016-1497-6"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25276"},{"key":"e_1_2_9_8_1","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia P. W.","year":"2018","journal-title":"arXiv Preprint"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-014-1762-2"},{"key":"e_1_2_9_10_1","first-page":"20","article-title":"Deepfit: 3D surface fitting via neural network weighted least squares","author":"Ben\u2010Shabat Y.","year":"2020","journal-title":"Proceedings of European Conference on Computer Vision"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-020-00383-y"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/55\/2\/N01"},{"key":"e_1_2_9_13_1","volume-title":"Proceedings of the International Society for Magnetic Resonance in Medicine, 2914","author":"Cui C.","year":"2022"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3522"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3139455"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/41\/11\/001"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/41\/11\/002"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/41\/11\/003"},{"key":"e_1_2_9_19_1","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume":"48","author":"Gal Y.","year":"2016","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28285"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2020.2991399"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28117"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/59\/18\/5287"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2017.2763590"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26097"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/36\/6\/002"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2296715"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab9356"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27453"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMTT.2017.2725830"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/1099-0534(2000)12:4<173::AID-CMR1>3.0.CO;2-Q"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1227\/NEU.0000000000000892"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3172220"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28826"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28407"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29192"},{"key":"e_1_2_9_38_1","volume-title":"Proceedings of the International Society for Magnetic Resonance in Medicine, 3775","author":"Karsa A.","year":"2021"},{"key":"e_1_2_9_39_1","volume-title":"Proceedings of the International Society for Magnetic Resonance in Medicine, 3774","author":"Karsa A.","year":"2021"},{"key":"e_1_2_9_40_1","volume-title":"Proceedings of the International Society for Magnetic Resonance in Medicine, 3336","author":"Katscher U.","year":"2016"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/546562"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2015757"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16195"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-015-4067-7"},{"key":"e_1_2_9_45_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kingma D. P.","year":"2015"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12600"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/52\/20\/002"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25891"},{"issue":"73","key":"e_1_2_9_50_1","first-page":"1","article-title":"In vivo electrical conductivity measurement of muscle, cartilage, and peripheral nerve around knee joint using MR\u2010electrical properties tomography","volume":"12","author":"Lee J. H.","year":"2022","journal-title":"Scientific Reports"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251417"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2361810"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2427236"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4211"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54717-7"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0071616"},{"key":"e_1_2_9_57_1","first-page":"1391","volume-title":"Measurement of T1 relaxation times at 3.0T: Implications for clinical MRA","author":"Lin C.","year":"2001"},{"key":"e_1_2_9_58_1","first-page":"9204","article-title":"Pay attention to MLPSs","volume":"34","author":"Liu H.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2017.2725140"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25434"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.20356"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-45382-x"},{"key":"e_1_2_9_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10548-020-00813-1"},{"key":"e_1_2_9_64_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27004"},{"key":"e_1_2_9_65_1","first-page":"2921","volume-title":"A semi\u2010realistic and reusable 3D printed brain phantom for MR\u2010based electrical properties tomography","author":"Meerbothe T. G.","year":"2022"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4895987"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5708-4"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27019"},{"key":"e_1_2_9_69_1","first-page":"8024","article-title":"PyTorch: An imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_2_9_71_1","first-page":"234","article-title":"U\u2010Net: Convolutional networks for biomedical image segmentation","volume":"18","author":"Ronneberger O.","year":"2015","journal-title":"Proceedings of the International Conference on Medical Image Computing and Computer\u2010Assisted Intervention"},{"key":"e_1_2_9_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.03.042"},{"key":"e_1_2_9_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2013.08.001"},{"key":"e_1_2_9_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmr.2015.11.002"},{"issue":"2","key":"e_1_2_9_75_1","first-page":"430","article-title":"Error analysis of nonconstant admittivity for MR\u2010based electric property imaging","volume":"31","author":"Seo J. K.","year":"2011","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_2_9_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2019.2907442"},{"key":"e_1_2_9_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-8415(02)00054-3"},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24803"},{"key":"e_1_2_9_79_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27528"},{"key":"e_1_2_9_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2004.07.051"},{"key":"e_1_2_9_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-017-0659-3"},{"key":"e_1_2_9_82_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20605"},{"key":"e_1_2_9_83_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27655"},{"key":"e_1_2_9_84_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117366"},{"key":"e_1_2_9_85_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-017-4942-5"},{"key":"e_1_2_9_86_1","volume-title":"Proceedings of the International Society for Magnetic Resonance in Medicine, 1885","author":"Tha K. K.","year":"2014"},{"key":"e_1_2_9_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01303-4"},{"key":"e_1_2_9_88_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/54\/5\/010"},{"key":"e_1_2_9_89_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22995"},{"key":"e_1_2_9_90_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.23322"},{"key":"e_1_2_9_91_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22832"},{"key":"e_1_2_9_92_1","article-title":"PIFON\u2010EPT: MR\u2010based electrical property tomography using physics\u2010informed Fourier networks","author":"Yu X.","year":"2023","journal-title":"arXiv Preprint"},{"key":"e_1_2_9_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2251653"}],"container-title":["Human Brain Mapping"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.26421","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/hbm.26421","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.26421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:55:16Z","timestamp":1781261716000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hbm.26421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,19]]},"references-count":92,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2023,10,15]]}},"alternative-id":["10.1002\/hbm.26421"],"URL":"https:\/\/doi.org\/10.1002\/hbm.26421","archive":["Portico"],"relation":{},"ISSN":["1065-9471","1097-0193"],"issn-type":[{"value":"1065-9471","type":"print"},{"value":"1097-0193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,19]]},"assertion":[{"value":"2023-02-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}