{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:36:19Z","timestamp":1784136979322,"version":"3.55.0"},"reference-count":40,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2023,5]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>An inherently poor signal\u2010to\u2010noise ratio (SNR) causes inaccuracy and less precision in cerebral blood flow (CBF) and arterial transit time (ATT) when using arterial spin labeling (ASL). Deep neural network (DNN)\u2010based parameter estimation can solve these problems.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To reduce the effects of Rician noise on ASL parameter estimation and compute unbiased CBF and ATT using simulation\u2010based supervised DNNs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Study Type<\/jats:title><jats:p>Retrospective.<\/jats:p><\/jats:sec><jats:sec><jats:title>Population<\/jats:title><jats:p>One million simulation test data points, 17 healthy volunteers (five women and 12 men, 33.2\u2009\u00b1\u200914.6\u2009years of age), and one patient with moyamoya disease.<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>3.0 T\/Hadamard\u2010encoded pseudo\u2010continuous <jats:styled-content style=\"fixed-case\">ASL<\/jats:styled-content> with a three\u2010dimensional fast spin\u2010echo stack of spirals.<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>Performances of DNN and conventional methods were compared. For test data, the normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) between the ground truth and predicted values were evaluated. For in vivo data, baseline CBF and ATT and their relative changes with respect to SNR using artificial noise\u2010added images were assessed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p>One\u2010way analysis of variance with post\u2010hoc Tukey's multiple comparison test, paired <jats:italic>t<\/jats:italic>\u2010test, and the Bland\u2013Altman graphical analysis. Statistical significance was defined as <jats:italic>P<\/jats:italic>\u2009&lt;\u20090.05.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>For both CBF and ATT, NMAE and NRMSE were lower with DNN than with the conventional method. The baseline values were significantly smaller with DNN than with the conventional method (CBF in gray matter, 66\u2009\u00b1\u200910 vs. 71\u2009\u00b1\u200912\u2009mL\/100\u2009g\/min; white matter, 45\u2009\u00b1\u20096 vs. 46\u2009\u00b1\u20097\u00a0mL\/100\u2009g\/min; ATT in gray matter, 1424\u2009\u00b1\u2009201 vs. 1471\u2009\u00b1\u2009154\u2009msec). CBF and ATT increased with decreasing SNR; however, their change rates were smaller with DNN than were those with the conventional method. Higher CBF in the prolonged ATT region and clearer contrast in ATT were identified by DNN in a clinical case.<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusion<\/jats:title><jats:p>DNN outperformed the conventional method in terms of accuracy, precision, and noise immunity.<\/jats:p><jats:p>Evidence Level: 3<\/jats:p><jats:p>Technical Efficacy: Stage 1<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.28433","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T14:56:45Z","timestamp":1664377005000},"page":"1477-1489","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi\u2010Delay Arterial Spin Labeling <scp>MRI<\/scp> Using a Simulation\u2010Based Supervised Deep Neural Network"],"prefix":"10.1002","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0728-8057","authenticated-orcid":false,"given":"Shota","family":"Ishida","sequence":"first","affiliation":[{"name":"Department of Radiological Technology, Faculty of Medical Sciences Kyoto College of Medical Science  Kyoto Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makoto","family":"Isozaki","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Division of Medicine, Faculty of Medical Sciences University of Fukui  Fukui Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuhiro","family":"Fujiwara","sequence":"additional","affiliation":[{"name":"Department of Medical Image Sciences, Faculty of Life Sciences Kumamoto University  Kumamoto Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoyuki","family":"Takei","sequence":"additional","affiliation":[{"name":"GE Healthcare  Tokyo Japan"},{"name":"Department of Radiology, Graduate School of Medicine The University of Tokyo  Tokyo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayuki","family":"Kanamoto","sequence":"additional","affiliation":[{"name":"Radiological Center University of Fukui Hospital  Fukui Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirohiko","family":"Kimura","sequence":"additional","affiliation":[{"name":"Faculty of Medical Sciences University of Fukui  Fukui Japan"},{"name":"Radiology Section National Health Insurance Echizen\u2010cho Ota Hospital  Fukui Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8980-1044","authenticated-orcid":false,"given":"Tetsuya","family":"Tsujikawa","sequence":"additional","affiliation":[{"name":"Department of Radiology, Faculty of Medical Sciences University of Fukui  Fukui Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1910230106"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25197"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29052"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24026"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0156005"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24451"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.2463\/mrms.mp.2020-0123"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25834"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4319"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27580"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117246"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.23103"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2013.06.017"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-014-3098-9"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27823"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24335"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28300"},{"key":"e_1_2_7_19_1","article-title":"Very deep convolutional networks for large\u2010scale image recognition","author":"Simonyan K","year":"2014","journal-title":"arXiv"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3833"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27910"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28852"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28074"},{"key":"e_1_2_7_24_1","doi-asserted-by":"crossref","unstructured":"GongE GuoJ LiuJ et al.Deep learning and multi\u2010contrast based denoising for low\u2010SNR arterial spin labeling (ASL) MRI. In Proceedings of SPIE Medical Imaging.2020;11313.","DOI":"10.1117\/12.2549765"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2020.01.005"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/0271678X19888123"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2021.101546"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29193"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.NPh.3.3.031411"},{"key":"e_1_2_7_30_1","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert DA","year":"2016","journal-title":"arXiv"},{"key":"e_1_2_7_31_1","article-title":"Adam: A method for stochastic optimization","author":"Kingma DP","year":"2017","journal-title":"arXiv"},{"key":"e_1_2_7_32_1","article-title":"Delving deep into rectifiers: Surpassing human\u2010level performance on ImageNet classification","author":"He K","year":"2015","journal-title":"arXiv"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21790"},{"key":"e_1_2_7_34_1","doi-asserted-by":"publisher","DOI":"10.1177\/0271678X17721830"},{"key":"e_1_2_7_35_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-7-1247-2014"},{"key":"e_1_2_7_36_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A2008"},{"key":"e_1_2_7_37_1","doi-asserted-by":"publisher","DOI":"10.1177\/0284185116632387"},{"key":"e_1_2_7_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.10211"},{"key":"e_1_2_7_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2018.02.001"},{"key":"e_1_2_7_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-019-00785-9"},{"key":"e_1_2_7_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22320"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28433","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.28433","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T18:26:31Z","timestamp":1692728791000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.28433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10.1002\/jmri.28433"],"URL":"https:\/\/doi.org\/10.1002\/jmri.28433","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]},"assertion":[{"value":"2022-06-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}