{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:21:06Z","timestamp":1788153666966,"version":"build-2803163510"},"reference-count":23,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance in Med"],"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a unified image reconstruction framework that bridges real\u2010time and gated cardiac MRI, including quantitative MRI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We introduce generative multitasking, which learns subject\u2010 and dataset\u2010specific implicit neural temporal bases from sequence timings and an interpretable latent space for cardiac and respiratory motion. Cardiac motion is modeled as a complex harmonic, with phase encoding timing and a latent amplitude capturing beat\u2010to\u2010beat functional variability, linking cardiac phase\u2010resolved (\u201cgated\u2010like\u201d) and time\u2010resolved (\u201creal\u2010time\u2010like\u201d) views. We implemented the framework using a conditional variational autoencoder (CVAE) and evaluated it for free\u2010breathing, non\u2010ECG\u2010gated radial GRE in three settings: steady\u2010state cine imaging, multicontrast T2prep\/inversion\u2010recovery imaging, and dual\u2010flip\u2010angle T1\/T2 mapping, compared with conventional multitasking.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Generative multitasking provided flexible cardiac motion representation, enabling reconstruction of archetypal cardiac phase\u2010resolved cines (like gating) as well as time\u2010resolved series that reveal beat\u2010to\u2010beat variability (like real\u2010time imaging). Conditioning on the previous k\u2010space angle and modifying this term at inference removed eddy\u2010current artifacts without globally smoothing high temporal frequencies. For quantitative mapping, generative multitasking reduced intraseptal T1 and T2 coefficients of variation (CoV) compared with conventional multitasking (T1: 0.13 vs. 0.31; T2: 0.12 vs. 0.32;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001), indicating higher SNR.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Generative multitasking uses a CVAE with complex harmonic cardiac coordinates to unify gated and real\u2010time CMR within a single free\u2010breathing, non\u2010ECG\u2010gated acquisition. The framework allows flexible cardiac motion representation, suppresses trajectory\u2010dependent artifacts, and improves T1 and T2 mapping, suggesting a path toward cine, multicontrast, and quantitative imaging without separate gated and real\u2010time scans.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mrm.70509","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T20:07:43Z","timestamp":1784059663000},"page":"2440-2450","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative\n                    <scp>MR<\/scp>\n                    Multitasking With Complex\u2010Harmonic Cardiac Encoding: Bridging the Gap Between Gated Imaging and Real\u2010Time Imaging"],"prefix":"10.1002","volume":"96","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1070-354X","authenticated-orcid":false,"given":"Xinguo","family":"Fang","sequence":"first","affiliation":[{"name":"Department of Radiological Sciences David Geffen School of Medicine at UCLA  Los Angeles California USA"},{"name":"Department of Bioengineering University of California, Los Angeles  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9334-8684","authenticated-orcid":false,"given":"Anthony G.","family":"Christodoulou","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences David Geffen School of Medicine at UCLA  Los Angeles California USA"},{"name":"Department of Bioengineering University of California, Los Angeles  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2412041866"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2022.100404"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocmr.2024.100997"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocmr.2024.100998"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0217-y"},{"key":"e_1_2_8_7_1","unstructured":"D.Abraham M.Nishimura X.Cao C.Liao andK.Setsompop \u201cImplicit Representation of GRAPPA Kernels for Fast MRI Reconstruction \u201d(2023) arXiv Preprint arXiv:2310.10823."},{"key":"e_1_2_8_8_1","doi-asserted-by":"crossref","unstructured":"V.Spieker H.Eichhorn W.Huang et al. \u201cPISCO: Self\u2010Supervised k\u2010Space Regularization for Improved Neural Implicit k\u2010Space Representations of Dynamic MRI \u201d(2025) arXiv Preprint arXiv:2501.09403.","DOI":"10.1016\/j.media.2025.103890"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109467"},{"key":"e_1_2_8_10_1","first-page":"3483","article-title":"Learning Structured Output Representation Using Deep Conditional Generative Models","volume":"28","author":"Sohn K.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims.2017.03.02"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20527"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2985994"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.21479"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10030345"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26381"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28642"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.29425"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.5091"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25665"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2020.02.005"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.29206"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29521"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27898"}],"container-title":["Magnetic Resonance in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.70509","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mrm.70509","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.70509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T04:52:20Z","timestamp":1788151940000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/mrm.70509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":23,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1002\/mrm.70509"],"URL":"https:\/\/doi.org\/10.1002\/mrm.70509","archive":["Portico"],"relation":{},"ISSN":["0740-3194","1522-2594"],"issn-type":[{"value":"0740-3194","type":"print"},{"value":"1522-2594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"2025-11-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}