{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T09:01:04Z","timestamp":1772010064542,"version":"3.50.1"},"reference-count":37,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T00:00:00Z","timestamp":1655769600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2022,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Using the spin\u2010lattice relaxation time (<jats:italic>T<\/jats:italic>1) as a biomarker, the myocardium can be quantitatively characterized using cardiac <jats:italic>T<\/jats:italic>1 mapping. The modified Look\u2013Locker inversion (MOLLI) recovery sequences have become the standard clinical method for cardiac <jats:italic>T<\/jats:italic>1 mapping. However, the MOLLI sequences require an 11\u2010heartbeat breath\u2010hold that can be difficult for subjects, particularly during exercise or pharmacologically induced stress. Although shorter cardiac <jats:italic>T<\/jats:italic>1 mapping sequences have been proposed, these methods suffer from reduced precision. As such, there is an unmet need for accelerated cardiac <jats:italic>T<\/jats:italic>1 mapping.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To accelerate cardiac <jats:italic>T<\/jats:italic>1 mapping MOLLI sequences by using neural networks to estimate <jats:italic>T<\/jats:italic>1 maps using a reduced number of <jats:italic>T<\/jats:italic>1\u2010weighted images and their corresponding inversion times.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>In this retrospective study, 911 pre\u2010contrast <jats:italic>T<\/jats:italic>1 mapping datasets from 202 subjects (128 males, 56 \u00b1 15 years; 74 females, 54 \u00b1 17 years) and 574 <jats:italic>T<\/jats:italic>1 mapping post\u2010contrast datasets from 193 subjects (122 males, 57 \u00b1 15 years; 71 females, 54 \u00b1 17 years) were acquired using the MOLLI\u20105(3)3 sequence and the MOLLI\u20104(1)3(1)2 sequence, respectively. All acquisition protocols used similar scan parameters: , , and , gadoteridol (ProHance, Bracco Diagnostics) dose . A bidirectional multilayered long short\u2010term memory (LSTM) network with fully connected output and cyclic model\u2010based loss was used to estimate <jats:italic>T<\/jats:italic>1 maps from the first three <jats:italic>T<\/jats:italic>1\u2010weighted images and their corresponding inversion times for pre\u2010 and post\u2010contrast <jats:italic>T<\/jats:italic>1 mapping. The performance of the proposed architecture was compared to the three\u2010parameter <jats:italic>T<\/jats:italic>1 recovery model using the same reduction of the number of <jats:italic>T<\/jats:italic>1\u2010weighted images and inversion times. Reference <jats:italic>T<\/jats:italic>1 maps were generated from the scanner using the full MOLLI sequences and the three\u2010parameter <jats:italic>T<\/jats:italic>1 recovery model. Correlation and Bland\u2013Altman plots were used to evaluate network performance in which each point represents averaged regions of interest in the myocardium corresponding to the standard American Heart Association 16\u2010segment model. The precision of the network was examined using consecutively repeated scans. Stress and rest pre\u2010contrast MOLLI studies as well as various disease test cases, including amyloidosis, hypertrophic cardiomyopathy, and sarcoidosis were also examined. Paired <jats:italic>t<\/jats:italic>\u2010tests were used to determine statistical significance with .<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our proposed network demonstrated similar <jats:italic>T<\/jats:italic>1 estimations to the standard MOLLI sequences (pre\u2010contrast:  vs.  with ; post\u2010contrast:  vs.  with ). The precision of standard MOLLI sequences was well preserved with the proposed network architecture ( vs. ). Network\u2010generated <jats:italic>T<\/jats:italic>1 reactivities are similar to stress and rest pre\u2010contrast MOLLI studies ( vs.  with ). Amyloidosis <jats:italic>T<\/jats:italic>1 maps generated using the proposed network are also similar to the reference <jats:italic>T<\/jats:italic>1 maps (pre\u2010contrast:  vs.  with ; post\u2010contrast:  vs.  with ).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>A bidirectional multilayered LSTM network with fully connected output and cyclic model\u2010based loss was used to generate high\u2010quality pre\u2010 and post\u2010contrast <jats:italic>T<\/jats:italic>1 maps using the first three <jats:italic>T<\/jats:italic>1\u2010weighted images and their corresponding inversion times. This work demonstrates that combining deep learning with cardiac <jats:italic>T<\/jats:italic>1 mapping can potentially accelerate standard MOLLI sequences from 11 to 3 heartbeats.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15801","type":"journal-article","created":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T10:49:28Z","timestamp":1655290168000},"page":"6986-7000","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Accelerated cardiac <i>T<\/i>1 mapping with recurrent networks and cyclic, model\u2010based loss"],"prefix":"10.1002","volume":"49","author":[{"given":"Johnathan V.","family":"Le","sequence":"first","affiliation":[{"name":"Utah Center for Advanced Imaging Research (UCAIR) Department of Radiology and Imaging Sciences University of Utah  Salt Lake City Utah USA"},{"name":"Department of Biomedical Engineering University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason K.","family":"Mendes","sequence":"additional","affiliation":[{"name":"Utah Center for Advanced Imaging Research (UCAIR) Department of Radiology and Imaging Sciences University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"McKibben","sequence":"additional","affiliation":[{"name":"Utah Center for Advanced Imaging Research (UCAIR) Department of Radiology and Imaging Sciences University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brent D.","family":"Wilson","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward V.R.","family":"DiBella","sequence":"additional","affiliation":[{"name":"Utah Center for Advanced Imaging Research (UCAIR) Department of Radiology and Imaging Sciences University of Utah  Salt Lake City Utah USA"},{"name":"Department of Biomedical Engineering University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganesh","family":"Adluru","sequence":"additional","affiliation":[{"name":"Utah Center for Advanced Imaging Research (UCAIR) Department of Radiology and Imaging Sciences University of Utah  Salt Lake City Utah USA"},{"name":"Department of Biomedical Engineering University of Utah  Salt Lake City Utah USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2022,6,21]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/1532\u2010429X\u201014\u201015"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2012.11.013"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.112.000070"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010016\u20100308\u20104"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehr481"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/1532\u2010429X\u201014\u201063"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2015.08.018"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2017.11.071"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2019.05.019"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10554\u2010019\u201001554\u20104"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010019\u20100585\u20109"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10554\u2010015\u20100639\u20105"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010016\u20100232\u20107"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010020\u201071722\u20103"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2019.04.016"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20110"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24878"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14140296"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010016\u20100302\u2010x"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.3978\/j.issn.2223\u20104292.2015.04.07"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010018\u20100516\u20101"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12968\u2010020\u201000650\u2010y"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"JeelaniHY YangY Zhou Ruixi et\u00a0al.A myocardial T1\u2010mapping framework with recurrent and U\u2010Net convolutional neural networks.Presented at: IEEE 17th International Symposium on Biomedical Imaging (ISBI);2020;Iowa City Iowa.","DOI":"10.1109\/ISBI45749.2020.9098459"},{"key":"e_1_2_10_25_1","unstructured":"AdluruGT Ye Mendes Jason Wilson Brent DiBella Edward.Rapid myocardial T1 mapping with deep learning. In:The Proceedings of the 22nd Annual Meeting of SCMR;2019."},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mric.2014.08.007"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.23153"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24793"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09838-1"},{"key":"e_1_2_10_31_1","first-page":"404","article-title":"Fundamentals of recurrent neural network (RNN) and long short\u2010term memory (LSTM) network","volume":"2020","author":"Sherstinsky A","year":"2020","journal-title":"Physica D: Nonlinear Phenom"},{"key":"e_1_2_10_32_1","unstructured":"PaszkeAG GrossS Chintala S et\u00a0al.Automatic differentiation in PyTorch. In:NIPS 2017 Workshop;2017."},{"issue":"1","key":"e_1_2_10_33_1","first-page":"539","article-title":"Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association","volume":"18","author":"Cerqueira MD","year":"2002","journal-title":"Int J Cardiovasc Imaging"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: convolutional networks for biomedical image segmentation. In:The Proceedings of the 18th Annual Meeting of MICCAI;2015:234\u2013241.Munich Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2014.00044"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3223631"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1186\/1532\u2010429X\u201015\u201092"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010019\u20100686\u20102"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15801","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15801","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T23:30:05Z","timestamp":1692487805000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,21]]},"references-count":37,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["10.1002\/mp.15801"],"URL":"https:\/\/doi.org\/10.1002\/mp.15801","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,21]]},"assertion":[{"value":"2022-02-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}