{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:18:58Z","timestamp":1789564738700,"version":"build-2803163510"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Ultrasonography (US) is useful for soft tissue delineation, but its diagnostic objectivity is limited by surgeon dependency and lack of guidelines. Diagnostic support based on deep learning may overcome these issues, and integrating demographic factors (age, sex, and body mass index [BMI]) may improve accuracy. However, multimodal convolutional neural network (CNN) models incorporating these factors have not been fully investigated for knee osteoarthritis (OA). In this study, we developed such a model and evaluated its usefulness for diagnosis and severity classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed image-only and multimodal CNN models using 11 architectures pre-trained on ImageNet. OA severity was classified based on Kellgren\u2013Lawrence grades. Diagnostic performance was assessed using the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among 491 limbs, 318 were diagnosed with OA. For diagnosing knee OA, a statistically significant improvement in performance of the multimodal model compared with the image-only model was observed only for AlexNet (AUC: 0.87 to 0.89,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.036). No significant differences were observed between the models for other architectures, with differences in sensitivity, specificity, and F1 score remaining within 1\u20133%. SHapley Additive exPlanations analysis indicated that the contributions of age, sex, and BMI were generally small, and model predictions were predominantly driven by imaging features. In the stepwise evaluation, ResNet50 (image-only model) showed the highest sensitivity and NPV in the initial screening step (Step 1; 80% and 68%, respectively). For supplemental re-evaluation, ResNet152 and GoogLeNet demonstrated high specificity and PPV (96% and 97%, respectively). In severity classification among OA-positive cases (Step 2), VGG16 achieved the highest sensitivity and NPV (94% and 96%), whereas ResNet50 showed relatively high specificity and PPV (89% and 79%) for definitive diagnostic support following severity classification.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>CNN models using only US images demonstrated high diagnostic performance for knee OA. The addition of background factors provided limited benefit, suggesting that image-only models are sufficient for diagnostic support.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration<\/jats:title>\n                    <jats:p>\n                      This study was registered with the UMIN Clinical Trials Registration System:\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/center6.umin.ac.jp\/cgi-open-bin\/ctr\/ctr_view.cgi?recptno=R000056245\" ext-link-type=\"uri\">https:\/\/center6.umin.ac.jp\/cgi-open-bin\/ctr\/ctr_view.cgi?recptno=R000056245<\/jats:ext-link>\n                      ; Trial Registration Number: UMIN000049395; Registration date: 2022\/11\/01.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-026-02249-8","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:46:19Z","timestamp":1775097979000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal model integrating ultrasound and demographic data for the diagnosis of knee osteoarthritis"],"prefix":"10.1186","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7905-7453","authenticated-orcid":false,"given":"Takeharu","family":"Kiso","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukinori","family":"Okada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoru","family":"Kawata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kouta","family":"Shichiji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiichiro","family":"Okumura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noritaka","family":"Hatsumi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryohei","family":"Matsuura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaki","family":"Kaminaga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hikaru","family":"Kuwano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erika","family":"Okumura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Narumi","family":"Nonoura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"2249_CR1","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1001\/jama.2023.19675","volume":"330","author":"V Duong","year":"2023","unstructured":"Duong V, Oo WM, Ding C, Culvenor AG, Hunter DJ. Evaluation and treatment of knee pain: a review. JAMA. 2023;330:1568\u201380. https:\/\/doi.org\/10.1001\/jama.2023.19675.","journal-title":"JAMA"},{"key":"2249_CR2","first-page":"786","volume":"61","author":"MN Iqbal","year":"2011","unstructured":"Iqbal MN, Haidri FR, Motiani B, Mannan A. Frequency of factors associated with knee osteoarthritis. J Pak Med Assoc. 2011;61:786\u20139.","journal-title":"J Pak Med Assoc"},{"key":"2249_CR3","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1002\/msc.1814","volume":"21","author":"K Obara","year":"2023","unstructured":"Obara K, Cardoso JR, Reis BM, Matos MA, Kawano MM. Quality of life in individuals with knee osteoarthritis versus asymptomatic individuals. Musculoskelet Care. 2023;21:1364\u201370. https:\/\/doi.org\/10.1002\/msc.1814.","journal-title":"Musculoskelet Care"},{"key":"2249_CR4","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s12955-023-02133-x","volume":"21","author":"J Chang","year":"2023","unstructured":"Chang J, Yuan Y, Fu M, Wang D. Health-related quality of life among patients with knee osteoarthritis in Guangzhou, China: a multicenter cross-sectional study. Health Qual Life Outcomes. 2023;21:50. https:\/\/doi.org\/10.1186\/s12955-023-02133-x.","journal-title":"Health Qual Life Outcomes"},{"key":"2249_CR5","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1186\/s12891-020-03367-2","volume":"21","author":"JB Driban","year":"2020","unstructured":"Driban JB, Harkey MS, Barbe MF, Ward RJ, MacKay JW, Davis JE, et al. Risk factors and the natural history of accelerated knee osteoarthritis: a narrative review. BMC Musculoskelet Disord. 2020;21:332. https:\/\/doi.org\/10.1186\/s12891-020-03367-2.","journal-title":"BMC Musculoskelet Disord"},{"key":"2249_CR6","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.joca.2025.03.003","volume":"33","author":"V Duong","year":"2025","unstructured":"Duong V, Abdel Shaheed C, Ferreira ML, Narayan SW, Venkatesha V, Hunter DJ, et al. Risk factors for the development of knee osteoarthritis across the lifespan: a systematic review and meta-analysis. Osteoarthr Cartil. 2025;33:1162\u201379. https:\/\/doi.org\/10.1016\/j.joca.2025.03.003.","journal-title":"Osteoarthr Cartil"},{"key":"2249_CR7","doi-asserted-by":"publisher","first-page":"12335","DOI":"10.1038\/s41598-024-63291-6","volume":"14","author":"H Deng","year":"2024","unstructured":"Deng H, Chen Z, Kang J, Liu J, Chen S, Li M, et al. The mediating role of synovitis in meniscus pathology and knee osteoarthritis radiographic progression. Sci Rep. 2024;14:12335. https:\/\/doi.org\/10.1038\/s41598-024-63291-6.","journal-title":"Sci Rep"},{"key":"2249_CR8","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.1016\/j.joca.2021.06.012","volume":"29","author":"BAM Snoeker","year":"2021","unstructured":"Snoeker BAM, Ishijima M, Kumm J, Zhang F, Turkiewicz AT, Englund M. Are structural abnormalities on knee MRI associated with osteophyte development? Data from the osteoarthritis initiative. Osteoarthr Cartil. 2021;29:1701\u20138. https:\/\/doi.org\/10.1016\/j.joca.2021.06.012.","journal-title":"Osteoarthr Cartil"},{"key":"2249_CR9","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1002\/acr.23592","volume":"71","author":"LA MacFarlane","year":"2019","unstructured":"MacFarlane LA, Yang H, Collins JE, Guermazi A, Mandl LA, Levy BA, et al. Relationship between patient-reported swelling and magnetic resonance imaging-defined effusion-synovitis in patients with meniscus tears and knee osteoarthritis. Arthritis Care Res (Hoboken). 2019;71:385\u20139. https:\/\/doi.org\/10.1002\/acr.23592.","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"2249_CR10","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1093\/rheumatology\/keab020","volume":"60","author":"C-C Wang","year":"2021","unstructured":"Wang C-C, Wang C-T, Tsai K-L, Chou C-L, Chao J-K, Huang H-Y, et al. Effect of ultrasound-detected synovitis on therapeutic efficacy of hyaluronic acid injection for symptomatic knee osteoarthritis. Rheumatol (Oxf Engl). 2021;60:4486\u201394. https:\/\/doi.org\/10.1093\/rheumatology\/keab020.","journal-title":"Rheumatol (Oxf Engl)"},{"key":"2249_CR11","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1002\/acr.25205","volume":"76","author":"K Liu","year":"2024","unstructured":"Liu K, Li X, Weng Q, Wang Y, Wei J, Zeng C, et al. Diagnostic accuracy of ultrasound for assessment of synovial abnormalities among patients with knee pain: a meta-analysis. Arthritis Care Res (Hoboken). 2024;76:295\u2013303. https:\/\/doi.org\/10.1002\/acr.25205.","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"2249_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.2463\/mrms.rev.2021-0052","volume":"21","author":"M Banjar","year":"2022","unstructured":"Banjar M, Horiuchi S, Gedeon DN, Yoshioka H. Review of quantitative knee articular cartilage MR imaging. Magn Reson Med Sci. 2022;21:29\u201340. https:\/\/doi.org\/10.2463\/mrms.rev.2021-0052.","journal-title":"Magn Reson Med Sci"},{"key":"2249_CR13","doi-asserted-by":"publisher","first-page":"3913","DOI":"10.1007\/s10067-024-07171-4","volume":"43","author":"MAEME Menyawi","year":"2024","unstructured":"Menyawi MAEME, Gamal G, Abdelbadie H, Elgohary R. Assessment of validity, reliability, and feasibility of OMERACT ultrasound knee osteoarthritis scores in Egyptian patients with primary knee osteoarthritis. Clin Rheumatol. 2024;43:3913\u201323. https:\/\/doi.org\/10.1007\/s10067-024-07171-4.","journal-title":"Clin Rheumatol"},{"key":"2249_CR14","doi-asserted-by":"publisher","first-page":"270","DOI":"10.3899\/jrheum.191291","volume":"48","author":"WM Oo","year":"2021","unstructured":"Oo WM, Linklater JM, Bennell KL, Pryke D, Yu S, Fu K, et al. Are OMERACT knee osteoarthritis ultrasound scores associated with pain severity, other symptoms, and radiographic and magnetic resonance imaging findings? J Rheumatol. 2021;48:270\u20138. https:\/\/doi.org\/10.3899\/jrheum.191291.","journal-title":"J Rheumatol"},{"key":"2249_CR15","doi-asserted-by":"publisher","first-page":"161","DOI":"10.4137\/CMAMD.S38141","volume":"9","author":"M Mortada","year":"2016","unstructured":"Mortada M, Zeid A, Al-Toukhy MAEH, Ezzeldin N, Elgawish M. Reliability of a proposed ultrasonographic grading scale for severity of primary knee osteoarthritis. Clin Med Insights Arthritis Musculoskelet Disord. 2016;9:161\u20136. https:\/\/doi.org\/10.4137\/CMAMD.S38141.","journal-title":"Clin Med Insights Arthritis Musculoskelet Disord"},{"key":"2249_CR16","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1093\/rheumatology\/kew304","volume":"55","author":"T Okano","year":"2016","unstructured":"Okano T, Filippucci E, Di Carlo M, Draghessi A, Carotti M, Salaffi F, et al. Ultrasonographic evaluation of joint damage in knee osteoarthritis: feature-specific comparisons with conventional radiography. Rheumatol (Oxf Engl). 2016;55:2040\u20139. https:\/\/doi.org\/10.1093\/rheumatology\/kew304.","journal-title":"Rheumatol (Oxf Engl)"},{"key":"2249_CR17","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/s00776-013-0524-9","volume":"19","author":"S Yanagisawa","year":"2014","unstructured":"Yanagisawa S, Ohsawa T, Saito K, Kobayashi T, Yamamoto A, Takagishi K. Morphological evaluation and diagnosis of medial type osteoarthritis of the knee using ultrasound. J Orthop Sci. 2014;19:270\u20134. https:\/\/doi.org\/10.1007\/s00776-013-0524-9.","journal-title":"J Orthop Sci"},{"key":"2249_CR18","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1002\/jcu.23691","volume":"52","author":"T Kiso","year":"2024","unstructured":"Kiso T, Okada Y, Kawata S, Shichiji K, Okumura E, Hatsumi N, et al. Diagnostic accuracy of a novel ultrasound imaging index for knee osteoarthritis: evaluation of sensitivity, specificity, and predictive values. J Clin Ultrasound. 2024;52:687\u201399. https:\/\/doi.org\/10.1002\/jcu.23691.","journal-title":"J Clin Ultrasound"},{"key":"2249_CR19","doi-asserted-by":"publisher","first-page":"164518","DOI":"10.1155\/2010\/164518","volume":"2010","author":"S Ohrndorf","year":"2010","unstructured":"Ohrndorf S, Naumann L, Grundey J, Scheel T, Scheel AK, Werner C, et al. Is musculoskeletal ultrasonography an operator-dependent method or a fast and reliably teachable diagnostic tool? Interreader agreements of three ultrasonographers with different training levels. Int J Rheumatol. 2010;2010:164518. https:\/\/doi.org\/10.1155\/2010\/164518.","journal-title":"Int J Rheumatol"},{"key":"2249_CR20","doi-asserted-by":"publisher","first-page":"100649","DOI":"10.1016\/j.ejro.2025.100649","volume":"14","author":"T Kiso","year":"2025","unstructured":"Kiso T, Okada Y, Kawata S, Shichiji K, Okumura E, Hatsumi N, et al. Ultrasound-based radiomics and machine learning for enhanced diagnosis of knee osteoarthritis: evaluation of diagnostic accuracy, sensitivity, specificity, and predictive value. Eur J Radiol Open. 2025;14:100649. https:\/\/doi.org\/10.1016\/j.ejro.2025.100649.","journal-title":"Eur J Radiol Open"},{"key":"2249_CR21","doi-asserted-by":"publisher","first-page":"744","DOI":"10.3390\/jcm12030744","volume":"12","author":"M Neubauer","year":"2023","unstructured":"Neubauer M, Moser L, Neugebauer J, Raudner M, Wondrasch B, F\u00fchrer M, et al. Artificial-intelligence-aided radiographic diagnostic of knee osteoarthritis leads to a higher association of clinical findings with diagnostic ratings. J Clin Med. 2023;12:744. https:\/\/doi.org\/10.3390\/jcm12030744.","journal-title":"J Clin Med"},{"key":"2249_CR22","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1186\/s12891-021-04722-7","volume":"22","author":"S Olsson","year":"2021","unstructured":"Olsson S, Akbarian E, Lind A, Razavian AS, Gordon M. Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population. BMC Musculoskelet Disord. 2021;22:844. https:\/\/doi.org\/10.1186\/s12891-021-04722-7.","journal-title":"BMC Musculoskelet Disord"},{"key":"2249_CR23","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.3390\/diagnostics13081380","volume":"13","author":"AS Mohammed","year":"2023","unstructured":"Mohammed AS, Hasanaath AA, Latif G, Bashar A. Knee osteoarthritis detection and severity classification using residual neural networks on preprocessed X-ray images. Diagnostics (Basel). 2023;13:1380. https:\/\/doi.org\/10.3390\/diagnostics13081380.","journal-title":"Diagnostics (Basel)"},{"key":"2249_CR24","doi-asserted-by":"publisher","first-page":"22887","DOI":"10.1038\/s41598-023-50210-4","volume":"13","author":"S-W Pi","year":"2023","unstructured":"Pi S-W, Lee B-D, Lee MS, Lee HJ. Ensemble deep-learning networks for automated osteoarthritis grading in knee X-ray images. Sci Rep. 2023;13:22887. https:\/\/doi.org\/10.1038\/s41598-023-50210-4.","journal-title":"Sci Rep"},{"key":"2249_CR25","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1016\/j.joca.2019.02.800","volume":"27","author":"V Pedoia","year":"2019","unstructured":"Pedoia V, Lee J, Norman B, Link TM, Majumdar S. Diagnosing osteoarthritis from T2 maps using deep learning: an analysis of the entire osteoarthritis Initiative baseline cohort. Osteoarthr Cartil. 2019;27:1002\u201310. https:\/\/doi.org\/10.1016\/j.joca.2019.02.800.","journal-title":"Osteoarthr Cartil"},{"key":"2249_CR26","doi-asserted-by":"publisher","first-page":"3341","DOI":"10.3390\/jcm9103341","volume":"9","author":"DH Kim","year":"2020","unstructured":"Kim DH, Lee KJ, Choi D, Lee JI, Choi HG, Lee YS. Can additional patient information improve the diagnostic performance of deep learning for the interpretation of knee osteoarthritis severity. J Clin Med. 2020;9:3341. https:\/\/doi.org\/10.3390\/jcm9103341.","journal-title":"J Clin Med"},{"key":"2249_CR27","doi-asserted-by":"publisher","first-page":"932","DOI":"10.3390\/diagnostics10110932","volume":"10","author":"A Tiulpin","year":"2020","unstructured":"Tiulpin A, Saarakkala S. Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. Diagnostics (Basel). 2020;10:932. https:\/\/doi.org\/10.3390\/diagnostics10110932.","journal-title":"Diagnostics (Basel)"},{"key":"2249_CR28","doi-asserted-by":"publisher","first-page":"5196","DOI":"10.3390\/app11115196","volume":"11","author":"C Guida","year":"2021","unstructured":"Guida C, Zhang M, Shan J. Knee osteoarthritis classification using 3D CNN and MRI. Appl Sci. 2021;11:5196. https:\/\/doi.org\/10.3390\/app11115196.","journal-title":"Appl Sci"},{"key":"2249_CR29","doi-asserted-by":"publisher","first-page":"e0184059","DOI":"10.1371\/journal.pone.0184059","volume":"12","author":"P Burlina","year":"2017","unstructured":"Burlina P, Billings S, Joshi N, Albayda J. Automated diagnosis of myositis from muscle ultrasound: exploring the use of machine learning and deep learning methods. PLoS ONE. 2017;12:e0184059. https:\/\/doi.org\/10.1371\/journal.pone.0184059.","journal-title":"PLoS ONE"},{"key":"2249_CR30","doi-asserted-by":"publisher","first-page":"2143","DOI":"10.1007\/s11548-023-03040-8","volume":"19","author":"K Sasaki","year":"2024","unstructured":"Sasaki K, Fujita D, Takatsuji K, Kotoura Y, Minami M, Kobayashi Y, et al. Deep learning-based osteochondritis dissecans detection in ultrasound images with humeral capitellum localization. Int J Comput Assist Radiol Surg. 2024;19:2143\u201352. https:\/\/doi.org\/10.1007\/s11548-023-03040-8.","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2249_CR31","doi-asserted-by":"publisher","first-page":"h5527","DOI":"10.1136\/bmj.h5527","volume":"351","author":"PM Bossuyt","year":"2015","unstructured":"Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, et al. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ. 2015;351:h5527. https:\/\/doi.org\/10.1136\/bmj.h5527.","journal-title":"BMJ"},{"key":"2249_CR32","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1136\/annrheumdis-2019-216655","volume":"79","author":"JS Smolen","year":"2020","unstructured":"Smolen JS, Landew\u00e9 RBM, Bijlsma JWJ, Burmester GR, Dougados M, Kerschbaumer A, et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2019 update. Ann Rheum Dis. 2020;79:685\u201399. https:\/\/doi.org\/10.1136\/annrheumdis-2019-216655.","journal-title":"Ann Rheum Dis"},{"key":"2249_CR33","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1136\/ard.16.4.494","volume":"16","author":"JH Kellgren","year":"1957","unstructured":"Kellgren JH, Lawrence JS. Radiological assessment of osteo-arthrosis. Ann Rheum Dis. 1957;16:494\u2013502. https:\/\/doi.org\/10.1136\/ard.16.4.494.","journal-title":"Ann Rheum Dis"},{"key":"2249_CR34","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1016\/j.joca.2013.05.014","volume":"21","author":"Y Shimura","year":"2013","unstructured":"Shimura Y, Kurosawa H, Sugawara Y, Tsuchiya M, Sawa M, Kaneko H, et al. The factors associated with pain severity in patients with knee osteoarthritis vary according to the radiographic disease severity: a cross-sectional study. Osteoarthr Cartil. 2013;21:1179\u201384. https:\/\/doi.org\/10.1016\/j.joca.2013.05.014.","journal-title":"Osteoarthr Cartil"},{"key":"2249_CR35","doi-asserted-by":"publisher","first-page":"15245","DOI":"10.1038\/s41598-020-72270-6","volume":"10","author":"J Koh","year":"2020","unstructured":"Koh J, Lee E, Han K, Kim E-K, Son EJ, Sohn Y-M, et al. Diagnosis of thyroid nodules on ultrasonography by a deep convolutional neural network. Sci Rep. 2020;10:15245. https:\/\/doi.org\/10.1038\/s41598-020-72270-6.","journal-title":"Sci Rep"},{"key":"2249_CR36","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1080\/02656736.2022.2062463","volume":"39","author":"J-P Wu","year":"2022","unstructured":"Wu J-P, Ding W-Z, Wang Y-L, Liu S, Zhang X-Q, Yang Q, et al. Radiomics analysis of ultrasound to predict recurrence of hepatocellular carcinoma after microwave ablation. Int J Hyperth. 2022;39:595\u2013604. https:\/\/doi.org\/10.1080\/02656736.2022.2062463.","journal-title":"Int J Hyperth"},{"key":"2249_CR37","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1148\/radiol.2019190372","volume":"294","author":"L-Q Zhou","year":"2020","unstructured":"Zhou L-Q, Wu X-L, Huang S-Y, Wu G-G, Ye H-R, Wei Q, et al. Lymph node metastasis prediction from primary breast cancer US images using deep learning. Radiology. 2020;294:19\u201328. https:\/\/doi.org\/10.1148\/radiol.2019190372.","journal-title":"Radiology"},{"key":"2249_CR38","doi-asserted-by":"publisher","first-page":"1101810","DOI":"10.3389\/fphys.2023.1101810","volume":"14","author":"P Hu","year":"2023","unstructured":"Hu P, Gao Y, Zhang Y, Sun K. Ultrasound image-based deep learning to differentiate tubal-ovarian abscess from ovarian endometriosis cyst. Front Physiol. 2023;14:1101810. https:\/\/doi.org\/10.3389\/fphys.2023.1101810.","journal-title":"Front Physiol"},{"key":"2249_CR39","unstructured":"Lundberg S, Lee S-I. A unified approach to interpreting model predictions; 2017."},{"key":"2249_CR40","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: IEEE International Conference on Computer Vision (ICCV); 22\u201329 Oct. 2017. pp. 618\u2009\u2013\u200926. https:\/\/doi.org\/10.1109\/ICCV.2017.74.","DOI":"10.1109\/ICCV.2017.74"},{"key":"2249_CR41","doi-asserted-by":"publisher","first-page":"355","DOI":"10.3390\/biomedicines13020355","volume":"13","author":"MD Brandt","year":"2025","unstructured":"Brandt MD, Malone JB, Kean TJ. Advances and challenges in the pursuit of disease-modifying osteoarthritis drugs: a review of 2010\u20132024 clinical trials. Biomedicines. 2025;13:355. https:\/\/doi.org\/10.3390\/biomedicines13020355.","journal-title":"Biomedicines"},{"key":"2249_CR42","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1017\/s0266462303000060","volume":"19","author":"A Escobar","year":"2003","unstructured":"Escobar A, Quintana JM, Ar\u00f3stegui I, Azk\u00e1rate J, G\u00fcenaga JI, Arenaza JC, et al. Development of explicit criteria for total knee replacement. Int J Technol Assess Health Care. 2003;19:57\u201370. https:\/\/doi.org\/10.1017\/s0266462303000060.","journal-title":"Int J Technol Assess Health Care"},{"key":"2249_CR43","doi-asserted-by":"publisher","first-page":"1714","DOI":"10.1016\/j.arth.2023.03.068","volume":"38","author":"GS Goh","year":"2023","unstructured":"Goh GS, Schwartz AM, Friend JK, Grace TR, Wickes CB, Bolognesi MP, et al. Patients who have Kellgren-Lawrence grade 3 and 4 osteoarthritis benefit equally from total knee arthroplasty. J Arthroplasty. 2023;38:1714\u20137. https:\/\/doi.org\/10.1016\/j.arth.2023.03.068.","journal-title":"J Arthroplasty"},{"key":"2249_CR44","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","volume":"3","author":"M Roberts","year":"2021","unstructured":"Roberts M, Driggs D, Thorpe M, Gilbey J, Yeung M, Ursprung S, et al. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nat Mach Intell. 2021;3:199\u2013217. https:\/\/doi.org\/10.1038\/s42256-021-00307-0.","journal-title":"Nat Mach Intell"},{"key":"2249_CR45","doi-asserted-by":"publisher","first-page":"e0267877","DOI":"10.1371\/journal.pone.0267877","volume":"17","author":"D Uritani","year":"2022","unstructured":"Uritani D, Campbell PK, Metcalf B, Egerton T. A comparison of psychological characteristics in people with knee osteoarthritis from Japan and Australia: a cross-sectional study. PLoS ONE. 2022;17:e0267877. https:\/\/doi.org\/10.1371\/journal.pone.0267877.","journal-title":"PLoS ONE"},{"key":"2249_CR46","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1186\/s12877-024-05556-3","volume":"24","author":"J Gao","year":"2024","unstructured":"Gao J, Yesihati M, Cheng H, Li T, Ding R, Wang W. Association of Sarcopenia and its prognostic value in symptomatic knee osteoarthritis among older people in China: the first longitudinal evidence from CHARLS. BMC Geriatr. 2024;24:977. https:\/\/doi.org\/10.1186\/s12877-024-05556-3.","journal-title":"BMC Geriatr"},{"key":"2249_CR47","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.archger.2017.07.005","volume":"73","author":"N Kojima","year":"2017","unstructured":"Kojima N, Kim M, Saito K, Yoshida Y, Hirano H, Obuchi S, et al. Predictors of self-reported knee osteoarthritis in community-dwelling older women in Japan: a cross-sectional and longitudinal cohort study. Arch Gerontol Geriatr. 2017;73:125\u201332. https:\/\/doi.org\/10.1016\/j.archger.2017.07.005.","journal-title":"Arch Gerontol Geriatr"},{"key":"2249_CR48","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.maturitas.2019.06.013","volume":"128","author":"R Takiguchi","year":"2019","unstructured":"Takiguchi R, Komatsu R, Kitamura K, Watanabe Y, Takahashi A, Kobayashi R, et al. Modifiable factors associated with symptomatic knee osteoarthritis: the Murakami cohort study. Maturitas. 2019;128:53\u20139. https:\/\/doi.org\/10.1016\/j.maturitas.2019.06.013.","journal-title":"Maturitas"},{"key":"2249_CR49","doi-asserted-by":"publisher","unstructured":"Cui C, Yang H, Wang Y, Zhao S, Asad Z, Coburn LA, et al. Deep multimodal fusion of image and non-image data in disease diagnosis and prognosis: a review. Prog Biomed Eng (Bristol). 2023;5. https:\/\/doi.org\/10.1088\/2516-1091\/acc2fe.","DOI":"10.1088\/2516-1091\/acc2fe"},{"key":"2249_CR50","doi-asserted-by":"publisher","first-page":"e2298","DOI":"10.7717\/peerj-cs.2298","volume":"10","author":"JR Teoh","year":"2024","unstructured":"Teoh JR, Dong J, Zuo X, Lai KW, Hasikin K, Wu X. Advancing healthcare through multimodal data fusion: a comprehensive review of techniques and applications. PeerJ Comput Sci. 2024;10:e2298. https:\/\/doi.org\/10.7717\/peerj-cs.2298.","journal-title":"PeerJ Comput Sci"},{"key":"2249_CR51","doi-asserted-by":"publisher","unstructured":"He K, Xiangyu Z, Shaoqing R, Jian S. Deep residual learning for image recognition. In:, Recognition P. (CVPR); 27\u201330 June 2016. pp. 770-8. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2249_CR52","doi-asserted-by":"publisher","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint. https:\/\/doi.org\/10.48550\/arXiv.1409.1556.","DOI":"10.48550\/arXiv.1409.1556"},{"key":"2249_CR53","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 7\u201312 June 2015. pp. 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2249_CR54","doi-asserted-by":"publisher","unstructured":"Antony J, McGuinness K, O\u2019Connor NE, Moran K. Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. In: IEEE International Symposium on Biomedical Imaging (ISBI); 2017. pp. 1203-6. https:\/\/doi.org\/10.48550\/arXiv.1703.09856.","DOI":"10.48550\/arXiv.1703.09856"},{"key":"2249_CR55","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1038\/s41598-018-20132-7","volume":"8","author":"A Tiulpin","year":"2018","unstructured":"Tiulpin A, Thevenot J, Rahtu E, Lehenkari P, Saarakkala S. Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci Rep. 2018;8:1727. https:\/\/doi.org\/10.1038\/s41598-018-20132-7.","journal-title":"Sci Rep"},{"key":"2249_CR56","doi-asserted-by":"publisher","first-page":"7582","DOI":"10.21037\/qims-22-1392","volume":"13","author":"CL Piccolo","year":"2023","unstructured":"Piccolo CL, Mallio CA, Vaccarino F, Grasso RF, Zobel BB. Imaging of knee osteoarthritis: a review of multimodal diagnostic approach. Quant Imaging Med Surg. 2023;13:7582\u201395. https:\/\/doi.org\/10.21037\/qims-22-1392.","journal-title":"Quant Imaging Med Surg"},{"key":"2249_CR57","doi-asserted-by":"publisher","first-page":"1164655","DOI":"10.3389\/fbioe.2023.1164655","volume":"11","author":"PSQ Yeoh","year":"2023","unstructured":"Yeoh PSQ, Lai KW, Goh SL, Hasikin K, Wu X, Li P. Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: data from the osteoarthritis initiative. Front Bioeng Biotechnol. 2023;11:1164655. https:\/\/doi.org\/10.3389\/fbioe.2023.1164655.","journal-title":"Front Bioeng Biotechnol"},{"key":"2249_CR58","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR 2021-9th International Conference on Learning Representations; 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.11929.","DOI":"10.48550\/arXiv.2010.11929"},{"key":"2249_CR59","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu M, Unterthiner T, Kornblith S, Zhang C, Dosovitskiy A. Do vision transformers see like convolutional neural networks? Adv Neural Inf Process Syst. 2021;34:12116\u201328.","journal-title":"Adv Neural Inf Process Syst"},{"key":"2249_CR60","doi-asserted-by":"publisher","first-page":"4431","DOI":"10.3390\/jcm10194431","volume":"10","author":"CY Yang","year":"2021","unstructured":"Yang CY, Pan YJ, Chou Y, Yang CJ, Kao CC, Huang KC, et al. Using deep neural networks for predicting age and sex in healthy adult chest radiographs. J Clin Med. 2021;10:4431. https:\/\/doi.org\/10.3390\/jcm10194431.","journal-title":"J Clin Med"},{"key":"2249_CR61","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin R, Varadarajan AV, Blumer K, Liu Y, McConnell MV, Corrado GS, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018;2:158\u201364. https:\/\/doi.org\/10.1038\/s41551-018-0195-0.","journal-title":"Nat Biomed Eng"},{"key":"2249_CR62","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1186\/1471-2474-13-153","volume":"13","author":"AJ Metcalfe","year":"2012","unstructured":"Metcalfe AJ, Andersson MLE, Goodfellow R, Thorstensson CA. Is knee osteoarthritis a symmetrical disease? Analysis of a 12 year prospective cohort study. BMC Musculoskelet Disord. 2012;13:153. https:\/\/doi.org\/10.1186\/1471-2474-13-153.","journal-title":"BMC Musculoskelet Disord"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-026-02249-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02249-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02249-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:21:46Z","timestamp":1781644906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12880-026-02249-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2249"],"URL":"https:\/\/doi.org\/10.1186\/s12880-026-02249-8","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]},"assertion":[{"value":"16 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Ethical Review Committee of Tsukuba International University (No. R07-11) and conducted in accordance with the Declaration of Helsinki. All patients provided written informed consent.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors used ChatGPT-4 (OpenAI) to obtain suggestions for part of the CNN model development process. After using this tool, the authors reviewed and edited the content and implemented the code as needed.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration of generative AI and AI-assisted technologies in the writing process"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"248"}}