{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:48:30Z","timestamp":1792054110431,"version":"4.4.0"},"reference-count":27,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["NMR in Biomedicine"],"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Commonly occurring fat\u2010water swap artifacts in multi\u2010echo MRI hinder accurate estimation of the clinical biomarker, proton density fat fraction (PDFF). This study evaluates a novel physics\u2010informed deep learning (PI\u2010DL) model to correct these swap artifacts. The proposed PI\u2010DL model, the \u201cSwap\u2010Net,\u201d utilizes a branch\u2010constrained optimization method to explore different bifurcate regions in the residual function optimized, thereby increasing the probability of reaching global minima, as the swap artifacts are caused by the optimization routine settling into a local minimum. Performance evaluation was conducted using multi\u2010echo MRI of 37 (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200937) subjects, and this included a cohort of 23 (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u200923) high\u2010resolution MRIs. The proprietary mDixon Quant sequence, with optimized parameter settings for accurate liver fat quantification, served as the clinical standard for benchmarking performance. The results of the quantitative evaluations revealed that the average liver PDFF% from the proposed Swap\u2010Net demonstrated excellent agreement with the clinical standard mDixon Quant (correlation coefficient\n                    <jats:italic>R<\/jats:italic>\n                    of 0.98 in the high\u2010resolution cohort). The qualitative evaluations also showed that the fat\u2010water maps from the Swap\u2010Net contained no swap artifacts. In contrast, other state\u2010of\u2010the\u2010art methods exhibited swap artifacts, particularly in high\u2010resolution MRI. The proposed Swap\u2010Net corrected swap artifacts in MRI\u2010based fat quantification, particularly in high\u2010resolution MRI, enabling high\u2010resolution fat\u2010water imaging.\n                  <\/jats:p>","DOI":"10.1002\/nbm.70413","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T07:51:57Z","timestamp":1790668317000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fat\u2010Water Swap Artifact Correction in MRI\u2010Based Fat Quantification Using Physics\u2010Informed Deep Learning With Branch Constrained Optimization"],"prefix":"10.1002","volume":"39","author":[{"given":"Moorthy","family":"Ganeshkumar","sequence":"first","affiliation":[{"name":"Centre for Biomedical Engineering Indian Institute of Technology Delhi  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8615-4937","authenticated-orcid":false,"given":"Devasenathipathy","family":"Kandasamy","sequence":"additional","affiliation":[{"name":"Department of Radio Diagnosis All India Institute of Medical Sciences  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Shalimar","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology All India Institute of Medical Sciences  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somil","family":"Anshal","sequence":"additional","affiliation":[{"name":"Department of Radio Diagnosis All India Institute of Medical Sciences  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3075-5121","authenticated-orcid":false,"given":"Rajnandini","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Department of Radio Diagnosis All India Institute of Medical Sciences  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raju","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Radio Diagnosis All India Institute of Medical Sciences  New Delhi India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-2462","authenticated-orcid":false,"given":"Amit","family":"Mehndiratta","sequence":"additional","affiliation":[{"name":"Centre for Biomedical Engineering Indian Institute of Technology Delhi  New Delhi India"},{"name":"Yardi School of Artificial Intelligence Indian Institute of Technology Delhi  New Delhi India"},{"name":"Faculty of Medicine and Health University of New South Wales (UNSW)  Sydney Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"e_1_2_15_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24568"},{"key":"e_1_2_15_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29860"},{"key":"e_1_2_15_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pnmrs.2013.04.001"},{"key":"e_1_2_15_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20654"},{"key":"e_1_2_15_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27728"},{"key":"e_1_2_15_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22177"},{"key":"e_1_2_15_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29175"},{"key":"e_1_2_15_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26485"},{"key":"e_1_2_15_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28546"},{"key":"e_1_2_15_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29525"},{"key":"e_1_2_15_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30045"},{"key":"e_1_2_15_13_1","unstructured":"B.Yaman S. A. H.Hosseini andM.Ak\u00e7akaya \u201cZero\u2010Shot Self\u2010Supervised Learning for MRI Reconstruction \u201d (2021):https:\/\/doi.org\/10.48550\/ARXIV.2102.07737."},{"key":"e_1_2_15_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.70216"},{"key":"e_1_2_15_15_1","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2025-bac4"},{"key":"e_1_2_15_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010015\u20103703\u20106"},{"key":"e_1_2_15_17_1","unstructured":"N. V.Koninklijke Philips \u201cHigh Accuracy Non\u2010Invasive Fat Fraction Quantification: Philips mDIXON Quant for 1.5T and 3.0T Systems \u201d Koninklijke Philips N.V. Technical document (2015). [Online]. Available:https:\/\/www.documents.philips.com\/assets\/20170523\/0f43ba9c51ea4a3c9c95a77c014e0056.pdf."},{"key":"e_1_2_15_18_1","unstructured":"T. G.Perkins A.Duijndam H.Eggers E.deWeerdt andY. H. E.Rijckaert \u201cmDIXON XD: The Next Generation Fat\u2010Free Imaging \u201d Koninklijke Philips N.V. Technical Note Oct. 2015. [Online]. Available:https:\/\/www.documents.philips.com\/assets\/20180126\/1e42bcf9b1934fc597fea87400c078a8.pdf."},{"key":"e_1_2_15_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28701"},{"key":"e_1_2_15_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28515"},{"key":"e_1_2_15_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26228"},{"key":"e_1_2_15_22_1","doi-asserted-by":"publisher","DOI":"10.1364\/AO.41.007437"},{"key":"e_1_2_15_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24775"},{"key":"e_1_2_15_24_1","doi-asserted-by":"publisher","DOI":"10.18383\/j.tom.2017.00011"},{"key":"e_1_2_15_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00261\u2010024\u201004698\u20107"},{"key":"e_1_2_15_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.12901"},{"key":"e_1_2_15_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4156"},{"key":"e_1_2_15_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24441"}],"container-title":["NMR in Biomedicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nbm.70413","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/nbm.70413","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nbm.70413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:21:52Z","timestamp":1792052512000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/nbm.70413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":27,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1002\/nbm.70413"],"URL":"https:\/\/doi.org\/10.1002\/nbm.70413","archive":["Portico"],"relation":{},"ISSN":["0952-3480","1099-1492"],"issn-type":[{"value":"0952-3480","type":"print"},{"value":"1099-1492","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"assertion":[{"value":"2026-06-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70413"}}