{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:08:15Z","timestamp":1788739695292,"version":"build-2803163510"},"reference-count":31,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T00:00:00Z","timestamp":1788652800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T00:00:00Z","timestamp":1788652800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100013061","name":"Jilin Scientific and Technological Development Program","doi-asserted-by":"publisher","award":["20240305034YY"],"award-info":[{"award-number":["20240305034YY"]}],"id":[{"id":"10.13039\/501100013061","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["arthroscopyjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Arthroscopy"],"abstract":"\n Purpose<\/jats:title>\n To develop and externally validate KneeFusionNet, a multimodal deep learning model for detecting anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), and lateral collateral ligament (LCL) injuries on knee magnetic resonance imaging (MRI), and to assess the impact of multimodal fusion and artificial intelligence (AI) assistance on diagnostic performance.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This 3\u2010center retrospective study was conducted between April 2020 and August 2025. The injury group included patients who underwent knee MRI within 1\u2009month before arthroscopy and had surgically confirmed ACL, PCL, MCL, or LCL injuries; controls had unremarkable MRI and physical examination findings. Two centers formed the development set, and the remaining center served as the external test set. DenseNet\u2010based KneeFusionNet was developed and compared with 3 deep learning models. Diagnostic performance was assessed using the area under the receiver operating characteristic curve, and a reader study evaluated AI\u2010assisted diagnostic performance.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Overall, 919 patients were included: 759 in the development set and 160 in the external test set. Multimodal fusion outperformed single\u2010modality approaches for all ligaments (all\n P\u2009<\/jats:italic>\n <\n \u2009<\/jats:italic>\n .05). On internal validation, KneeFusionNet achieved area under the receiver operating characteristic curves of 0.971 for ACL, 0.906 for PCL, 0.919 for MCL, and 0.924 for LCL. Corresponding external area under the receiver operating characteristic curves were 0.888, 0.867, 0.862, and 0.874. Sex\u2010stratified analyses showed no consistent sex\u2010related decrease in model performance. KneeFusionNet outperformed all comparison models on internal validation (all\n P\u2009<\/jats:italic>\n <\n \u2009<\/jats:italic>\n .05). AI assistance improved mean diagnostic accuracy for junior surgeons from 0.818 to 0.900 and reduced mean interpretation time by 14.73\u2009seconds across all surgeons (all\n P\u2009<\/jats:italic>\n <\n \u2009<\/jats:italic>\n .05).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n KneeFusionNet detected ACL, PCL, MCL, and LCL injuries on MRI with high diagnostic performance and outperformed comparison models. AI assistance improved diagnostic accuracy for junior surgeons and reduced interpretation time for all surgeons.<\/jats:p>\n <\/jats:sec>\n \n Level of Evidence<\/jats:title>\n Level III, retrospective case\u2010control study.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/arj.70510","type":"journal-article","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T23:50:56Z","timestamp":1788738656000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KneeFusionNet Enables Accurate and Efficient Comprehensive Detection of Knee Ligament Injuries on Magnetic Resonance Imaging: A Multicenter Validation Study"],"prefix":"10.1002","author":[{"given":"Bo","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"},{"name":"College of Artificial Intelligence Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deming","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianyue","family":"Shen","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital of the University of Science and Technology of China Hefei China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenghao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihuai","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingshuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Joint Surgery Weifang People's Hospital Weifang China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3296-3779","authenticated-orcid":false,"given":"Yanguo","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Sports Medicine and Arthroscopy The Second Hospital of Jilin University Changchun China"},{"name":"Joint International Research Laboratory of Ageing Active Strategy and Bionic Health in Northeast Asia of Ministry of Education Jilin University Changchun China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,6]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1136\/bjsports-2024-108089","article-title":"Multiligament knee injury (MLKI): An expert consensus statement on nomenclature, diagnosis, treatment and rehabilitation","volume":"58","author":"Murray IR","year":"2024","journal-title":"Br J Sports Med."},{"key":"e_1_2_10_3_1","first-page":"255","article-title":"Medial collateral ligament injury of the knee: A review on current concept and management","volume":"9","author":"Vosoughi F","year":"2021","journal-title":"Arch Bone Jt Surg."},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1007\/s00167-021-06723-4","article-title":"Operative management of isolated posterior cruciate ligament injuries improves stability and reduces the incidence of secondary osteoarthritis: A systematic review","volume":"30","author":"Schroven W","year":"2022","journal-title":"Knee Surg Sports Traumatol Arthrosc."},{"key":"e_1_2_10_5_1","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1302\/2058-5241.6.200096","article-title":"Posterolateral corner knee injuries: A narrative review","volume":"6","author":"Figueroa F","year":"2021","journal-title":"EFORT Open Rev."},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s13075-020-02156-5","article-title":"Post\u2010traumatic osteoarthritis following ACL injury","volume":"22","author":"Wang LJ","year":"2020","journal-title":"Arthritis Res Ther."},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","first-page":"e70006","DOI":"10.1002\/jeo2.70006","article-title":"Delayed anterior cruciate ligament reconstruction and risk of meniscus injury: Exploring the safest delay interval","volume":"11","author":"Utoyo GA","year":"2024","journal-title":"J Exp Orthop."},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1136\/bjsports-2022-106425","article-title":"Diagnosis and treatment strategies of the multiligament injured knee: A scoping review","volume":"57","author":"Makaram NS","year":"2023","journal-title":"Br J Sports Med."},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1056\/NEJMcp1805931","article-title":"Anterior cruciate ligament tear","volume":"380","author":"Musahl V","year":"2019","journal-title":"N Engl J Med."},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1186\/s12891-021-04376-5","article-title":"Intra\u2010and interobserver reliability of determining the femoral footprint of the torn anterior cruciate ligament on MRI scans","volume":"22","author":"Zee MJM","year":"2021","journal-title":"BMC Musculoskelet Disord."},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1007\/s00330-025-11820-w","article-title":"Impact of AI assistance on radiologist interpretation of knee MRI","volume":"36","author":"Herpe G","year":"2026","journal-title":"Eur Radiol."},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1007\/s00256-021-03830-8","article-title":"Artificial intelligence for MRI diagnosis of joints: A scoping review of the current state\u2010of\u2010the\u2010art of deep learning\u2010based approaches","volume":"51","author":"Fritz B","year":"2022","journal-title":"Skeletal Radiol."},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","first-page":"3576","DOI":"10.1007\/s00330-020-06672-5","article-title":"Integrating artificial intelligence into the clinical practice of radiology: Challenges and recommendations","volume":"30","author":"Recht MP","year":"2020","journal-title":"Eur Radiol."},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1177\/03635465221145697","article-title":"Accuracy of magnetic resonance imaging in the diagnosis of multiple ligament knee injuries: A multicenter study of 178 patients","volume":"51","author":"Sanchez\u2010Munoz E","year":"2023","journal-title":"Am J Sports Med."},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s12891-021-04976-1","article-title":"The accuracy of MRI in diagnosing and classifying acute traumatic multiple ligament knee injuries","volume":"23","author":"Li X","year":"2022","journal-title":"BMC Musculoskelet Disord."},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","first-page":"e1002699","DOI":"10.1371\/journal.pmed.1002699","article-title":"Deep\u2010learning\u2010assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet","volume":"15","author":"Bien N","year":"2018","journal-title":"PLoS Med."},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1016\/j.arthro.2023.08.010","article-title":"A deep learning model enhances clinicians\u2019 diagnostic accuracy to more than 96% for anterior cruciate ligament ruptures on magnetic resonance imaging","volume":"40","author":"Wang DY","year":"2024","journal-title":"Arthroscopy."},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","first-page":"8394","DOI":"10.1007\/s00330-022-08923-z","article-title":"Deep learning to detect anterior cruciate ligament tear on knee MRI: Multi\u2010continental external validation","volume":"32","author":"Tran A","year":"2022","journal-title":"Eur Radiol."},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","first-page":"7637","DOI":"10.1038\/s41467-024-51888-4","article-title":"Learning co\u2010plane attention across MRI sequences for diagnosing 12 types of knee abnormalities","volume":"15","author":"Qiu Z","year":"2024","journal-title":"Nat Commun."},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/j.arthro.2024.05.027","article-title":"Transformer\u2010based multilabel deep learning model is efficient for detecting ankle lateral and medial ligament injuries on magnetic resonance imaging and improving clinicians\u2019 diagnostic accuracy for rotational chronic ankle instability","volume":"41","author":"Yin R","year":"2025","journal-title":"Arthroscopy."},{"key":"e_1_2_10_21_1","doi-asserted-by":"crossref","unstructured":"UchiyamaT SogiN NiinumaK FukuiK.Visually explaining 3D\u2010CNN predictions for video classification with an adaptive occlusion sensitivity analysis. In2023IEEE\/CVFWinter Conference on Applications of Computer Vision (WACV).2023:1513\u20101522.","DOI":"10.1109\/WACV56688.2023.00156"},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.2214\/AJR.21.26056","article-title":"Five overlooked injuries on knee MRI","volume":"217","author":"Griffith JF","year":"2021","journal-title":"Am J Roentgenol."},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","first-page":"102470","DOI":"10.1016\/j.media.2022.102470","article-title":"Explainable artificial intelligence (XAI) in deep learning\u2010based medical image analysis","volume":"79","author":"van der Velden BHM","year":"2022","journal-title":"Medical Image Analysis."},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","first-page":"110787","DOI":"10.1016\/j.ejrad.2023.110787","article-title":"Explainable AI in medical imaging: An overview for clinical practitioners \u2010 Saliency\u2010based XAI approaches","volume":"162","author":"Borys K","year":"2023","journal-title":"Eur J Radiol."},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","first-page":"2457","DOI":"10.1007\/s00330-024-11105-8","article-title":"MRI deep learning models for assisted diagnosis of knee pathologies: A systematic review","volume":"35","author":"Mead K","year":"2025","journal-title":"Eur Radiol."},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","first-page":"776","DOI":"10.3390\/diagnostics15060776","article-title":"Deep learning models to detect anterior cruciate ligament injury on MRI: A comprehensive review","volume":"15","author":"Mercurio M","year":"2025","journal-title":"Diagnostics"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","first-page":"103534","DOI":"10.1016\/j.eclinm.2025.103534","article-title":"Development of a multi\u2010task deep learning system for classification of 9 common knee abnormalities on MRI: A large\u2010scale, multicentre, stepwise validation study","volume":"89","author":"Xie Z","year":"2025","journal-title":"EClinicalMedicine."},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","first-page":"2563","DOI":"10.1007\/s00330-025-12052-8","article-title":"Comprehensive deep learning\u2010assisted multi\u2010condition analysis of knee MRI studies improves resident radiologist performance","volume":"36","author":"Vuskov R","year":"2026","journal-title":"Eur Radiol."},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1007\/s12194-019-00552-4","article-title":"AI\u2010based computer\u2010aided diagnosis (AI\u2010CAD): The latest review to read first","volume":"13","author":"Fujita H","year":"2020","journal-title":"Radiol Phys Technol."},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","first-page":"111252","DOI":"10.1016\/j.ejrad.2023.111252","article-title":"Prospective effects of an artificial intelligence\u2010based computer\u2010aided detection system for prostate imaging on routine workflow and radiologists\u2019 outcomes","volume":"170","author":"Wenderott K","year":"2024","journal-title":"Eur J Radiol."},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","first-page":"101207","DOI":"10.1016\/j.xcrm.2023.101207","article-title":"AI\u2010clinician collaboration via disagreement prediction: A decision pipeline and retrospective analysis of real\u2010world radiologist\u2010AI interactions","volume":"4","author":"Sanchez M","year":"2023","journal-title":"Cell Rep Med."},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/s41746-024-01248-9","article-title":"Effects of artificial intelligence implementation on efficiency in medical imaging \u2010 A systematic literature review and meta\u2010analysis","volume":"7","author":"Wenderott K","year":"2024","journal-title":"NPJ Digit Med."}],"container-title":["Arthroscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/arj.70510","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/arj.70510","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/arj.70510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T23:51:01Z","timestamp":1788738661000},"score":1,"resource":{"primary":{"URL":"https:\/\/arthroscopyjournals.onlinelibrary.wiley.com\/doi\/10.1002\/arj.70510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,6]]},"references-count":31,"alternative-id":["10.1002\/arj.70510"],"URL":"https:\/\/doi.org\/10.1002\/arj.70510","archive":["Portico"],"relation":{},"ISSN":["0749-8063","1526-3231"],"issn-type":[{"value":"0749-8063","type":"print"},{"value":"1526-3231","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,6]]},"assertion":[{"value":"2025-12-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"arj.70510"}}