{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T20:24:43Z","timestamp":1793305483183,"version":"4.5.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Magnetic resonance imaging (MRI) is a cornerstone of neuroimaging but is limited by lengthy acquisition times, which can lead to motion artifacts, patient discomfort, and delayed care. Deep learning reconstruction is an emerging technology that can offer image acquisition acceleration while maintaining image quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To compare image quality and acquisition efficiency between deep learning\u2013accelerated vs conventional MRI (C-MRI) across a spectrum of routine neuroradiologic examinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>In this single-center retrospective study, 26 patients underwent imaging with a commercially available, FDA-cleared deep learning-accelerated MRI reconstruction algorithm (Deep Resolve, Siemens Healthineers), and C-MRI on a Siemens 3\u2009T MAGNETOM Vida scanner between October 24 and November 14, 2023. A total of 113 sequence pairs were acquired across multiple body parts (brain [n\u2009=\u200928], cervical spine [n\u2009=\u200924], thoracic spine [n\u2009=\u200916], lumbar spine [n\u2009=\u200914], internal auditory canals [n\u2009=\u20095], sella [n\u2009=\u20095], neck [n\u2009=\u20095], temporomandibular joints [n\u2009=\u20096], brachial plexus [n\u2009=\u20094], and orbits [n\u2009=\u20096]) and sequences (T2 [n\u2009=\u200938], T1 [n\u2009=\u200930], short tau inversion recovery [n\u2009=\u200921], T1 post-contrast [n\u2009=\u200917], T2 fluid attenuated inversion recovery [n\u2009=\u20095], and proton density [n\u2009=\u20092]) and evaluated by 4 neuroradiologists blinded to the acquisition method for image quality using a 5-point Likert scale. Acquisition parameters were extracted from Digital Imaging and Communications in Medicine (DICOM) metadata and statistically compared. Rater preferences and interrater reliability were assessed using nonparametric tests and intraclass correlation coefficients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Deep learning reduced mean scan time by 51.6% (95% CI: 45.7%\u201357.7%; from 110.8\u2009seconds to 53.7\u2009seconds; P &amp;lt; .001). Image quality assessments using a Likert scale showed scores slightly above neutral for signal-to-noise ratio (mean 3.51; 95% CI: 3.44\u20133.58), structural delineation (mean 3.51, 95% CI: 3.44\u20133.56), and overall image quality (mean 3.56, 95% CI: 3.49\u20133.63). However, poor interrater reliability (intraclass correlation [ICC] range: 0.06\u20130.33) showed that the observed differences were not consistent, indicating functional equivalence between conventional and deep learning images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Deep learning MRI enabled substantial scan time reductions while maintaining image quality.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/radadv\/umaf029","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:43:45Z","timestamp":1755863025000},"source":"Crossref","is-referenced-by-count":5,"title":["Deep learning MRI halves scan time and preserves image quality across routine neuroradiologic examinations"],"prefix":"10.1093","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5999-6194","authenticated-orcid":false,"given":"Shawn K","family":"Lyo","sequence":"first","affiliation":[{"name":"Department of Radiology, Hospital of the University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4025-115X","authenticated-orcid":false,"given":"Suyash","family":"Mohan","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hospital of the University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3435-4662","authenticated-orcid":false,"given":"Michael J","family":"Hoch","sequence":"additional","affiliation":[{"name":"Department of Radiology, Thomas Jefferson University Hospital , Philadelphia, PA 19107,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9266-7758","authenticated-orcid":false,"given":"Vivek P","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hospital of the University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1506-4141","authenticated-orcid":false,"given":"Robert M","family":"Kurtz","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hospital of the University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1292-5265","authenticated-orcid":false,"given":"Alvand","family":"Hassankhani","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hospital of the University of Pennsylvania , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,8,23]]},"reference":[{"issue":"9","key":"2025091915174713800_umaf029-B1","doi-asserted-by":"publisher","first-page":"e016391","DOI":"10.1136\/bmjopen-2017-016391","article-title":"Patient experience and perceived acceptability of whole-body magnetic resonance imaging for staging colorectal and lung cancer compared with current staging scans: a qualitative study","volume":"7","author":"Evans","year":"2017","journal-title":"BMJ Open"},{"issue":"8","key":"2025091915174713800_umaf029-B2","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.jacr.2010.05.002","article-title":"MRI: time is dose\u2014and money and versatility","volume":"7","author":"Edelstein","year":"2010","journal-title":"J Am Coll Radiol"},{"key":"2025091915174713800_umaf029-B3","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1016\/j.neuroimage.2018.04.044","article-title":"Challenges in pediatric neuroimaging","volume":"185","author":"Barkovich","year":"2019","journal-title":"NeuroImage"},{"key":"2025091915174713800_umaf029-B4","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/1471-2342-11-4","article-title":"Reduction of claustrophobia during magnetic resonance imaging: methods and design of the \u201cCLAUSTRO\u201d randomized controlled trial","volume":"11","author":"Enders","year":"2011","journal-title":"BMC Med Imaging"},{"issue":"3","key":"2025091915174713800_umaf029-B5","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1002\/jmri.26909","article-title":"MRI safety and devices: an update and expert consensus","volume":"51","author":"Jabehdar Maralani","year":"2020","journal-title":"Magnetic Resonance Imaging"},{"issue":"6","key":"2025091915174713800_umaf029-B6","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1002\/mrm.10171","article-title":"Generalized autocalibrating partially parallel acquisitions (GRAPPA)","volume":"47","author":"Griswold","year":"2002","journal-title":"Magn Reson Med"},{"issue":"8","key":"2025091915174713800_umaf029-B7","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.3174\/ajnr.A7140","article-title":"Simultaneous multislice for accelerating diffusion MRI in clinical neuroradiology protocols","volume":"42","author":"Hoch","year":"2021","journal-title":"AJNR Am J Neuroradiol"},{"issue":"12","key":"2025091915174713800_umaf029-B8","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1097\/RLI.0000000000000499","article-title":"Accelerated IAC screening MRI protocol with compressed sensing 3D T2-weighted sequence","volume":"53","author":"Yuhasz","year":"2018","journal-title":"Invest Radiol"},{"issue":"1056","key":"2025091915174713800_umaf029-B9","doi-asserted-by":"crossref","first-page":"20150487","DOI":"10.1259\/bjr.20150487","article-title":"Compressed sensing MRI: a review of the clinical literature","volume":"88","author":"Jaspan","year":"2015","journal-title":"Br J Radiol"},{"issue":"2","key":"2025091915174713800_umaf029-B10","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/MSP.2007.914728","article-title":"Compressed sensing MRI","volume":"25","author":"Lustig","year":"2008","journal-title":"IEEE Signal Process Mag"},{"issue":"4","key":"2025091915174713800_umaf029-B11","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1002\/jmri.27078","article-title":"Artificial intelligence for MR image reconstruction: an overview for clinicians","volume":"53","author":"Lin","year":"2021","journal-title":"J Magn Reson Imaging"},{"key":"2025091915174713800_umaf029-B12","doi-asserted-by":"crossref","first-page":"32","DOI":"10.37549\/AR2698","article-title":"Deep learning: promising to revolutionize image reconstruction","volume":"50","author":"Bash","year":"2021","journal-title":"AR"},{"issue":"6","key":"2025091915174713800_umaf029-B13","doi-asserted-by":"crossref","first-page":"e220133","DOI":"10.1148\/rg.220133","article-title":"Clinical impact of deep learning reconstruction in MRI","volume":"43","author":"Kiryu","year":"2023","journal-title":"Radiographics"},{"issue":"12","key":"2025091915174713800_umaf029-B14","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.3390\/diagnostics11122181","article-title":"Deep learning applications in magnetic resonance imaging: has the future become present?","volume":"11","author":"Gassenmaier","year":"2021","journal-title":"Diagnostics"},{"issue":"1","key":"2025091915174713800_umaf029-B15","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TMI.2018.2863670","article-title":"Convolutional recurrent neural networks for dynamic MR image reconstruction","volume":"38","author":"Qin","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"issue":"5","key":"2025091915174713800_umaf029-B16","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1002\/mrm.27201","article-title":"KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images","volume":"80","author":"Eo","year":"2018","journal-title":"Magn Reson Med"},{"issue":"2","key":"2025091915174713800_umaf029-B17","doi-asserted-by":"crossref","first-page":"e210059","DOI":"10.1148\/ryai.210059","article-title":"Clinical assessment of deep learning\u2013based super-resolution for 3D volumetric brain MRI","volume":"4","author":"Rudie","year":"2022","journal-title":"Radiol Artif Intell"},{"issue":"6","key":"2025091915174713800_umaf029-B18","doi-asserted-by":"crossref","first-page":"e210313","DOI":"10.1148\/ryai.210313","article-title":"Exploring the acceleration limits of deep learning variational network\u2013based two-dimensional brain MRI","volume":"4","author":"Radmanesh","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"2025091915174713800_umaf029-B19","doi-asserted-by":"crossref","first-page":"869","DOI":"10.3389\/fneur.2019.00869","article-title":"Applications of deep learning to neuro-imaging techniques","volume":"10","author":"Zhu","year":"2019","journal-title":"Front Neurol"},{"issue":"1","key":"2025091915174713800_umaf029-B20","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s00256-023-04390-9","article-title":"Fast high-quality MRI protocol of the lumbar spine with deep learning-based algorithm: an image quality and scanning time comparison with standard protocol","volume":"53","author":"Zerunian","year":"2024","journal-title":"Skeletal Radiol"},{"issue":"12","key":"2025091915174713800_umaf029-B21","doi-asserted-by":"publisher","first-page":"2130","DOI":"10.3174\/ajnr.A7358","article-title":"Deep learning enables 60% accelerated volumetric brain MRI while preserving quantitative performance: a prospective, multicenter, multireader trial","volume":"42","author":"Bash","year":"2021","journal-title":"Am J Neuroradiol"},{"issue":"11","key":"2025091915174713800_umaf029-B22","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.3174\/ajnr.A7664","article-title":"Accelerated synthetic MRI with deep learning\u2013based reconstruction for pediatric neuroimaging","volume":"43","author":"Kim","year":"2022","journal-title":"Am J Neuroradiol"},{"issue":"2","key":"2025091915174713800_umaf029-B23","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1111\/jon.13187","article-title":"Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality","volume":"34","author":"Estler","journal-title":"J Neuroimaging"},{"issue":"1","key":"2025091915174713800_umaf029-B24","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s00062-021-01121-2","article-title":"Deep learning image processing enables 40% faster spinal MR scans which match or exceed quality of standard of care: a prospective multicenter multireader study","volume":"32","author":"Bash","year":"2022","journal-title":"Clin Neuroradiol"},{"issue":"3","key":"2025091915174713800_umaf029-B25","doi-asserted-by":"publisher","first-page":"e212922","DOI":"10.1148\/radiol.212922","article-title":"Deep learning reconstruction for accelerated spine MRI: prospective analysis of interchangeability","volume":"306","author":"Almansour","year":"2023","journal-title":"Radiology"},{"issue":"12","key":"2025091915174713800_umaf029-B26","doi-asserted-by":"publisher","first-page":"8656","DOI":"10.1007\/s00330-023-09918-0","article-title":"Deep learning-based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI","volume":"33","author":"Yoo","year":"2023","journal-title":"Eur Radiol"},{"key":"2025091915174713800_umaf029-B27","first-page":"29","article-title":"Deep Resolve\u2014mobilizing the power of networks","volume":"1","author":"Behl","year":"2021","journal-title":"Magnetom Flash"},{"issue":"3","key":"2025091915174713800_umaf029-B28","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10278-018-0082-y","article-title":"The Orthanc ecosystem for medical imaging","volume":"31","author":"Jodogne","year":"2018","journal-title":"J Digit Imaging"},{"issue":"1","key":"2025091915174713800_umaf029-B29","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1148\/radiol.2020200723","article-title":"Thin-slice pituitary MRI with deep learning\u2013based reconstruction: diagnostic performance in a postoperative setting","volume":"298","author":"Kim","year":"2021","journal-title":"Radiology"},{"issue":"48","key":"2025091915174713800_umaf029-B30","doi-asserted-by":"crossref","first-page":"30088","DOI":"10.1073\/pnas.1907377117","article-title":"On instabilities of deep learning in image reconstruction and the potential costs of AI","volume":"117","author":"Antun","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"2025091915174713800_umaf029-B31","doi-asserted-by":"publisher","first-page":"23","DOI":"10.20982\/tqmp.08.1.p023","article-title":"Computing inter-rater reliability for observational data: an overview and tutorial","volume":"8","author":"Hallgren","year":"2012","journal-title":"Tutor Quant Methods Psychol"}],"container-title":["Radiology Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/radadv\/advance-article-pdf\/doi\/10.1093\/radadv\/umaf029\/64114534\/umaf029.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf029\/64114534\/umaf029.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf029\/64114534\/umaf029.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:17:55Z","timestamp":1758309475000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/radadv\/article\/doi\/10.1093\/radadv\/umaf029\/8240289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,23]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,4]]}},"URL":"https:\/\/doi.org\/10.1093\/radadv\/umaf029","relation":{},"ISSN":["2976-9337"],"issn-type":[{"value":"2976-9337","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,23]]},"article-number":"umaf029"}}