{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:54:06Z","timestamp":1792155246178,"version":"4.4.0"},"reference-count":59,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF\u20102022R1A4A1030579"],"award-info":[{"award-number":["NRF\u20102022R1A4A1030579"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS\u20102024\u201000349509"],"award-info":[{"award-number":["RS\u20102024\u201000349509"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019211","name":"Institute of Engineering Research, Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019211","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":[[2025,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Magnetic susceptibility source separation (\n                    <jats:italic>\u03c7<\/jats:italic>\n                    \u2010separation), an advanced quantitative susceptibility mapping (QSM) method, enables the separate estimation of paramagnetic and diamagnetic susceptibility source distributions in the brain. Similar to QSM, it requires solving the ill\u2010conditioned problem of dipole inversion, suffering from so\u2010called streaking artifacts. Additionally, the method utilizes reversible transverse relaxation () to complement frequency shift information for estimating susceptibility source concentrations, requiring time\u2010consuming data acquisition for  (e.g., multi\u2010echo spin\u2010echo) in addition to multi\u2010echo GRE data for . To address these challenges, we develop a new deep learning network,\n                    <jats:italic>\u03c7<\/jats:italic>\n                    \u2010sepnet, and propose two deep learning\u2010based susceptibility source separation pipelines,\n                    <jats:italic>\u03c7<\/jats:italic>\n                    \u2010sepnet\u2010 for inputs with multi\u2010echo GRE and multi\u2010echo spin\u2010echo (or turbo spin\u2010echo) and\n                    <jats:italic>\u03c7\u2010<\/jats:italic>\n                    sepnet\u2010 for input with multi\u2010echo GRE only. The neural network is trained using multiple head orientation data that provide streaking artifact\u2010free labels, generating high\u2010quality\n                    <jats:italic>\u03c7<\/jats:italic>\n                    \u2010separation maps. The evaluation of the pipelines encompasses both qualitative and quantitative assessments in healthy subjects, and visual inspection of lesion characteristics in multiple sclerosis patients. The susceptibility source\u2010separated maps of the proposed pipelines delineate detailed brain structures with substantially reduced artifacts compared to those from the conventional regularization\u2010based reconstruction methods. In quantitative analysis,\n                    <jats:italic>\u03c7<\/jats:italic>\n                    \u2010sepnet\u2010 achieves the best outcomes followed by\n                    <jats:italic>\u03c7\u2010<\/jats:italic>\n                    sepnet\u2010, outperforming the conventional methods. When the lesions of multiple sclerosis patients are classified into subtypes, most lesions are identified as the same subtype in the maps from\n                    <jats:italic>\u03c7\u2010<\/jats:italic>\n                    sepnet\u2010 and\n                    <jats:italic>\u03c7\u2010<\/jats:italic>\n                    sepnet\u2010 (paramagnetic susceptibility: 99.6% and diamagnetic susceptibility: 98.4%; both out of 250 lesions). The\n                    <jats:italic>\u03c7\u2010<\/jats:italic>\n                    sepnet\u2010 pipeline, which only requires multi\u2010echo GRE data, has demonstrated its potential to offer broad clinical and scientific applications, although further evaluations for various diseases and pathological conditions are necessary.\n                  <\/jats:p>","DOI":"10.1002\/hbm.70136","type":"journal-article","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T07:43:57Z","timestamp":1737445437000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["<scp>\n                      <i>\u03c7<\/i>\n                    <\/scp>\n                    \u2010sepnet: Deep Neural Network for Magnetic Susceptibility Source Separation"],"prefix":"10.1002","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2104-4734","authenticated-orcid":false,"given":"Minjun","family":"Kim","sequence":"first","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1644-6560","authenticated-orcid":false,"given":"Sooyeon","family":"Ji","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"},{"name":"Division of Computer Engineering Hankuk University of Foreign Studies  Yongin Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6891-6520","authenticated-orcid":false,"given":"Jiye","family":"Kim","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7614-2089","authenticated-orcid":false,"given":"Kyeongseon","family":"Min","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5711-4290","authenticated-orcid":false,"given":"Hwihun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4902-5171","authenticated-orcid":false,"given":"Jonghyo","family":"Youn","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2257-7120","authenticated-orcid":false,"given":"Taechang","family":"Kim","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3386-1208","authenticated-orcid":false,"given":"Jinhee","family":"Jang","sequence":"additional","affiliation":[{"name":"Department of Radiology Seoul St Mary's Hospital, College of Medicine, The Catholic University of Korea  Seoul Republic of Korea"},{"name":"Institute for Precision Health University of California  Irvine California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9080-7865","authenticated-orcid":false,"given":"Berkin","family":"Bilgic","sequence":"additional","affiliation":[{"name":"Massachusetts General Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7876-173X","authenticated-orcid":false,"given":"Hyeong\u2010Geol","family":"Shin","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"},{"name":"F.M. Kirby Research Center for Functional Brain Imaging Kennedy Krieger Institute  Baltimore Maryland USA"},{"name":"Russell H. Morgan Department of Radiology and Radiological Science The Johns Hopkins University School of Medicine  Baltimore Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-5434","authenticated-orcid":false,"given":"Jongho","family":"Lee","sequence":"additional","affiliation":[{"name":"Laboratory for Imaging Science and Technology, Department of Electrical and Computer Engineering Seoul National University  Seoul Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,1,21]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.1534"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28331"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.03.060"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118477"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/jnr.490310111"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21710"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(87)91361-4"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/jon.13014"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28563"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2016.11.020"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmr.2021.107033"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0911177107"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A5927"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A8488"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.5167"},{"key":"e_1_2_9_17_1","unstructured":"Ji S. J.Park H.\u2010G.Shin J.Youn M.Kim andJ.Lee.2023.\u201cSuccessfulgeneralization for Data With Higher or Lower Resolution Than Training Data Resolution in Deep Learning Powered QSM Reconstruction \u201dJoint Annual Meeting ISMRM\u2010ESMRMB & ISMRT 32nd Annual Meeting Toronto Canada."},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4292"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.116619"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2024.120676"},{"key":"e_1_2_9_21_1","unstructured":"Kim M. H.\u2010G.Shin C.Oh et\u00a0al.2022.\u201cChi\u2010Sepnet: Susceptibility Source Separation Using Deep Neural Network \u201dJoint Annual Meeting ISMRM\u2010ESMRMB & ISMRT 31st Annual Meeting London UK."},{"key":"e_1_2_9_22_1","unstructured":"Kim T. S.Ji K.Min et\u00a0al.2024.\u201cPhysics\u2010Informed Vessel Segmentation for \u03c7\u2010Separation (Chi\u2010Separation).\u201dJoint Annual Meeting ISMRM\u2010ESMRMB & ISMRT 33rd Annual Meeting Singapore."},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.220941"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22487"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0910222107"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.2463\/mrms.rev.2024-0001"},{"key":"e_1_2_9_27_1","unstructured":"Lee J. Y.Nam J. Y.Choi H. G.Shin T.Hwang andJ.Lee.2017.\u201cSeparating Positive and Negative Susceptibility Sources in QSM.\u201dInProceedings of the ISMRM 25th Annual Meeting & Exhibition 22\u201327."},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.04.026"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2023.120058"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.12.043"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2023.120148"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22816"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21828"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26946"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1097\/00019052-199906000-00010"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.05.079"},{"key":"e_1_2_9_37_1","unstructured":"Min K. B.Sohn W. J.Kim et\u00a0al.2023.\u201cA Human Brain Atlas of Chi\u2010Separation for Normative Iron and Myelin Distributions.\u201darXiv preprint arXiv:2311.04468."},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106371"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000209604"},{"key":"e_1_2_9_40_1","volume-title":"Imaging of the Brain E\u2010Book: Expert Radiology Series","author":"Naidich T. P.","year":"2012"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2024.107135"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.01.051"},{"key":"e_1_2_9_43_1","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_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25137"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30006"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22753"},{"key":"e_1_2_9_47_1","volume-title":"Atlas for Stereotaxy of the Human Brain","author":"Schaltenbrand G.","year":"1977"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.10.070"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118371"},{"key":"e_1_2_9_50_1","unstructured":"Shin H.\u2010G. J.Seo Y.Lee et\u00a0al.2022.\u201cChi\u2010Separation Using Multi\u2010Orientation Data in Invivo and Exvivo Brains: Visualization of Histology up to the Resolution of 350\u2009\u03bcm.\u201dInProceedings of the 30th Annual ISMRM Meeting London."},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22135"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2004.07.051"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.02.026"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A7920"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25358"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(07)70216-8"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.07.019"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.23000"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2018.06.030"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.29266"}],"container-title":["Human Brain Mapping"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.70136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T03:32:39Z","timestamp":1739244759000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hbm.70136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1002\/hbm.70136"],"URL":"https:\/\/doi.org\/10.1002\/hbm.70136","archive":["Portico"],"relation":{},"ISSN":["1065-9471","1097-0193"],"issn-type":[{"value":"1065-9471","type":"print"},{"value":"1097-0193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,21]]},"assertion":[{"value":"2024-09-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70136"}}