{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T01:41:07Z","timestamp":1773020467786,"version":"3.50.1"},"reference-count":41,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T00:00:00Z","timestamp":1580774400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801026"],"award-info":[{"award-number":["61801026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81371540"],"award-info":[{"award-number":["81371540"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81571667"],"award-info":[{"award-number":["81571667"]}],"id":[{"id":"10.13039\/501100001809","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":[[2020,8]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To develop a reproducible and fast method to reconstruct MR fingerprinting arterial spin labeling (MRF\u2010ASL) perfusion maps using deep learning.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>A fully connected neural network, denoted as DeepMARS, was trained using simulation data and added Gaussian noise. Two MRF\u2010ASL models were used to generate the simulation data, specifically a single\u2010compartment model with 4 unknowns parameters and a two\u2010compartment model with 7 unknown parameters. The DeepMARS method was evaluated using MRF\u2010ASL data from healthy subjects (N = 7) and patients with Moymoya disease (N = 3). Computation time, coefficient of determination (R<jats:sup>2<\/jats:sup>), and intraclass correlation coefficient (ICC) were compared between DeepMARS and conventional dictionary matching (DM). The relationship between DeepMARS and Look\u2013Locker PASL was evaluated by a linear mixed model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Computation time per voxel was &lt;0.5 ms for DeepMARS and &gt;4 seconds for DM in the single\u2010compartment model. Compared with DM, the DeepMARS showed higher R<jats:sup>2<\/jats:sup> and significantly improved ICC for single\u2010compartment derived bolus arrival time (BAT) and two\u2010compartment derived cerebral blood flow (CBF) and higher or similar R<jats:sup>2<\/jats:sup>\/ICC for other parameters. In addition, the DeepMARS was significantly correlated with Look\u2013Locker PASL for BAT (single\u2010compartment) and CBF (two\u2010compartment). Moreover, for Moyamoya patients, the location of diminished CBF and prolonged BAT shown in DeepMARS was consistent with the position of occluded arteries shown in time\u2010of\u2010flight MR angiography.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Reconstruction of MRF\u2010ASL with DeepMARS is faster and more reproducible than DM.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mrm.28166","type":"journal-article","created":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T09:01:41Z","timestamp":1580806901000},"page":"1024-1034","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Deep learning\u2013based MR fingerprinting ASL ReconStruction (DeepMARS)"],"prefix":"10.1002","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5875-2692","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"first","affiliation":[{"name":"Center for Biomedical Imaging Research Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Su","sequence":"additional","affiliation":[{"name":"The Russell H. Morgan Department of Radiology Johns Hopkins University School of Medicine Baltimore Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7975-2528","authenticated-orcid":false,"given":"Zhensen","family":"Chen","sequence":"additional","affiliation":[{"name":"Vascular Imaging Laboratory Department of Radiology University of Washington Seattle Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Liao","sequence":"additional","affiliation":[{"name":"Center for Biomedical Imaging Department of Radiology New York University School of Medicine New York New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Biomedical Imaging Research Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Medicine (Cardiovascular Division) Beth Israel deaconess Medical Center and Harvard Medical School Boston Massachusetts"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haikun","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering and Imaging Sciences King\u2019s College London London, London United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuesong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Beijing Institute of Technology Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Biomedical Imaging Research Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6534-4299","authenticated-orcid":false,"given":"Zhangxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Center for Biomedical Imaging Research Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzhang","family":"Lu","sequence":"additional","affiliation":[{"name":"The Russell H. Morgan Department of Radiology Johns Hopkins University School of Medicine Baltimore Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1158-5510","authenticated-orcid":false,"given":"Huijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Biomedical Imaging Research Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2020,2,4]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.3171\/2009.1.FOCUS08300"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.111.616466"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.108.192616"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.111.631929"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25197"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1910400308"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature11971"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26587"},{"key":"e_1_2_6_10_1","unstructured":"McGivneyDF DeshmaneA JiangY MaD GriswoldMA.Nonlinear dimensionality reduction for magnetic resonance fingerprinting with applications to partial volume. In Proceedings of the 23rd Annual Meeting of the ISMRM Toronto Ontario Canada 2015. Abstract 3380."},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2337321"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25439"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2017.04.004"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2817547"},{"key":"e_1_2_6_15_1","unstructured":"GopalN MingjieG JakobA ClaytonS FesslerJA.Shallow learning with kernels for dictionary\u2010free magnetic resonance fingerprinting. In Proceedings of the ISMRM Workshop on Magnetic Resonance Fingerprinting Cleveland OH 2017."},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27198"},{"key":"e_1_2_6_17_1","unstructured":"LahiriA FesslerJA Hernandez\u2010GarciaL.Optimizing MRF\u2010ASL scan design towards precise quantification of hemodynamic properties in cerebrovascular disorders. In Proceedings of the 27th Annual Meeting of the ISMRM Montreal Quebec Canada 2019. Abstract 5026."},{"key":"e_1_2_6_18_1","unstructured":"LahiriA FesslerJA Hernandez\u2010GarciaL.Optimized scan design for ASL fingerprinting and multiparametric estimation using neural network regression. In Proceedings of the 26th Annual Meeting of the ISMRM Paris France 2018. Abstract 0309."},{"key":"e_1_2_6_19_1","doi-asserted-by":"crossref","unstructured":"LahiriA FesslerJA Hernandez\u2010GarciaL.Optimizing MRF\u2010ASL scan design for precise quantification of brain hemodynamics using neural network regression. arXiv e\u2010prints.2019;arXiv:1905(06474) [eess.IV].","DOI":"10.1002\/mrm.28051"},{"key":"e_1_2_6_20_1","unstructured":"ZhangQ SuP LiaoY et al.Deep learning based MR fingerprinting ASL ReconStruction (DeepMARS). In Proceedings of the 27th Annual Meeting of the ISMRM Montreal Quebec Canada 2019. Abstract 0820."},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1284"},{"key":"e_1_2_6_22_1","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap AF","year":"2018","journal-title":"ArXiv e\u2010prints"},{"key":"e_1_2_6_23_1","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe S","year":"2015","journal-title":"ArXiv e\u2010prints"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.01.005"},{"key":"e_1_2_6_25_1","doi-asserted-by":"crossref","unstructured":"BosseS ManiryD WiegandT SamekW.A deep neural network for image quality assessment. In Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP) Phoenix AZ 2016.","DOI":"10.1109\/ICIP.2016.7533065"},{"key":"e_1_2_6_26_1","article-title":"Adam: a method for stochastic optimization","author":"Kingma DP","year":"2014","journal-title":"ArXiv e\u2010prints"},{"key":"e_1_2_6_27_1","unstructured":"CholletF. keras.2015 GitHub.https:\/\/github.com\/fchollet. Accessed January 4 2020."},{"key":"e_1_2_6_28_1","article-title":"Deep learning for single image super\u2010resolution: a brief review","author":"Yang W","year":"2018","journal-title":"ArXiv e\u2010prints"},{"key":"e_1_2_6_29_1","doi-asserted-by":"crossref","unstructured":"VincentP LarochelleH BengioY ManzagolP-A.Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (ICML 2008).Helsinki Finland:ACM;2008:1096\u20131103.","DOI":"10.1145\/1390156.1390294"},{"key":"e_1_2_6_30_1","unstructured":"SuP LiuP LiY et al.Comparison of MR Fingerprinting ASL with Gd\u2010based DSC MRI: validation and direct parametric mapping with deep learning. In Proceedings of the 27th Annual Meeting of the ISMRM Montreal Quebec Canada 2019. Abstract 0843."},{"key":"e_1_2_6_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4202"},{"key":"e_1_2_6_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20784"},{"key":"e_1_2_6_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20178"},{"key":"e_1_2_6_34_1","unstructured":"SuP LiuP LiY et al.Non\u2010contrast fingerprinting perfusion imaging reveals hemodynamic deficits in cerebrovascular diseases. In Proceedings of the 26th Annual Meeting of the ISMRM Paris France 2018. Abstract 0860."},{"key":"e_1_2_6_35_1","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.1.1.30"},{"key":"e_1_2_6_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.2005752"},{"key":"e_1_2_6_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.22320"},{"key":"e_1_2_6_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurad.2016.12.006"},{"key":"e_1_2_6_39_1","volume-title":"Mixed\u2010Effect Models in S and S\u2010plus","author":"Pinheiro JC","year":"2002"},{"key":"e_1_2_6_40_1","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7064120"},{"key":"e_1_2_6_41_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.254082000"},{"key":"e_1_2_6_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0730-725X(02)00629-X"}],"updated-by":[{"DOI":"10.1002\/mrm.29538","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000}}],"container-title":["Magnetic Resonance in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmrm.28166","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.28166","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mrm.28166","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mrm.28166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T16:34:51Z","timestamp":1693931691000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/mrm.28166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,4]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["10.1002\/mrm.28166"],"URL":"https:\/\/doi.org\/10.1002\/mrm.28166","archive":["Portico"],"relation":{"erratum":[{"id-type":"doi","id":"10.1002\/mrm.29538","asserted-by":"object"}]},"ISSN":["0740-3194","1522-2594"],"issn-type":[{"value":"0740-3194","type":"print"},{"value":"1522-2594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,4]]},"assertion":[{"value":"2019-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-12-17","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-02-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}