{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T22:45:42Z","timestamp":1789425942064,"version":"build-2803163510"},"reference-count":58,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"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":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Magnetic Resonance Imaging (MRI) enables non\u2010invasive assessment of brain abnormalities during early life development. Permanent magnet scanners operating in the neonatal intensive care unit (NICU) facilitate MRI of sick infants, but have long scan times due to lower signal\u2010to\u2010noise ratios (SNR) and limited receive coils. This work accelerates in\u2010NICU MRI with diffusion probabilistic generative models by developing a training pipeline accounting for these challenges.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We establish a novel training dataset of clinical, 1 Tesla neonatal MR images in collaboration with Aspect Imaging and Sha'are Zedek Medical Center. We propose a pipeline to handle the low quantity and SNR of our real\u2010world dataset (1) modifying existing network architectures to support varying resolutions; (2) training a single model on all data with learned class embedding vectors; (3) applying self\u2010supervised denoising before training; and (4) reconstructing by averaging posterior samples. Retrospective under\u2010sampling experiments, accounting for signal decay, evaluated each item of our proposed methodology. A clinical reader study with practicing pediatric neuroradiologists evaluated our proposed images reconstructed from  under\u2010sampled data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Combining all data, denoising pre\u2010training, and averaging posterior samples yields quantitative improvements in reconstruction. The generative model decouples the learned prior from the measurement model and functions at two acceleration rates without re\u2010training. The reader study suggests that proposed images reconstructed from  under\u2010sampled data are adequate for clinical use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Diffusion probabilistic generative models applied with the proposed pipeline to handle challenging real\u2010world datasets could reduce the scan time of in\u2010NICU neonatal MRI.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mrm.30585","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:50:20Z","timestamp":1750215020000},"page":"1546-1562","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diffusion probabilistic generative models for accelerated, in\u2010NICU permanent magnet neonatal MRI"],"prefix":"10.1002","volume":"94","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2194-1945","authenticated-orcid":false,"given":"Yamin","family":"Arefeen","sequence":"first","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin  Austin Texas USA"},{"name":"Department of Imaging Physics MD Anderson Cancer Center  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1182-3438","authenticated-orcid":false,"given":"Brett","family":"Levac","sequence":"additional","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin  Austin Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhairav","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Medicine The University of Texas at Austin Dell Medical School  Austin Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Ho","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Medicine The University of Texas at Austin Dell Medical School  Austin Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan I.","family":"Tamir","sequence":"additional","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin  Austin Texas USA"},{"name":"Department of Diagnostic Medicine The University of Texas at Austin Dell Medical School  Austin Texas USA"},{"name":"Oden Institute for Computational Engineering and Sciences The University of Texas at Austin  Austin Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27192"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.earlhumdev.2008.09.004"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(09)70257-1"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa053792"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A3521"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41372-022-01387-5","article-title":"Clinical experience with an in\u2010nicu magnetic resonance imaging system","volume":"42","author":"Thiim K","year":"2022","journal-title":"Journal Of Perinatology"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2020.07.079"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-012-2444-9"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.13.10613"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1055\/a-1926-2238"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A3128"},{"key":"e_1_2_9_13_1","first-page":"260","article-title":"Transport, monitoring, and successful brain MR imaging in unsedated neonates","volume":"37","author":"Mathur AM","year":"2007","journal-title":"Pediatric Radiology"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26644"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24850"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.23639"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21391"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.10091218"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","DOI":"10.1109\/MSP.2010.936726","article-title":"Model\u2010based image reconstruction for MRI","volume":"27","author":"Fessler JA","year":"2010","journal-title":"IEEE Signal Process Mag"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-024-01173-8"},{"key":"e_1_2_9_21_1","first-page":"514","article-title":"Accelerating magnetic resonance imaging via deep learning","author":"Wang S","year":"2016","journal-title":"IEEE International Symposium on Biomedical Imaging"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3075856"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2865356"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26977"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2887072"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28274"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102479"},{"key":"e_1_2_9_28_1","unstructured":"Song Yang Sohl\u2010Dickstein Jascha Kingma Diederik P. Kumar Abhishek Ermon Stefano Poole Ben.Score\u2010based generative modeling through stochastic differential equations 2021."},{"key":"e_1_2_9_29_1","first-page":"26565","article-title":"Elucidating the design space of diffusion\u2010based generative models","volume":"35","author":"Karras T","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"e_1_2_9_30_1","unstructured":"ChungH KimJ McCannMT KlaskyML YeJC.Diffusion posterior sampling for general noisy inverse problems.2023."},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29624"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2017.00685"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28408"},{"key":"e_1_2_9_34_1","first-page":"3978","article-title":"Diffusion probabilistic generative models for accelerated in\u2010nicu, permanent magnet neonatal MRI reconstruction","volume":"33","author":"Arefeen Y","year":"2025","journal-title":"Process of the Int Soc of Magn Reson Med."},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"e_1_2_9_36_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho J","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"e_1_2_9_38_1","first-page":"14938","article-title":"Robust compressed sensing MRI with deep generative priors","volume":"34","author":"Jalal A","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.1985.4307722"},{"key":"e_1_2_9_40_1","first-page":"30018","article-title":"Robustness of deep learning for accelerated MRI: Benefits of diverse training data","volume":"1210","author":"Kang L","year":"2024","journal-title":"International Conference on Machine Learning"},{"key":"e_1_2_9_41_1","article-title":"Enhancing deep learning\u2010driven multi\u2010coil MRI reconstruction via self\u2010supervised denoising","volume":"2411","author":"Aali A","year":"2024","journal-title":"arXiv"},{"key":"e_1_2_9_42_1","first-page":"12061","article-title":"Noisier2noise: Learning to denoise from unpaired noisy data","author":"Moran N","year":"2020","journal-title":"Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_9_43_1","first-page":"233","volume-title":"Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2010MICCAI","author":"Rajput J","year":"2024"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16446-0_67"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2117203119"},{"key":"e_1_2_9_46_1","first-page":"2486","article-title":"Berkeley advanced reconstruction toolbox","volume":"23","author":"Uecker M","year":"2015","journal-title":"Process of the Int Soc of Magn Reson Med."},{"key":"e_1_2_9_47_1","article-title":"ContextMRI: Enhancing compressed sensing MRI through metadata conditioning","author":"Chung H","year":"2025","journal-title":"arXiv"},{"key":"e_1_2_9_48_1","volume-title":"Int. Conf. Learn. Rep (ICLR)","author":"Hu EJ","year":"2022"},{"key":"e_1_2_9_49_1","first-page":"1198","article-title":"Training diffusion probabilistic models with limited data for accelerated MRI reconstruction with application to stroke MRI","volume":"33","author":"Kumar S","year":"2025","journal-title":"Process of the Int Soc of Magn Reson Med."},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30100"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF59524.2023.10476746"},{"key":"e_1_2_9_52_1","first-page":"21","article-title":"Diffusion posterior sampling is computationally intractable","volume":"235","author":"Gupta S","year":"2024","journal-title":"Int. Conf. Mach. Learn."},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28991"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30082"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2949470"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2880326"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2024.3449101"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2998402"},{"key":"e_1_2_9_59_1","volume-title":"Int. Conf. Learn. Rep (ICLR)","author":"Zheng H","year":"2025"}],"container-title":["Magnetic Resonance in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.30585","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mrm.30585","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.30585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T22:56:14Z","timestamp":1777762574000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/mrm.30585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1002\/mrm.30585"],"URL":"https:\/\/doi.org\/10.1002\/mrm.30585","archive":["Portico"],"relation":{},"ISSN":["0740-3194","1522-2594"],"issn-type":[{"value":"0740-3194","type":"print"},{"value":"1522-2594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]},"assertion":[{"value":"2025-02-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}