{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:57:41Z","timestamp":1781045861715,"version":"3.54.1"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>To develop and validate a radiograph-only deep learning framework that jointly predicts magnetic resonance imaging (MRI)-defined early structural pathology in knees with early radiographic osteoarthritis (Kellgren-Lawrence [KL] grades 0-1) and performs full-spectrum KL classification across all grades within a single multi-task architecture.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study used baseline data from the Osteoarthritis Initiative (OAI) comprising 8260 knees (4130 participants). A multi-task ConvNeXt-Base network was trained with five-fold stratified group cross-validation enforcing strict subject-level data separation. KL classification was supervised across all knees. MRI prediction heads were activated only for KL 0\u20131 knees with available labels. MRI Osteoarthritis Knee Score (MOAKS)-derived binary endpoints were defined at a threshold of \u22652: tibiofemoral cartilage damage (primary endpoint) and meniscal morphology damage (secondary endpoint).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>KL grading performance across held-out folds was as follows: mean quadratic weighted kappa (QWK) 0.8284 (standard deviation [SD] 0.0255), balanced accuracy 0.6836 (SD 0.0159). In KL0\/1 knees with both MRI labels (n = 2561), prevalence was 31.3% for cartilage damage and 26.4% for meniscal damage. Mean AUROC\/AUPRC were 0.7329 (SD 0.0203)\/0.5741 (SD 0.0364) for cartilage damage and 0.7193 (SD 0.0533)\/0.5147 (SD 0.0719) for meniscal damage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>A leakage-controlled multi-task radiograph model achieved strong KL grading agreement and moderate discrimination of MRI-defined cartilage and meniscal pathology in knees with early radiographic osteoarthritis, supporting a potential role as an assistive triage signal to identify patients who may benefit from earlier MRI evaluation. However, clinical correlation remains essential; MRI referral decisions should always be made in the context of the individual patient\u2019s symptoms, functional impairment, and overall clinical assessment, and cannot be based on AI-derived probability scores alone.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1858407","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:10:19Z","timestamp":1781043019000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Standard knee radiographs enable deep learning inference of MRI-defined cartilage and meniscal damage in early knee osteoarthritis: a study using the osteoarthritis initiative database"],"prefix":"10.3389","volume":"17","author":[{"given":"Tariq","family":"Alkhatatbeh","sequence":"first","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Alkhatatbeh","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, The First Affiliated Hospital of Shantou University Medical College","place":["Shantou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongfeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Information Management, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery, Center for Orthopaedic Surgery, The Third Affiliated Hospital of Southern Medical University, Academy of Orthopedics","place":["Guangzhou, Guangdong, China"]},{"name":"Orthopedic Hospital of Guangdong Province","place":["Guangzhou, Guangdong, China"]},{"name":"Guangdong Provincial Key Laboratory of Bone and Joint Degeneration Diseases","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200165","article-title":"Automatic deep learning\u2013assisted detection and grading of abnormalities in knee MRI studies","volume":"3","author":"Astuto","year":"2021","journal-title":"Radiology: Artif. Intell."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.233341","article-title":"Interobserver agreement and performance of concurrent AI assistance for radiographic evaluation of knee osteoarthritis","volume":"312","author":"Brejneb\u00f8l","year":"2024","journal-title":"Radiology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1002\/art.42982","article-title":"Do existing magnetic resonance imaging definitions of knee osteoarthritis identify knees that will develop clinically significant disease over up to 11 years of follow\u2010up","volume":"77","author":"Chang","year":"2025","journal-title":"Arthritis Rheumatol."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocarto.2025.100733","article-title":"Magnetic resonance imaging-defined knee osteoarthritis rarely occurs without cartilage damage","volume":"8","author":"Chang","year":"2026","journal-title":"Osteoarthritis Cartilage Open"},{"key":"B5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1097\/jcma.0000000000001333","article-title":"Deep learning in detecting bucket-handle meniscal tears on knee radiographs: Comparison with surgeon interpretations","volume":"89","author":"Chen","year":"2026","journal-title":"J. Chin. Med. Assoc."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1007\/s00256-020-03410-2","article-title":"Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference","volume":"49","author":"Fritz","year":"2020","journal-title":"Skeletal Radiol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1002\/ksa.12369","article-title":"Achieving high accuracy in meniscus tear detection using advanced deep learning models with a relatively small data set","volume":"33","author":"G\u00fcng\u00f6r","year":"2025","journal-title":"Knee Surg. Sports Traumatol. Arthrosc."},{"key":"B8","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1007\/s00256-023-04296-6","article-title":"Deep learning applications in osteoarthritis imaging","volume":"52","author":"Kijowski","year":"2023","journal-title":"Skeletal Radiol."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.15154\/64DX-3822","article-title":"Osteoarthritis initiative","author":"Lester","year":"2016"},{"key":"B10","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.ejmp.2021.02.010","article-title":"Meniscal lesion detection and characterization in adult knee MRI: A deep learning model approach with external validation","volume":"83","author":"Rizk","year":"2021","journal-title":"Physica Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.diii.2019.02.007","article-title":"Artificial intelligence to diagnose meniscus tears on MRI","volume":"100","author":"Roblot","year":"2019","journal-title":"Diagn. Interventional Imaging"},{"key":"B12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.joca.2021.04.018","article-title":"State of the art: Imaging of osteoarthritis\u2014revisited 2020","volume":"296","author":"Roemer","year":"2020","journal-title":"Radiology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1016\/j.joca.2014.02.032","article-title":"Imaging in osteoarthritis","volume":"30","author":"Roemer","year":"2022","journal-title":"Osteoarthritis Cartilage"},{"key":"B14","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1056\/nejmcp1903768","article-title":"Osteoarthritis of the knee","volume":"384","author":"Sharma","year":"2021","journal-title":"N. Engl. J. Med."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104334","article-title":"Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists","volume":"133","author":"Swiecicki","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1016\/j.joca.2020.02.480","article-title":"Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks","volume":"10","author":"Tiulpin","year":"2020","journal-title":"Diagnostics"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocarto.2025.100580","article-title":"Kellgren-Lawrence grading of knee osteoarthritis using deep learning: Diagnostic performance with external dataset and comparison with four readers","volume":"7","author":"Vaattovaara","year":"2025","journal-title":"Osteoarthritis Cartilage Open"},{"key":"B18","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/s00330-024-10928-9","article-title":"The value of deep learning-based X-ray techniques in detecting and classifying K-L grades of knee osteoarthritis: a systematic review and meta-analysis","volume":"35","author":"Zhao","year":"2024","journal-title":"Eur. Radiol."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1858407\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:10:20Z","timestamp":1781043020000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1858407\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":18,"alternative-id":["10.3389\/fphys.2026.1858407"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1858407","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"article-number":"1858407"}}