{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T06:29:53Z","timestamp":1785306593646,"version":"3.55.0"},"reference-count":33,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:00:00Z","timestamp":1699574400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["acrjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Arthritis &amp; Rheumatology"],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>We aimed to develop and validate a fully automated machine learning (ML) algorithm that predicts bone marrow edema (BME) on a quadrant level in sacroiliac (SI) joint magnetic resonance imaging (MRI).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A computer vision workflow automatically locates the SI joints, segments regions of interest (ilium and sacrum), performs objective quadrant extraction, and predicts presence of BME, suggestive of inflammatory lesions, on a quadrant level in semicoronal slices of T1\/T2\u2010weighted MRI scans. Ground truth was determined by consensus among human readers. The inflammation classifier was trained using a ResNet18 backbone and five\u2010fold cross\u2010validated on scans of patients with spondyloarthritis (SpA) (n\u00a0=\u00a0279), postpartum individuals (n\u00a0=\u00a071), and healthy subjects (n\u00a0=\u00a0114). Independent SpA patient MRI scans (n\u00a0=\u00a0243) served as test data set. Patient\u2010level predictions were derived from aggregating quadrant\u2010level predictions, ie, at least one positive quadrant.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The algorithm automatically detects the SI joints with a precision of 98.4% and segments ilium\/sacrum with an intersection over union of 85.6% and 67.9%, respectively. The inflammation classifier performed well in cross\u2010validation: area under the curve (AUC) 94.5%, balanced accuracy (B\u2010ACC) 80.5%, and F1 score 64.1%. In the test data set, AUC was 88.2%, B\u2010ACC 72.1%, and F1 score 50.8%. On a patient level, the model achieved a B\u2010ACC of 81.6% and 81.4% in the cross\u2010validation and test data set, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We propose a fully automated ML pipeline that enables objective and standardized evaluation of BME along the SI joints on MRI. This method has the potential to screen large numbers of patients with (suspected) SpA and is a step closer towards artificial intelligence\u2013assisted diagnosis and follow\u2010up.<\/jats:p><\/jats:sec>","DOI":"10.1002\/art.42650","type":"journal-article","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T13:44:30Z","timestamp":1688651070000},"page":"2169-2177","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Machine Learning Pipeline for Predicting Bone Marrow Edema Along the Sacroiliac Joints on Magnetic Resonance Imaging"],"prefix":"10.1002","volume":"75","author":[{"given":"Joris","family":"Roels","sequence":"first","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7062-8934","authenticated-orcid":false,"given":"Ann\u2010Sophie","family":"De Craemer","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5503-000X","authenticated-orcid":false,"given":"Thomas","family":"Renson","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manouk","family":"de Hooge","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arne","family":"Gevaert","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-8055","authenticated-orcid":false,"given":"Thomas","family":"Van Den Berghe","sequence":"additional","affiliation":[{"name":"Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lennart","family":"Jans","sequence":"additional","affiliation":[{"name":"Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0244-0168","authenticated-orcid":false,"given":"Nele","family":"Herregods","sequence":"additional","affiliation":[{"name":"Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9254-6171","authenticated-orcid":false,"given":"Philippe","family":"Carron","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filip","family":"Van den Bosch","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yvan","family":"Saeys","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7468-974X","authenticated-orcid":false,"given":"Dirk","family":"Elewaut","sequence":"additional","affiliation":[{"name":"Vlaams Instituut voor Biotechnologie \u2010 Universiteit Gent (VIB\u2010UGent), Ghent\u2010Zwijnaarde, and Ghent University Hospital  Ghent Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,11,10]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2014-206971"},{"key":"e_1_2_7_3_1","unstructured":"OECD Data.Magnetic resonance imaging (MRI) exams (indicator).2022. Accessed June 27 2022.https:\/\/data.oecd.org\/healthcare\/magnetic-resonance-imaging-mri-exams.htm"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.40475"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2020-217095"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.21445"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keab099"},{"key":"e_1_2_7_8_1","first-page":"2050","article-title":"Scoring sacroiliac joints by magnetic resonance imaging. A multiple\u2010reader reliability experiment","volume":"32","author":"Landew\u00e9 RB","year":"2005","journal-title":"J Rheumatol"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kez375"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.07.007"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-021-02484-0"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s42358-020-00126-8"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11071156"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2021.05.005"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00296-020-04511-w"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keab887"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.42145"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-015-0729-8"},{"key":"e_1_2_7_19_1","first-page":"202","article-title":"How sensitive and specific are MRI features of sacroiliitis for diagnosis of spondyloarthritis in patients with inflammatory back pain?","volume":"97","author":"Jans L","year":"2014","journal-title":"JBR\u2010BTR"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0582-9"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.03815"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab99e5"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2015-208642"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.01365"},{"key":"e_1_2_7_30_1","first-page":"12272","volume-title":"2020 IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang Y","year":"2020"},{"key":"e_1_2_7_31_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems 25 (NIPS 2012)","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_7_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keac059"}],"container-title":["Arthritis &amp; Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.42650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T19:33:21Z","timestamp":1759952001000},"score":1,"resource":{"primary":{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/10.1002\/art.42650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,10]]},"references-count":33,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10.1002\/art.42650"],"URL":"https:\/\/doi.org\/10.1002\/art.42650","archive":["Portico"],"relation":{},"ISSN":["2326-5191","2326-5205"],"issn-type":[{"value":"2326-5191","type":"print"},{"value":"2326-5205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,10]]},"assertion":[{"value":"2022-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}