{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:39:33Z","timestamp":1783021173648,"version":"3.54.6"},"reference-count":26,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101021218"],"award-info":[{"award-number":["101021218"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["18981"],"award-info":[{"award-number":["18981"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance in Med"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Ultra\u2010low\u2010field (ULF) MRI provides a cost\u2010effective, portable imaging option but has relatively low SNR and long acquisition times compared to standard clinical scans. This study presents a time\u2010conditioned zero\u2010shot self\u2010supervised learning image reconstruction framework (ULF\u2010ZS\u2010SSL) to accelerate 3D\u2010acquired single\u2010coil ULF MRI without relying on external training data. In addition, for faster computation, a transfer\u2010learning (TL) variant (ULF\u2010ZS\u2010SSL\u2010TL) was implemented by pretraining on a small fully\u2010sampled ULF brain dataset and fine\u2010tuning on the target subject in a zero\u2010shot manner.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This image reconstruction method combines a physics\u2010based data\u2010consistency step with a 3D residual network prior and sinusoidal time\u2010step embeddings to improve convergence speed. Data were acquired on a 47 mT Halbach\u2010based scanner using 3D turbo spin\u2010echo sequences with T\n                      <jats:sub>1<\/jats:sub>\n                      \u2010, T\n                      <jats:sub>2<\/jats:sub>\n                      \u2010, and inversion\u2010recovery\u2013T\n                      <jats:sub>1<\/jats:sub>\n                      \u2010weighted contrasts. Additional T\n                      <jats:sub>1<\/jats:sub>\n                      \u2010weighted wrist scans were acquired to evaluate cross\u2010anatomy generalization. Both true and retrospectively undersampled data were compared with total variation (TV) and model\u2010based deep learning (MoDL).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The ULF\u2010ZS\u2010SSL method produced high\u2010quality reconstructions across all tested contrasts, outperforming zero\u2010filled and TV reconstructions, particularly at higher acceleration factors. Time\u2010step conditioning improved convergence speed, while ULF\u2010ZS\u2010SSL\u2010TL further accelerated the image reconstruction three\u2010fold, enabling full 3D reconstructions in about 3\u2009min. Pretraining on brain data also worked well for wrist reconstructions, indicating cross\u2010anatomy generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The ULF\u2010ZS\u2010SSL framework enables accurate, training\u2010free reconstruction of undersampled single\u2010coil ULF MRI data, as does the ULF\u2010ZS\u2010SSL\u2010TL approach using minimal training data. The combination of physics\u2010based unrolling, time\u2010step conditioning, and transfer\u2010learning supports rapid and robust application in portable or resource\u2010limited ULF MRI systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mrm.70407","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T05:15:42Z","timestamp":1777439742000},"page":"1303-1312","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Time\u2010Conditioned Zero\u2010Shot Self\u2010Supervised Reconstruction for Accelerated\n                    <scp>3D<\/scp>\n                    Ultra\u2010Low\u2010Field\n                    <scp>MRI<\/scp>"],"prefix":"10.1002","volume":"96","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3310-0224","authenticated-orcid":false,"given":"Mart W. J.","family":"van Straten","sequence":"first","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"},{"name":"Department of Biomedical Engineering Eindhoven University of Technology  Eindhoven the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9283-5918","authenticated-orcid":false,"given":"Beatrice","family":"Lena","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7804-2281","authenticated-orcid":false,"given":"Chlo\u00e9","family":"Najac","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruben","family":"van den Broek","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"B\u00f6rnert","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"},{"name":"Philips Innovative Technologies Hamburg  Hamburg Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Webb","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8580-4555","authenticated-orcid":false,"given":"Yiming","family":"Dong","sequence":"additional","affiliation":[{"name":"C.J. Gorter MRI Center, Department of Radiology LUMC  Leiden the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28408"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00641-5"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28396"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26942"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26637"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30442"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1241"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1522\u20102594(199911)42:5<952::AID\u2010MRM16>3.0.CO;2\u2010S"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.10171"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21391"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adm7168"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30104"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334\u2010024\u201001173\u20108"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2865356"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26977"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29642"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201021806\u20109"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2024.3396223"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/MRM.28378"},{"key":"e_1_2_10_21_1","unstructured":"B.Yaman S. A. H.Hosseini andM.Ak\u00e7akaya \u201cZero\u2010Shot Self\u2010Supervised Learning for MRI Reconstruction \u201d(2022) Preprint."},{"key":"e_1_2_10_22_1","unstructured":"J.Yun Y. U.Alcalar andM.Akcakaya \u201cTime\u2010Embedded Algorithm Unrolling for Computational MRI \u201d(2025) In Proceedings of the Thirty\u2010Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)."},{"key":"e_1_2_10_23_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et al. \u201cAttention is All You Need \u201dIn Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17) (2017) Curran Associates Inc. (Red Hook NY USA) 6000\u20136010."},{"key":"e_1_2_10_24_1","unstructured":"J.Ho A.Jain andP.Abbeel \u201cDenoising Diffusion Probabilistic Models \u201d(2020) ArXiv abs\/2006.11239."},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190007"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334\u2010025\u201001311\u2010w"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmr.2024.107812"}],"container-title":["Magnetic Resonance in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.70407","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mrm.70407","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.70407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:38:24Z","timestamp":1783017504000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/mrm.70407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/mrm.70407"],"URL":"https:\/\/doi.org\/10.1002\/mrm.70407","archive":["Portico"],"relation":{},"ISSN":["0740-3194","1522-2594"],"issn-type":[{"value":"0740-3194","type":"print"},{"value":"1522-2594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]},"assertion":[{"value":"2025-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}