{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:53:56Z","timestamp":1792792436762,"version":"4.5.0"},"reference-count":30,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T00:00:00Z","timestamp":1660608000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01\u2010HD087221"],"award-info":[{"award-number":["U01\u2010HD087221"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"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>Automated segmentation of the placenta by MRI in early pregnancy may help predict normal and aberrant placenta function, which could improve the efficiency of placental assessment and the prediction of pregnancy outcomes. An automated segmentation method that works at one gestational age may not transfer effectively to other gestational ages.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To evaluate a spatial attentive deep learning method (SADL) for automated placental segmentation on longitudinal placental MRI scans.<\/jats:p><\/jats:sec><jats:sec><jats:title>Study type<\/jats:title><jats:p>Prospective, single\u2010center.<\/jats:p><\/jats:sec><jats:sec><jats:title>Subjects<\/jats:title><jats:p>A total of 154 pregnant women who underwent MRI scans at both 14\u201318\u2009weeks of gestation and at 19\u201324\u2009weeks of gestation, divided into training (<jats:italic>N<\/jats:italic>\u00a0=\u00a0108), validation (<jats:italic>N<\/jats:italic>\u00a0=\u00a015), and independent testing datasets (<jats:italic>N<\/jats:italic>\u00a0=\u00a031).<\/jats:p><\/jats:sec><jats:sec><jats:title>Field Strength\/Sequence<\/jats:title><jats:p>A 3\u2009T, T2\u2010weighted half Fourier single\u2010shot turbo spin\u2010echo (T2\u2010HASTE) sequence.<\/jats:p><\/jats:sec><jats:sec><jats:title>Assessment<\/jats:title><jats:p>The reference standard of placental segmentation was manual delineation on T2\u2010HASTE by a third\u2010year neonatology clinical fellow (B.L.) under the supervision of an experienced maternal\u2010fetal medicine specialist (C.J. with 20\u2009years of experience) and an MRI scientist (K.S. with 19\u2009years of experience).<\/jats:p><\/jats:sec><jats:sec><jats:title>Statistical Tests<\/jats:title><jats:p>The three\u2010dimensional Dice similarity coefficient (DSC) was used to measure the automated segmentation performance compared to the manual placental segmentation. A paired <jats:italic>t<\/jats:italic>\u2010test was used to compare the DSCs between SADL and U\u2010Net methods. A Bland\u2013Altman plot was used to analyze the agreement between manual and automated placental volume measurements. A <jats:italic>P<\/jats:italic> value\u2009&lt;\u20090.05 was considered statistically significant.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the testing dataset, SADL achieved average DSCs of 0.83\u2009\u00b1\u20090.06 and 0.84\u2009\u00b1\u20090.05 in the first and second MRI, which were significantly higher than those achieved by U\u2010Net (0.77\u2009\u00b1\u20090.08 and 0.76\u2009\u00b1\u20090.10, respectively). A total of 6 out of 62 MRI scans (9.6%) had volume measurement differences between the SADL\u2010based automated and manual volume measurements that were out of 95% limits of agreement.<\/jats:p><\/jats:sec><jats:sec><jats:title>Data Conclusions<\/jats:title><jats:p>SADL can automatically detect and segment the placenta with high performance in MRI at two different gestational ages.<\/jats:p><\/jats:sec><jats:sec><jats:title>Level of Evidence<\/jats:title><jats:p>4<\/jats:p><\/jats:sec><jats:sec><jats:title>Technical Efficacy Stage<\/jats:title><jats:p>2<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.28403","type":"journal-article","created":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T15:39:56Z","timestamp":1660664396000},"page":"1533-1540","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Evaluation of Spatial Attentive Deep Learning for Automatic Placental Segmentation on Longitudinal <scp>MRI<\/scp>"],"prefix":"10.1002","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4478-4006","authenticated-orcid":false,"given":"Yongkai","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Radiological Sciences University of California  Los Angeles California USA"},{"name":"Physics and Biology in Medicine IDP, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatemeh","family":"Zabihollahy","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8204-8654","authenticated-orcid":false,"given":"Ran","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences University of California  Los Angeles California USA"},{"name":"Department of Bioengineering, Henry Samueli School of Engineering University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carla","family":"Janzen","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sherin U.","family":"Devaskar","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4175-5322","authenticated-orcid":false,"given":"Kyunghyun","family":"Sung","sequence":"additional","affiliation":[{"name":"Department of Radiological Sciences University of California  Los Angeles California USA"},{"name":"Physics and Biology in Medicine IDP, David Geffen School of Medicine University of California  Los Angeles California USA"},{"name":"Department of Bioengineering, Henry Samueli School of Engineering University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"e_1_2_6_2_1","article-title":"Segmentation of uterus and placenta in MR images using a fully convolutional neural network","volume":"11314","author":"Shahedi M","year":"2020","journal-title":"Proc SPIE Int Soc Opt Eng"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26944"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.20855"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.22473"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0730-725X(99)00035-1"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25806"},{"key":"e_1_2_6_8_1","first-page":"234","article-title":"U\u2010net: Convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger O","year":"2015","journal-title":"Med Image Comput Comput Assit Interv"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2791721"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958133"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.05.004"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952534"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017168"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.1172\/jci.insight.120178"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2019.8857448"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_68"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840695"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_4"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.04.009"},{"key":"e_1_2_6_21_1","first-page":"1635","article-title":"Half\u2010fourier acquisition single\u2010shot turbo spin\u2010echo (HASTE) MR: Comparison with fast spin\u2010echo MR in diseases of the brain","volume":"18","author":"Patel MR","year":"1997","journal-title":"Am J Neuroradiol"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"e_1_2_6_23_1","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He K","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"e_1_2_6_24_1","unstructured":"LiH XiongP AnJ WangL.Pyramid attention network for semantic segmentation.2018."},{"key":"e_1_2_6_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-05300-5"},{"key":"e_1_2_6_26_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2015.015"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/0968-0004(90)90295-M"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1053\/plac.2001.0684"},{"key":"e_1_2_6_31_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.semperi.2014.03.003"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28403","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.28403","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T18:27:47Z","timestamp":1692728867000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.28403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,16]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10.1002\/jmri.28403"],"URL":"https:\/\/doi.org\/10.1002\/jmri.28403","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,16]]},"assertion":[{"value":"2022-05-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}