{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T01:52:48Z","timestamp":1790301168223,"version":"4.1.0"},"reference-count":34,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T00:00:00Z","timestamp":1639699200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004836","name":"Independent Research Fund Denmark","doi-asserted-by":"publisher","award":["9131\u201000099B"],"award-info":[{"award-number":["9131\u201000099B"]}],"id":[{"id":"10.13039\/501100004836","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":[[2022,6]]},"abstract":"Background<\/jats:title>Segmentation of medical image volumes is a time\u2010consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it is unclear how they behave in other clinical settings.<\/jats:p><\/jats:sec>Purpose<\/jats:title>To evaluate the performance of the open\u2010source Multi\u2010Planar U\u2010Net (MPUnet), the validated Knee Imaging Quantification (KIQ) framework, and a state\u2010of\u2010the\u2010art two\u2010dimensional (2D) U\u2010Net architecture on three clinical cohorts without extensive adaptation of the algorithms.<\/jats:p><\/jats:sec>Study Type<\/jats:title>Retrospective cohort study.<\/jats:p><\/jats:sec>Subjects<\/jats:title>A total of 253 subjects (146 females, 107 males, ages 57\u2009\u00b1\u200912\u2009years) from three knee osteoarthritis (OA) studies (Center for Clinical and Basic Research [CCBR], Osteoarthritis Initiative [OAI], and Prevention of OA in Overweight Females [PROOF]) with varying demographics and OA severity (64\/37\/24\/53\/2 scans of Kellgren and Lawrence [KL] grades 0\u20134).<\/jats:p><\/jats:sec>Field Strength\/Sequence<\/jats:title>0.18\u2009T, 1.0\u2009T<\/jats:styled-content>\/1.5\u2009T,<\/jats:styled-content> and 3\u2009T<\/jats:styled-content> sagittal three\u2010dimensional<\/jats:styled-content> fast\u2010spin echo T1w and dual\u2010echo steady\u2010state sequences.<\/jats:p><\/jats:sec>Assessment<\/jats:title>All models were fit without tuning to knee magnetic resonance imaging (MRI) scans with manual segmentations from three clinical cohorts. All models were evaluated across KL grades.<\/jats:p><\/jats:sec>Statistical Tests<\/jats:title>Segmentation performance differences as measured by Dice coefficients were tested with paired, two\u2010sided Wilcoxon signed\u2010rank statistics with significance threshold \u03b1<\/jats:italic>\u00a0=\u00a00.05.<\/jats:p><\/jats:sec>Results<\/jats:title>The MPUnet performed superior or equal to KIQ and 2D U\u2010Net on all compartments across three cohorts. Mean Dice overlap was significantly higher for MPUnet compared to KIQ and U\u2010Net on CCBR ( vs. and ), significantly higher than KIQ and U\u2010Net OAI ( vs. and , and not significantly different from KIQ while significantly higher than 2D U\u2010Net on PROOF ( vs. , , and . The MPUnet performed significantly better on KL grade 3 CCBR scans with vs. for KIQ and for 2D U\u2010Net.<\/jats:p><\/jats:sec>Data Conclusion<\/jats:title>The MPUnet matched or exceeded the performance of state\u2010of\u2010the\u2010art knee MRI segmentation models across cohorts of variable sequences and patient demographics. The MPUnet required no manual tuning making it both accurate and easy\u2010to\u2010use.<\/jats:p><\/jats:sec>Level of Evidence<\/jats:title>3<\/jats:p><\/jats:sec>Technical Efficacy<\/jats:title>Stage 2<\/jats:p><\/jats:sec>","DOI":"10.1002\/jmri.27978","type":"journal-article","created":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T08:23:43Z","timestamp":1639729423000},"page":"1650-1663","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Cross\u2010Cohort<\/scp> Automatic Knee MRI<\/scp> Segmentation With Multi\u2010Planar U\u2010Nets<\/scp>"],"prefix":"10.1002","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0358-4692","authenticated-orcid":false,"given":"Mathias","family":"Perslev","sequence":"first","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akshay","family":"Pai","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"},{"name":"Cerebriu A\/S Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos","family":"Runhaar","sequence":"additional","affiliation":[{"name":"Erasmus MC, Rotterdam University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2868-0856","authenticated-orcid":false,"given":"Christian","family":"Igel","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8888-2524","authenticated-orcid":false,"given":"Erik B.","family":"Dam","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Copenhagen Copenhagen Denmark"},{"name":"Cerebriu A\/S Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,12,17]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng-071516-044442"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09924-4"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27130"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2781541"},{"key":"e_1_2_10_7_1","series-title":"Lecture Notes in Computer Science","first-page":"215","volume-title":"Proceedings \u2010 Medical Image Analysis for the Clinic: a Grand Challenge in Conjunction with MICCAI","author":"Seim H","year":"2010"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.01.007"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.2.2.024001"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172322"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-020-00889-7"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00057"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27229"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2018.02.907"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.11.009"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363705"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363866"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_31"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26841"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200078"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_4"},{"key":"e_1_2_10_25_1","unstructured":"AntonelliM ReinkeA BakasS et al.The medical segmentation decathlon.arXiv2021; Preprint."},{"key":"e_1_2_10_26_1","series-title":"Proceedings of Machine Learning Research","first-page":"448","volume-title":"Proceedings \u2010 32nd International Conference on Machine Learning (ICML)","author":"Ioffe S","year":"2015"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1136\/ard.16.4.494"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2007.01.013"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2015.03.006"},{"key":"e_1_2_10_31_1","first-page":"1","article-title":"A method of establishing groups of equal amplitude in plant sociology based on similarity","volume":"5","author":"S\u00f8rensen T","year":"1948","journal-title":"Kong Dansk Vidensk Selsk Biol Skr"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_10_33_1","unstructured":"BatesS HastieT TibshiraniR.Cross\u2010validation: What does it estimate and how well does it do it?arXiv2021; Preprint."},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keaa522"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00440-5"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.27978","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.27978","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.27978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T11:39:13Z","timestamp":1692963553000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.27978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,17]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.1002\/jmri.27978"],"URL":"https:\/\/doi.org\/10.1002\/jmri.27978","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,17]]},"assertion":[{"value":"2021-03-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}