{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T09:08:37Z","timestamp":1790759317930,"version":"4.1.0"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004336","name":"Novartis","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004336","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate the performance of machine learning (ML) models for the automated scoring of spinal MRI bone marrow oedema (BMO) in patients with axial spondyloarthritis (axSpA) and compare them with expert scoring.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>ML algorithms using SpineNet software were trained and validated on 3483 spinal MRIs from 686 axSpA patients across two clinical trial datasets. The scoring pipeline involved (i) detection and labelling of vertebral bodies and (ii) classification of vertebral units for the presence or absence of BMO. Two models were tested: Model 1, without manual segmentation, and Model 2, incorporating an intermediate manual segmentation step. Model outputs were compared with those of human experts using kappa statistics, balanced accuracy, sensitivity, specificity and AUC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Both models performed comparably to expert readers, regarding presence vs absence of BMO. Model 1 outperformed Model 2, with an AUC of 0.94 (vs 0.88), accuracy of 75.8% (vs 70.5%) and kappa of 0.50 (vs 0.31) using absolute reader consensus scoring as the external reference; this performance was similar to the expert inter-reader accuracy of 76.8% and kappa of 0.47 in a radiographic axSpA dataset. In a non-radiographic axSpA dataset, Model 1 achieved an AUC of 0.97 (vs 0.91 for Model 2), accuracy of 74.6% (vs 70%) and kappa of 0.52 (vs 0.27), comparable to the expert inter-reader accuracy of 74.2% and kappa of 0.46.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML software shows potential for automated MRI BMO assessment in axSpA, offering benefits such as improved consistency, reduced labour costs and minimized inter- and intra-reader variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration<\/jats:title>\n                    <jats:p>Clinicaltrials.gov, http:\/\/clinicaltrials.gov, MEASURE 1 study (NCT01358175); PREVENT study (NCT02696031).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/rheumatology\/keaf323","type":"journal-article","created":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T07:41:31Z","timestamp":1749282091000},"page":"5446-5454","source":"Crossref","is-referenced-by-count":6,"title":["Automated detection of spinal bone marrow oedema in axial spondyloarthritis: training and validation using two large phase 3 trial datasets"],"prefix":"10.1093","volume":"64","author":[{"given":"Amir","family":"Jamaludin","sequence":"first","affiliation":[{"name":"Visual Geometry Group, Department of Engineering Science, University of Oxford , Oxford,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rhydian","family":"Windsor","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, Department of Engineering Science, University of Oxford , Oxford,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarim","family":"Ather","sequence":"additional","affiliation":[{"name":"Oxford University Hospitals NHS Foundation Trust , Oxford,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timor","family":"Kadir","sequence":"additional","affiliation":[{"name":"Selka Health , Oxforrd,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, Department of Engineering Science, University of Oxford , Oxford,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juergen","family":"Braun","sequence":"additional","affiliation":[{"name":"Rheuma Praxis Berlin , Berlin,","place":["Germany"]},{"name":"Ruhr-Universit\u00e4t Bochum , Bochum,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6314-5336","authenticated-orcid":false,"given":"Lianne S","family":"Gensler","sequence":"additional","affiliation":[{"name":"Division of Rheumatology, University of California San Francisco , San Francisco, CA,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3690-467X","authenticated-orcid":false,"given":"Mikkel","family":"\u00d8stergaard","sequence":"additional","affiliation":[{"name":"Copenhagen Centre for Arthritis Research, Centre for Rheumatology and Spine Diseases, Rigshospitalet , Glostrup,","place":["Denmark"]},{"name":"Department of Clinical Medicine, University of Copenhagen , Copenhagen,","place":["Denmark"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4537-6015","authenticated-orcid":false,"given":"Denis","family":"Poddubnyy","sequence":"additional","affiliation":[{"name":"Division of Rheumatology, Department of Medicine, University Health Network and University of Toronto , Toronto,","place":["Canada"]},{"name":"Department of Gastroenterology, Infectiology and Rheumatology (including Nutrition Medicine), Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, corporate member of Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin , Berlin,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thibaud","family":"Coroller","sequence":"additional","affiliation":[{"name":"Novartis Pharmaceuticals Corporation , East Hanover, NJ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Porter","sequence":"additional","affiliation":[{"name":"Novartis Pharmaceuticals Corporation , East Hanover, NJ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Ligozio","sequence":"additional","affiliation":[{"name":"Novartis Pharmaceuticals Corporation , East Hanover, NJ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aimee","family":"Readie","sequence":"additional","affiliation":[{"name":"Novartis Pharmaceuticals Corporation , East Hanover, NJ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8411-7972","authenticated-orcid":false,"given":"Pedro M","family":"Machado","sequence":"additional","affiliation":[{"name":"Department of Neuromuscular Diseases, UCL Queen Square Institute of Neurology, University College London , London,","place":["UK"]},{"name":"National Institute for Health Research (NIHR), University College London Hospitals Biomedical Research Centre , London,","place":["UK"]},{"name":"Department of Rheumatology, Northwick Park Hospital, London North West University Healthcare NHS Trust , London,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"2025100315120517500_keaf323-B1","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1136\/annrheumdis-2021-222081","article-title":"MRI lesions of the spine in patients with axial spondyloarthritis: an update of lesion definitions and validation by the ASAS MRI working group","volume":"81","author":"Baraliakos","year":"2022","journal-title":"Ann Rheum Dis"},{"key":"2025100315120517500_keaf323-B2","doi-asserted-by":"crossref","first-page":"4778","DOI":"10.1093\/rheumatology\/keab099","article-title":"Data-driven definitions for active and structural MRI lesions in the sacroiliac joint in spondyloarthritis and their predictive utility","volume":"60","author":"Maksymowych","year":"2021","journal-title":"Rheumatology (Oxford)"},{"key":"2025100315120517500_keaf323-B3","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1177\/1759720X11436240","article-title":"Imaging in ankylosing spondylitis","volume":"4","author":"Ostergaard","year":"2012","journal-title":"Ther Adv Musculoskelet Dis"},{"key":"2025100315120517500_keaf323-B4","doi-asserted-by":"crossref","first-page":"658538","DOI":"10.3389\/fmed.2021.658538","article-title":"Axial spondyloarthritis: mimics and pitfalls of imaging assessment","volume":"8","author":"Caetano","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"2025100315120517500_keaf323-B5","volume-title":"Diagnosis of bone and joint disorders","author":"Resnick","year":"1995","edition":"3rd edn"},{"key":"2025100315120517500_keaf323-B6","first-page":"862","article-title":"Scoring inflammatory activity of the spine by magnetic resonance imaging in ankylosing spondylitis: a multireader experiment","volume":"34","author":"Lukas","year":"2007","journal-title":"J Rheumatol"},{"key":"2025100315120517500_keaf323-B7","doi-asserted-by":"crossref","first-page":"ii1","DOI":"10.1136\/ard.2008.104018","article-title":"The Assessment of SpondyloArthritis international Society (ASAS) handbook: a guide to assess spondyloarthritis","volume":"68(Suppl 2)","author":"Sieper","year":"2009","journal-title":"Ann Rheum Dis"},{"key":"2025100315120517500_keaf323-B8","doi-asserted-by":"crossref","first-page":"l886","DOI":"10.1136\/bmj.l886","article-title":"Clinical applications of machine learning algorithms: beyond the black box","volume":"364","author":"Watson","year":"2019","journal-title":"BMJ"},{"key":"2025100315120517500_keaf323-B9","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1164\/rccm.201903-0505OC","article-title":"Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules","volume":"202","author":"Massion","year":"2020","journal-title":"Am J Respir Crit Care Med"},{"key":"2025100315120517500_keaf323-B10","doi-asserted-by":"crossref","first-page":"811","DOI":"10.3174\/ajnr.A4173","article-title":"Systematic literature review of imaging features of spinal degeneration in asymptomatic populations","volume":"36","author":"Brinjikji","year":"2015","journal-title":"AJNR Am J Neuroradiol"},{"key":"2025100315120517500_keaf323-B11","doi-asserted-by":"crossref","first-page":"2721","DOI":"10.1007\/s00586-016-4654-6","article-title":"Intervertebral disc classification by its degree of degeneration from T2-weighted magnetic resonance images","volume":"25","author":"Castro-Mateos","year":"2016","journal-title":"Eur Spine J"},{"key":"2025100315120517500_keaf323-B12","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.1007\/s00586-017-4956-3","article-title":"ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist","volume":"26","author":"Jamaludin","year":"2017","journal-title":"Eur Spine J"},{"key":"2025100315120517500_keaf323-B13","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.media.2017.07.002","article-title":"SpineNet: automated classification and evidence visualization in spinal MRIs","volume":"41","author":"Jamaludin","year":"2017","journal-title":"Med Image Anal"},{"key":"2025100315120517500_keaf323-B14","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1007\/s00296-020-04511-w","article-title":"The semi-automated algorithm for the detection of bone marrow oedema lesions in patients with axial spondyloarthritis","volume":"40","author":"Kucyba\u0142a","year":"2020","journal-title":"Rheumatol Int"},{"key":"2025100315120517500_keaf323-B15","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1007\/s00296-018-4104-3","article-title":"Development and validation of SCAISS, a tool for semi-automated quantification of sacroilitis by magnetic resonance in spondyloarthritis","volume":"38","author":"Zarco","year":"2018","journal-title":"Rheumatol Int"},{"key":"2025100315120517500_keaf323-B16","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1136\/annrheumdis-2021-eular.864","article-title":"POS0958: responsiveness of conventional, semi-automatic and full-automatic methods to quantify marrow bone edema lesions in mri of axial spondyloarthritis patients: a pilot study","volume":"80","author":"Garrido-Gonz\u00e1lez","year":"2021","journal-title":"Ann Rheum Dis"},{"key":"2025100315120517500_keaf323-B17","doi-asserted-by":"crossref","first-page":"4852","DOI":"10.3390\/jcm12144852","article-title":"Performance of fully automated algorithm detecting bone marrow edema in sacroiliac joints","volume":"12","author":"O\u017cga","year":"2023","journal-title":"J Clin Med"},{"key":"2025100315120517500_keaf323-B18","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/j.bbe.2021.05.005","article-title":"Fully automated algorithm for the detection of bone marrow oedema lesions in patients with axial spondyloarthritis\u2014Feasibility study","volume":"41","author":"Rzecki","year":"2021","journal-title":"Biocybernet and Biomedical Engineering"},{"key":"2025100315120517500_keaf323-B19","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1148\/radiol.212526","article-title":"Deep learning detects changes indicative of axial spondyloarthritis at MRI of sacroiliac joints","volume":"305","author":"Bressem","year":"2022","journal-title":"Radiology"},{"key":"2025100315120517500_keaf323-B20","doi-asserted-by":"crossref","first-page":"1278247","DOI":"10.3389\/fimmu.2023.1278247","article-title":"Artificial intelligence for the detection of sacroiliitis on magnetic resonance imaging in patients with axial spondyloarthritis","volume":"14","author":"Lee","year":"2023","journal-title":"Front Immunol"},{"key":"2025100315120517500_keaf323-B21","author":"Nicolaes","year":"2024"},{"key":"2025100315120517500_keaf323-B22","doi-asserted-by":"crossref","first-page":"4125","DOI":"10.1007\/s00586-023-08099-0","article-title":"A deep neural network for MRI spinal inflammation in axial spondyloarthritis","volume":"33","author":"Lin","year":"2024","journal-title":"Eur Spine J"},{"key":"2025100315120517500_keaf323-B23","doi-asserted-by":"crossref","first-page":"14993","DOI":"10.1038\/s41598-024-64580-w","article-title":"Automated detection, labelling and radiological grading of clinical spinal MRIs","volume":"14","author":"Windsor","year":"2024","journal-title":"Sci Rep"},{"key":"2025100315120517500_keaf323-B24","doi-asserted-by":"crossref","first-page":"2534","DOI":"10.1056\/NEJMoa1505066","article-title":"Secukinumab, an Interleukin-17A Inhibitor, in Ankylosing Spondylitis","volume":"373","author":"Baeten","year":"2015","journal-title":"N Engl J Med"},{"key":"2025100315120517500_keaf323-B25","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1002\/art.41477","article-title":"Improvement of signs and symptoms of nonradiographic axial spondyloarthritis in patients treated with secukinumab: primary results of a randomized, placebo-controlled phase III study","volume":"73","author":"Deodhar","year":"2021","journal-title":"Arthritis Rheumatol"},{"key":"2025100315120517500_keaf323-B26","first-page":"712","author":"Windsor","year":"2020"},{"key":"2025100315120517500_keaf323-B27","first-page":"234","author":"Ronneberger","year":"2015"},{"key":"2025100315120517500_keaf323-B28","first-page":"770","author":"He","year":"2016"}],"container-title":["Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/rheumatology\/advance-article-pdf\/doi\/10.1093\/rheumatology\/keaf323\/63458108\/keaf323.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/rheumatology\/article-pdf\/64\/10\/5446\/63458108\/keaf323.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/rheumatology\/article-pdf\/64\/10\/5446\/63458108\/keaf323.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T19:12:18Z","timestamp":1759518738000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/rheumatology\/article\/64\/10\/5446\/8159075"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":28,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,6,9]]},"published-print":{"date-parts":[[2025,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/rheumatology\/keaf323","relation":{},"ISSN":["1462-0324","1462-0332"],"issn-type":[{"value":"1462-0324","type":"print"},{"value":"1462-0332","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,10]]},"published":{"date-parts":[[2025,6,9]]}}}