{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T20:29:28Z","timestamp":1790627368755,"version":"4.1.0"},"reference-count":36,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005617","name":"BHF Centre of Research Excellence, Oxford","doi-asserted-by":"publisher","award":["RE\/18\/3\/34214"],"award-info":[{"award-number":["RE\/18\/3\/34214"]}],"id":[{"id":"10.13039\/501100005617","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/M008894\/1"],"award-info":[{"award-number":["MR\/M008894\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/V027859\/1"],"award-info":[{"award-number":["MR\/V027859\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011703","name":"Yorkshire Cancer Research","doi-asserted-by":"publisher","award":["S406BT"],"award-info":[{"award-number":["S406BT"]}],"id":[{"id":"10.13039\/100011703","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":[[2023,10]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Recently, deep learning via convolutional neural networks (CNNs) has largely superseded conventional methods for proton (\n                      <jats:sup>1<\/jats:sup>\n                      H)\u2010MRI lung segmentation. However, previous deep learning studies have utilized single\u2010center data and limited acquisition parameters.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      Develop a generalizable CNN for lung segmentation in\n                      <jats:sup>1<\/jats:sup>\n                      H\u2010MRI, robust to pathology, acquisition protocol, vendor, and center.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Study type<\/jats:title>\n                    <jats:p>Retrospective.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Population<\/jats:title>\n                    <jats:p>\n                      A total of 809\n                      <jats:sup>1<\/jats:sup>\n                      H\u2010MRI scans from 258 participants with various pulmonary pathologies (median age (range): 57 (6\u201385); 42% females) and 31 healthy participants (median age (range): 34 (23\u201376); 34% females) that were split into training (593 scans (74%); 157 participants (55%)), testing (50 scans (6%); 50 participants (17%)) and external validation (164 scans (20%); 82 participants (28%)) sets.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Field Strength\/Sequence<\/jats:title>\n                    <jats:p>\n                      <jats:styled-content style=\"fixed-case\">1.5\u2010T<\/jats:styled-content>\n                      and\n                      <jats:styled-content style=\"fixed-case\">3\u2010T<\/jats:styled-content>\n                      \/\n                      <jats:styled-content style=\"fixed-case\">3D<\/jats:styled-content>\n                      spoiled\u2010gradient recalled and ultrashort echo\u2010time\n                      <jats:styled-content style=\"fixed-case\">\n                        <jats:sup>1<\/jats:sup>\n                        H\u2010MRI\n                      <\/jats:styled-content>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Assessment<\/jats:title>\n                    <jats:p>2D and 3D CNNs, trained on single\u2010center, multi\u2010sequence data, and the conventional spatial fuzzy c\u2010means (SFCM) method were compared to manually delineated expert segmentations. Each method was validated on external data originating from several centers. Dice similarity coefficient (DSC), average boundary Hausdorff distance (Average HD), and relative error (XOR) metrics to assess segmentation performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Statistical Tests<\/jats:title>\n                    <jats:p>\n                      Kruskal\u2013Wallis tests assessed significances of differences between acquisitions in the testing set. Friedman tests with post hoc multiple comparisons assessed differences between the 2D CNN, 3D CNN, and SFCM. Bland\u2013Altman analyses assessed agreement with manually derived lung volumes. A\n                      <jats:italic>P<\/jats:italic>\n                      value of &lt;0.05 was considered statistically significant.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The 3D CNN significantly outperformed its 2D analog and SFCM, yielding a median (range) DSC of 0.961 (0.880\u20130.987), Average HD of 1.63\u2009mm (0.65\u20135.45) and XOR of 0.079 (0.025\u20130.240) on the testing set and a DSC of 0.973 (0.866\u20130.987), Average HD of 1.11\u2009mm (0.47\u20138.13) and XOR of 0.054 (0.026\u20130.255) on external validation data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Data Conclusion<\/jats:title>\n                    <jats:p>\n                      The 3D CNN generated accurate\n                      <jats:sup>1<\/jats:sup>\n                      H\u2010MRI lung segmentations on a heterogenous dataset, demonstrating robustness to disease pathology, sequence, vendor, and center.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Evidence Level<\/jats:title>\n                    <jats:p>4.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Technical Efficacy<\/jats:title>\n                    <jats:p>Stage 1.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jmri.28643","type":"journal-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T06:15:39Z","timestamp":1676614539000},"page":"1030-1044","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Implementable Deep Learning for Multi\u2010sequence Proton\n                    <scp>MRI<\/scp>\n                    Lung Segmentation: A Multi\u2010center, Multi\u2010vendor, and Multi\u2010disease Study"],"prefix":"10.1002","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6552-5436","authenticated-orcid":false,"given":"Joshua R.","family":"Astley","sequence":"first","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"},{"name":"Department of Oncology and Metabolism The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto M.","family":"Biancardi","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7979-5840","authenticated-orcid":false,"given":"Paul J. C.","family":"Hughes","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-1449","authenticated-orcid":false,"given":"Helen","family":"Marshall","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guilhem J.","family":"Collier","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-2097","authenticated-orcid":false,"given":"Ho\u2010Fung","family":"Chan","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1080-9861","authenticated-orcid":false,"given":"Laura C.","family":"Saunders","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurie J.","family":"Smith","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin L.","family":"Brook","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0717-4551","authenticated-orcid":false,"given":"Roger","family":"Thompson","sequence":"additional","affiliation":[{"name":"Sheffield Teaching Hospitals NHS Foundation Trust  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Rowland\u2010Jones","sequence":"additional","affiliation":[{"name":"Sheffield Teaching Hospitals NHS Foundation Trust  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Skeoch","sequence":"additional","affiliation":[{"name":"Royal National Hospital for Rheumatic Diseases Royal United Hospital NHS Foundation Trust  Bath UK"},{"name":"Arthritis Research UK Centre for Epidemiology, Division of Musculoskeletal and Dermatological Sciences, School of Biological Sciences, Faculty of Biology, Medicine and Health University of Manchester, Manchester Academic Health Sciences Centre  Manchester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen M.","family":"Bianchi","sequence":"additional","affiliation":[{"name":"Sheffield Teaching Hospitals NHS Foundation Trust  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew Q.","family":"Hatton","sequence":"additional","affiliation":[{"name":"Sheffield Teaching Hospitals NHS Foundation Trust  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najib M.","family":"Rahman","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Radcliffe Department of Medicine, National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC) University of Oxford  Oxford UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling\u2010Pei","family":"Ho","sequence":"additional","affiliation":[{"name":"MRC Human Immunology Unit University of Oxford  Oxford UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris E.","family":"Brightling","sequence":"additional","affiliation":[{"name":"The Institute for Lung Health, NIHR Leicester Biomedical Research Centre University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louise V.","family":"Wain","sequence":"additional","affiliation":[{"name":"The Institute for Lung Health, NIHR Leicester Biomedical Research Centre University of Leicester  Leicester UK"},{"name":"Department of Health sciences University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amisha","family":"Singapuri","sequence":"additional","affiliation":[{"name":"The Institute for Lung Health, NIHR Leicester Biomedical Research Centre University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachael A.","family":"Evans","sequence":"additional","affiliation":[{"name":"University Hospitals of Leicester NHS Trust University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alastair J.","family":"Moss","sequence":"additional","affiliation":[{"name":"The Institute for Lung Health, NIHR Leicester Biomedical Research Centre University of Leicester  Leicester UK"},{"name":"Department of Cardiovascular Sciences University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerry P.","family":"McCann","sequence":"additional","affiliation":[{"name":"The Institute for Lung Health, NIHR Leicester Biomedical Research Centre University of Leicester  Leicester UK"},{"name":"Department of Cardiovascular Sciences University of Leicester  Leicester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Neubauer","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Radcliffe Department of Medicine, National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC) University of Oxford  Oxford UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1239-9608","authenticated-orcid":false,"given":"Betty","family":"Raman","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Radcliffe Department of Medicine, National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC) University of Oxford  Oxford UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"C\u2010MORE\/PHOSP\u2010COVID Collaborative Group","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7246-8660","authenticated-orcid":false,"given":"Jim M.","family":"Wild","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"},{"name":"Insigneo Institute for In Silico Medicine The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-3519","authenticated-orcid":false,"given":"Bilal A.","family":"Tahir","sequence":"additional","affiliation":[{"name":"POLARIS, Department of Infection, Immunity &amp; Cardiovascular Disease The University of Sheffield  Sheffield UK"},{"name":"Department of Oncology and Metabolism The University of Sheffield  Sheffield UK"},{"name":"Insigneo Institute for In Silico Medicine The University of Sheffield  Sheffield UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24523-2_1"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijid.2019.03.004"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/bjaceaccp\/mku063"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13244-012-0176-x"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27122"},{"key":"e_1_2_7_7_1","article-title":"Pulmonary functional imaging for lung adenocarcinoma: Combined MRI assessment based on IVIM\u2010DWI and OE\u2010UTE\u2010MRI","volume":"11","author":"Liu H","year":"2021","journal-title":"Front Oncol"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.617681"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27461"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2016.07.005"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25804"},{"key":"e_1_2_7_12_1","volume-title":"Proceedings of the 26th Annual Meeting of ISMRM Volume (abstract 2442)","author":"Biancardi A","year":"2018"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20201107"},{"key":"e_1_2_7_14_1","article-title":"Model evaluation, model selection, and algorithm selection in machine learning","author":"Raschka S","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-80936-4"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.20290"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3187"},{"key":"e_1_2_7_18_1","article-title":"nnu\u2010net: Self\u2010adapting framework for u\u2010net\u2010based medical image segmentation","author":"Isensee F","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.01.025"},{"key":"e_1_2_7_20_1","article-title":"Tensorflow: Large\u2010scale machine learning on heterogeneous distributed systems","author":"Abadi M","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_7_23_1","volume-title":"3rd International conference for learning representations\u00a0(ICLR) Volume abs\/1412.6980","author":"Kingma D","year":"2015"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-14672-2"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710815"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2010.10.007"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_7_28_1","first-page":"1003","volume-title":"On hausdorff distance measures","author":"Shapiro MD","year":"2004"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60964-5_70"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2015140232"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.semnuclmed.2020.11.003"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26734"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2018.08.003"},{"key":"e_1_2_7_34_1","unstructured":"ReinkeA Maier\u2010HeinL M\u00fcllerH.Medical imaging with deep learning common limitations of performance metrics in biomedical image analysis Delphi consortium on metrics.2021."},{"key":"e_1_2_7_35_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018171993"},{"key":"e_1_2_7_36_1","first-page":"1","article-title":"Role of dynamic sleep MRI in obstructive sleep apnea syndrome","volume":"37","author":"Gamaleldin O","year":"2020","journal-title":"Oral Radiol"},{"key":"e_1_2_7_37_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0068-x"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28643","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.28643","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.28643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:59:43Z","timestamp":1764691183000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.28643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["10.1002\/jmri.28643"],"URL":"https:\/\/doi.org\/10.1002\/jmri.28643","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"2022-12-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}