{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T06:05:55Z","timestamp":1791871555295,"version":"4.3.4"},"reference-count":65,"publisher":"SAGE Publications","issue":"9","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"the University-level Key Project of Ningxia Medical University","award":["XZ2024034"],"award-info":[{"award-number":["XZ2024034"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Acta Radiol"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Deep learning (DL) has been increasingly applied to grade knee osteoarthritis (KOA) on radiographs, but reported diagnostic performance varies across Kellgren\u2013Lawrence (K\u2013L) grades.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To systematically evaluate the diagnostic performance of DL models for radiographic KOA grading.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and Methods<\/jats:title>\n                    <jats:p>\n                      PubMed, Embase, and Web of Science were searched through November 2024 for studies using DL algorithms to grade KOA on X-ray images. Sensitivity and precision were synthesized. Heterogeneity was assessed using the\n                      <jats:italic toggle=\"yes\">I<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      statistic. Subgroup analyses and meta-regression were conducted according to transfer learning, external validation, multi-task learning, joint training strategy, and data splitting. Publication bias was assessed using funnel plots and Egger's test. Study quality was evaluated using the revised QUADAS-2 tool.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of 1004 records screened, 32 studies were included. Pooled sensitivity for K\u2013L grades 0\u20134 was 0.90, 0.66, 0.80, 0.87, and 0.88, respectively, and pooled precision was 0.87, 0.71, 0.81, 0.86, and 0.91, respectively. Diagnostic performance was poorest for K\u2013L grade 1, particularly in sensitivity, indicating limited reliability for early-stage KOA detection. Heterogeneity was high across outcomes and grades, particularly for sensitivity in K\u2013L grades 1 and 2 and precision in K\u2013L grades 0 and 1. Meta-regression identified transfer learning and data splitting as potential sources of heterogeneity. Egger's tests suggested no statistically significant small-study effects.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DL models showed better diagnostic performance for moderate-to-severe radiographic KOA than for early-stage disease. However, the poor sensitivity for K\u2013L grade 1, substantial heterogeneity, and limited external validation suggest that current DL models are not yet reliable for early KOA detection or ready for routine clinical implementation. Further standardized reporting, robust validation, and multicenter external evaluation are required.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/02841851261462501","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:45:08Z","timestamp":1784209508000},"page":"723-736","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Diagnostic performance of deep-learning algorithms in radiographic grading of knee osteoarthritis: a systematic review and meta-analysis"],"prefix":"10.1177","volume":"67","author":[{"given":"Xiaolu","family":"Ren","sequence":"first","affiliation":[{"name":"Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan, PR China"},{"name":"School of Health Sciences, Universiti Sains Malaysia, Kubang Kerian, Kelantan, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Second Affiliated Hospital of Zhejiang University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhiJun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan, PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8930-2476","authenticated-orcid":false,"given":"Ting","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan, PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.22171"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2020.100587"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMcp1903768"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1002\/msc.1536"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-019-02227-y"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1136\/ard.16.4.494"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12102362"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Ren X Hou L Liu S et al. OA-MEN: A fusion deep learning approach for enhanced accuracy in knee osteoarthritis detection and classification using X-ray imaging. Front Bioeng Biotechnol 2025;12:1437188.","DOI":"10.3389\/fbioe.2024.1437188"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109944"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2019.02.391"},{"key":"e_1_3_2_12_2","first-page":"40\u201357","article-title":"Visualizing preosteoarthritis: updates on UTE-based compositional MRI and deep learning algorithms","author":"Sun D","year":"2025","unstructured":"Sun D, Wu G, Zhang W, et al. Visualizing preosteoarthritis: updates on UTE-based compositional MRI and deep learning algorithms. J Magn Reson Imaging 2025;62:40\u201357.","journal-title":"J Magn Reson Imaging"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22041552"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00438-z"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128740"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Antony J McGuinness K Moran K et al. Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. In: Perner P editor. Machine Learning and Data Mining in Pattern Recognition. MLDM 2017. Lecture Notes in Computer Science. Vol. 10358. Cham: Springer 2017 pp.376\u2013390.","DOI":"10.1007\/978-3-319-62416-7_27"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2018.02.845"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2019.06.002"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02096-9"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190065"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9103341"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006335"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10529-3"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-021-04722-7"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21186189"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104334"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Mikhaylichenko A Demyanenko Y. Automatic grading of knee osteoarthritis from plain radiographs using densely connected convolutional networks. In: Recent Trends in Analysis of Images Social Networks and Texts. AIST 2020 Revised Supplementary Proceedings. 2021:149\u2013161.","DOI":"10.1007\/978-3-030-71214-3_13"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10557-0"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-022-01476-7"},{"key":"e_1_3_2_30_2","first-page":"1126","article-title":"Recognition of knee osteoarthritis (KOA) using YOLOv2 and classification based on convolutional neural network","volume":"12","author":"Yunus U","year":"2022","unstructured":"Yunus U, Amin J, Sharif M, et al. Recognition of knee osteoarthritis (KOA) using YOLOv2 and classification based on convolutional neural network. Life (Basel) 2022;12:1126.","journal-title":"Life (Basel)"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13018-022-03429-2"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12079"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10857-y"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3247502"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13091609"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13081380"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276810"},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Dharmani BC Khatri K. Dharmani BC et al. Deep learning for knee osteoarthritis severity stage detection using X-ray images. In: 2023 15th International Conference on Communication Systems & Networks (COMSNETS). Bangalore India 2023 pp.78\u201383.","DOI":"10.1109\/COMSNETS56262.2023.10041355"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22845"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15484-w"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13081385"},{"key":"e_1_3_2_42_2","first-page":"475","article-title":"Knee osteoarthritis prediction driven by deep learning and the kellgren-lawrence grading","volume":"5","author":"Kishore VV","year":"2023","unstructured":"Kishore VV, Batthala S, Chamarthi JV, et al. Knee osteoarthritis prediction driven by deep learning and the kellgren-lawrence grading. Proc Eng Sci 2023;5:475\u2013484.","journal-title":"Proc Eng Sci"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.21037\/qims-22-1250"},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Sinha V Veemaraj E. Sinha V et al. Knee osteoarthritis detection using X-rays and DNN. In: 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC) 2024 pp.467\u2013472.","DOI":"10.1109\/ICAAIC60222.2024.10575881"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14100993"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.3928\/01477447-20240718-02"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1177\/1947603519888793"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.2174\/1874120701307010018"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1186\/s43019-024-00228-3"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-20132-7"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-50210-4"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Kondal S Kulkarni V Gaikwad A et al. Automatic grading of knee osteoarthritis on the Kellgren-Lawrence scale from radiographs using convolutional neural networks. In: Advances in Deep Learning Artificial Intelligence and Robotics. ICDLAIR 2020. Lecture Notes in Networks and Systems. Vol. 249. Cham: Springer 2022 pp.163\u2013173.","DOI":"10.1007\/978-3-030-85365-5_16"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Akila SM Imanov E Almezhghwi K et al. Analysis of knee osteoarthritis grading using deep learning. In: 15th International Conference on Applications of Fuzzy Systems Soft Computing and Artificial Intelligence Tools \u2013 ICAFS-2022. Lecture Notes in Networks and Systems. Vol. 590. Cham: Springer 2022 pp.435\u2013443.","DOI":"10.1007\/978-3-031-25252-5_58"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-024-00437-5"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joca.2023.09.011"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-10928-9"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-021-04551-4"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1093\/jge\/gxac101"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2019.06.001"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.3390\/su15075930"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10134523"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00663"},{"key":"e_1_3_2_63_2","first-page":"1515","article-title":"Supplementary materials: weighted leave-one-out cross validation","volume":"11","author":"Pronzato L","year":"2023","unstructured":"Pronzato L, Rendas MJ. Supplementary materials: weighted leave-one-out cross validation. SIAM ASA J Uncertain Quantif 2023;11:1515\u20131543.","journal-title":"SIAM ASA J Uncertain Quantif"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12293-020-00316-3"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3015859"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1017\/S1049023X19003273"}],"container-title":["Acta Radiologica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851261462501","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02841851261462501","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02841851261462501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T10:47:41Z","timestamp":1788432461000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02841851261462501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":65,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1177\/02841851261462501"],"URL":"https:\/\/doi.org\/10.1177\/02841851261462501","relation":{},"ISSN":["0284-1851","1600-0455"],"issn-type":[{"value":"0284-1851","type":"print"},{"value":"1600-0455","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]}}}