{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T04:23:28Z","timestamp":1793507008416,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":30,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioMed Eng OnLine"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) techniques are increasingly applied to magnetic resonance imaging (MRI) for detecting temporomandibular joint (TMJ) anomalies; however, their overall diagnostic accuracy and generalizability remain uncertain.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To systematically review and meta-analyse the diagnostic performance of AI models for TMJ anomaly detection on MRI and to identify factors influencing model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A comprehensive search of PubMed, Scopus, Embase, and Web of Science was conducted for studies published between January 2015 and September 2025. Two reviewers independently screened and extracted data. Eligible studies developed and tested AI, machine learning, or deep learning models on human TMJ MRI and reported quantitative performance metrics. Risk of bias was assessed using the QUADAS-2 tool. Pooled sensitivity and specificity were estimated using a bivariate random-effects model, while pooled accuracy was derived using logit transformation. Heterogeneity (\n                      <jats:italic>I<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      ) was explored through subgroup analyses by model architecture and validation strategy.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Fourteen studies were included in the systematic review, of which six met the criteria for meta-analysis. Across these six studies, 18 models were analyzed for accuracy, 29 for sensitivity, and 24 for specificity. The pooled diagnostic accuracy was 0.487 (95% CI 0.403\u20130.571), with pooled sensitivity and specificity of 0.399 (95% CI 0.348\u20130.450) and 0.399 (95% CI 0.343\u20130.456), respectively, all showing substantial heterogeneity (\n                      <jats:italic>I<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      \u2009&gt;\u200990%). Subgroup analyses indicated that advanced architectures such as ResNet-18, Inception v3, and EfficientNet-b4 achieved higher and more consistent diagnostic performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Advanced deep learning architectures such as ResNet-18, Inception v3, and EfficientNet-b4 demonstrated superior diagnostic performance for detecting temporomandibular joint anomalies on MRI. These findings highlight the potential of AI-assisted MRI interpretation to improve diagnostic consistency, efficiency, and early detection of TMJ pathology. However, substantial heterogeneity and limited external validation currently limit clinical translation. Standardized multicenter studies and transparent model validation are essential to ensure reliable integration of AI tools into clinical TMJ imaging workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12938-026-01525-6","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T12:33:07Z","timestamp":1769862787000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic accuracy of artificial intelligence models for temporomandibular joint anomalies on MRI: a systematic review and meta-analysis"],"prefix":"10.1186","volume":"25","author":[{"given":"Abhimanyu","family":"Pradhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajagopal","family":"Kadavigere","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil Abraham","family":"Barnes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suresh","family":"Sukumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashwin","family":"Prabhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dilip","family":"Shettigar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winniecia","family":"Dkhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"1525_CR1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-1-4614-4466-4_8","volume-title":"Craniofacial muscles: a new framework for understanding the effector side of craniofacial muscle control","author":"SL Hebert","year":"2013","unstructured":"Hebert SL, Willoughby CL, Andrade FH, McLoon LK. Masticatory muscle response to neuromuscular diseases and specific pathologies. In: McLoon LK, Andrade F, editors. Craniofacial muscles: a new framework for understanding the effector side of craniofacial muscle control. New York: Springer; 2013. p. 131\u20138. https:\/\/doi.org\/10.1007\/978-1-4614-4466-4_8."},{"key":"1525_CR2","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1111\/joor.13472","volume":"50","author":"Z Qamar","year":"2023","unstructured":"Qamar Z, Alghamdi AMS, Haydarah NK, Balateef AA, Alamoudi AA, Abumismar MA, et al. Impact of temporomandibular disorders on oral health-related quality of life: a systematic review and meta-analysis. J Oral Rehabil. 2023;50:706\u201314. https:\/\/doi.org\/10.1111\/joor.13472.","journal-title":"J Oral Rehabil"},{"key":"1525_CR3","doi-asserted-by":"publisher","first-page":"375","DOI":"10.5114\/reum\/173078","volume":"61","author":"V Syrmou","year":"2023","unstructured":"Syrmou V, Grammatikopoulou MG, Bogdanos DP, Mitsimponas KT. Temporomandibular joint disorders in seronegative spondyloarthritis: what a rheumatologist needs to know? Reumatologia. 2023;61:375\u201388. https:\/\/doi.org\/10.5114\/reum\/173078.","journal-title":"Reumatologia"},{"key":"1525_CR4","doi-asserted-by":"publisher","first-page":"135","DOI":"10.24875\/aji.23000069","volume":"30","author":"M L\u00f3pez-Ram\u00edrez","year":"2024","unstructured":"L\u00f3pez-Ram\u00edrez M, Espinoza I, Sierra F, Grass B, N\u00fa\u00f1ez R, Miranda G. Temporomandibular joint study by magnetic resonance imaging: it is time to inform. Austral J Imaging (English Edition). 2024;30:135\u201346. https:\/\/doi.org\/10.24875\/aji.23000069.","journal-title":"Austral J Imaging (English Edition)"},{"key":"1525_CR5","doi-asserted-by":"publisher","first-page":"712","DOI":"10.12659\/MSM.899230","volume":"23","author":"Z Yang","year":"2017","unstructured":"Yang Z, Wang M, Ma Y, Lai Q, Tong D, Zhang F, et al. Magnetic resonance imaging (MRI) evaluation for anterior disc displacement of the temporomandibular joint. Med Sci Monit. 2017;23:712\u20138. https:\/\/doi.org\/10.12659\/MSM.899230.","journal-title":"Med Sci Monit"},{"key":"1525_CR6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s11282-018-0327-y","volume":"35","author":"T Kamio","year":"2019","unstructured":"Kamio T, Yakushiji T, Takaki T, Shibahara T, Imoto K, Wakoh M. Incidental findings during head and neck MRI screening in 1717 patients with temporomandibular disorders. Oral Radiol. 2019;35:135\u201342. https:\/\/doi.org\/10.1007\/s11282-018-0327-y.","journal-title":"Oral Radiol"},{"key":"1525_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1002\/jmri.26343","volume":"49","author":"JH Yacoub","year":"2019","unstructured":"Yacoub JH, Elsayes KM, Fowler KJ, Hecht EM, Mitchell DG, Santillan C, et al. Pitfalls in liver MRI: technical approach to avoiding misdiagnosis and improving image quality. J Magn Reson Imaging. 2019;49:41\u201358. https:\/\/doi.org\/10.1002\/jmri.26343.","journal-title":"J Magn Reson Imaging"},{"key":"1525_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9030055","author":"B de Wilde","year":"2023","unstructured":"de Wilde B, Joosten F, Venderink W, Davidse MEJ, Geurts J, Kruijt H, et al. Inter- and intra-observer variability and the effect of experience in cine-MRI for adhesion detection. J Imaging. 2023. https:\/\/doi.org\/10.3390\/jimaging9030055.","journal-title":"J Imaging"},{"key":"1525_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIPTEKNO63488.2024.10755235","volume-title":"2024 medical technologies congress (TIPTEKNO)","author":"M Sezdi","year":"2024","unstructured":"Sezdi M, Artu\u011f NT. The impact of artificial intelligence on medical imaging technologies. In: Sezdi M, editor. 2024 medical technologies congress (TIPTEKNO). Mugla: IEEE; 2024. p. 1\u20134. https:\/\/doi.org\/10.1109\/TIPTEKNO63488.2024.10755235."},{"key":"1525_CR10","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1002\/ird3.70008","volume":"3","author":"Y Yang","year":"2025","unstructured":"Yang Y, Ye L, Feng Z. Application of artificial intelligence in medical imaging: current status and future directions. Iradiology. 2025;3:144\u201351. https:\/\/doi.org\/10.1002\/ird3.70008.","journal-title":"Iradiology"},{"key":"1525_CR11","doi-asserted-by":"publisher","DOI":"10.1002\/ksa.12702","author":"FC Oettl","year":"2025","unstructured":"Oettl FC, Zsidai B, Oeding JF, Hirschmann MT, Feldt R, Fendrich D, et al. Artificial intelligence-assisted analysis of musculoskeletal imaging\u2014a narrative review of the current state of machine learning models. Knee Surg Sports Traumatol Arthrosc. 2025. https:\/\/doi.org\/10.1002\/ksa.12702.","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"key":"1525_CR12","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1530\/EOR-23-0174","volume":"9","author":"G Droppelmann","year":"2024","unstructured":"Droppelmann G, Rodr\u00edguez C, Jorquera C, Feijoo F. Artificial intelligence in diagnosing upper limb musculoskeletal disorders: a systematic review and meta-analysis of diagnostic tests. EFORT Open Rev. 2024;9:241\u201351. https:\/\/doi.org\/10.1530\/EOR-23-0174.","journal-title":"EFORT Open Rev"},{"key":"1525_CR13","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71","volume":"372","author":"MJ Page","year":"2021","unstructured":"Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. https:\/\/doi.org\/10.1136\/bmj.n71.","journal-title":"BMJ"},{"key":"1525_CR14","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1097\/XEB.0000000000000061","volume":"13","author":"JM Campbell","year":"2015","unstructured":"Campbell JM, Klugar M, Ding S, Carmody DP, Hakonsen SJ, Jadotte YT, et al. Diagnostic test accuracy: methods for systematic review and meta-analysis. Int J Evid Based Healthc. 2015;13:154\u201362. https:\/\/doi.org\/10.1097\/XEB.0000000000000061.","journal-title":"Int J Evid Based Healthc"},{"key":"1525_CR15","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1093\/dmfr\/twaf017","volume":"54","author":"EG Ha","year":"2025","unstructured":"Ha EG, Jeon KJ, Lee C, Kim DH, Han SS. Magnetic resonance image generation using enhanced TransUNet in temporomandibular disorder patients. Dentomaxillofac Radiol. 2025;54:357\u201363. https:\/\/doi.org\/10.1093\/dmfr\/twaf017.","journal-title":"Dentomaxillofac Radiol"},{"key":"1525_CR16","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1093\/dmfr\/twae063","volume":"54","author":"C Lee","year":"2025","unstructured":"Lee C, Lee J, Mandava S, Fung M, Choi YJ, Jeon KJ, et al. Deep learning image enhancement for confident diagnosis of TMJ osteoarthritis in zero-TE MR imaging. Dentomaxillofac Radiol. 2025;54:302\u20136. https:\/\/doi.org\/10.1093\/dmfr\/twae063.","journal-title":"Dentomaxillofac Radiol"},{"key":"1525_CR17","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1093\/dmfr\/twae033","volume":"53","author":"CK Min","year":"2024","unstructured":"Min CK, Jung W, Joo S. Enhanced multistage deep learning for diagnosing anterior disc displacement in the temporomandibular joint using MRI. Dentomaxillofac Radiol. 2024;53:488\u201396. https:\/\/doi.org\/10.1093\/dmfr\/twae033.","journal-title":"Dentomaxillofac Radiol"},{"key":"1525_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69848-9","author":"YH Lee","year":"2024","unstructured":"Lee YH, Jeon S, Won JH, Auh QS, Noh YK. Automatic detection and visualization of temporomandibular joint effusion with deep neural network. Sci Rep. 2024. https:\/\/doi.org\/10.1038\/s41598-024-69848-9.","journal-title":"Sci Rep"},{"key":"1525_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-86115-3","author":"JY Kim","year":"2021","unstructured":"Kim JY, Kim D, Jeon KJ, Kim H, Huh JK. Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging. Sci Rep. 2021. https:\/\/doi.org\/10.1038\/s41598-021-86115-3.","journal-title":"Sci Rep"},{"key":"1525_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-15231-5","author":"YH Lee","year":"2022","unstructured":"Lee YH, Won JH, Kim S, Auh QS, Noh YK. Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging. Sci Rep. 2022. https:\/\/doi.org\/10.1038\/s41598-022-15231-5.","journal-title":"Sci Rep"},{"key":"1525_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69814-5","author":"K Yoon","year":"2024","unstructured":"Yoon K, Kim JY, Kim SJ, Huh JK, Kim JW, Choi J. Multi-class segmentation of temporomandibular joint using ensemble deep learning. Sci Rep. 2024. https:\/\/doi.org\/10.1038\/s41598-024-69814-5.","journal-title":"Sci Rep"},{"key":"1525_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107465","author":"K Yoon","year":"2023","unstructured":"Yoon K, Kim JY, Kim SJ, Huh JK, Kim JW, Choi J. Explainable deep learning-based clinical decision support engine for MRI-based automated diagnosis of temporomandibular joint anterior disk displacement. Comput Methods Progr Biomed. 2023. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107465.","journal-title":"Comput Methods Progr Biomed"},{"key":"1525_CR23","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1093\/dmfr\/twae040","volume":"54","author":"M Nozawa","year":"2025","unstructured":"Nozawa M, Fukuda M, Kotaki S, Araragi M, Akiyama H, Ariji Y. Can temporomandibular joint osteoarthritis be diagnosed on MRI proton density-weighted images with diagnostic support from the latest deep learning classification models? Dentomaxillofac Radiol. 2025;54:56\u201363. https:\/\/doi.org\/10.1093\/dmfr\/twae040.","journal-title":"Dentomaxillofac Radiol"},{"key":"1525_CR24","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.oooo.2023.01.016","volume":"138","author":"Y Yoshimi","year":"2024","unstructured":"Yoshimi Y, Mine Y, Ito S, Takeda S, Okazaki S, Nakamoto T, et al. Image preprocessing with contrast-limited adaptive histogram equalization improves the segmentation performance of deep learning for the articular disk of the temporomandibular joint on magnetic resonance images. Oral Surg Oral Med Oral Pathol Oral Radiol. 2024;138:128\u201341. https:\/\/doi.org\/10.1016\/j.oooo.2023.01.016.","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"key":"1525_CR25","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1272814","author":"Y Li","year":"2023","unstructured":"Li Y, Li W, Wang L, Wang X, Gao S, Liao Y, et al. Detecting anteriorly displaced temporomandibular joint discs using super-resolution magnetic resonance imaging: a multi-center study. Front Physiol. 2023. https:\/\/doi.org\/10.3389\/fphys.2023.1272814.","journal-title":"Front Physiol"},{"key":"1525_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2025.105622","author":"R Azma","year":"2025","unstructured":"Azma R, Hareendranathan A, Li M, Nguyen P, S Wahd A, Jaremko JL, et al. Automated pediatric TMJ articular disk identification and displacement classification in MRI with machine learning. J Dent. 2025. https:\/\/doi.org\/10.1016\/j.jdent.2025.105622.","journal-title":"J Dent"},{"key":"1525_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2022.104345","author":"M Li","year":"2022","unstructured":"Li M, Punithakumar K, Major PW, Le LH, Nguyen KCT, Pacheco-Pereira C, et al. Temporomandibular joint segmentation in MRI images using deep learning. J Dent. 2022. https:\/\/doi.org\/10.1016\/j.jdent.2022.104345.","journal-title":"J Dent"},{"key":"1525_CR28","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/j.jds.2024.06.001","volume":"20","author":"TY Su","year":"2025","unstructured":"Su TY, Wu JCH, Chiu WC, Chen TJ, Lo WL, Lu HHS. Automatic classification of temporomandibular joint disorders by magnetic resonance imaging and convolutional neural networks. J Dent Sci. 2025;20:393\u2013401. https:\/\/doi.org\/10.1016\/j.jds.2024.06.001.","journal-title":"J Dent Sci"},{"key":"1525_CR29","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-024-02072-6","author":"H Han","year":"2025","unstructured":"Han H. Challenges of reproducible AI in biomedical data science. BMC Med Genomics. 2025. https:\/\/doi.org\/10.1186\/s12920-024-02072-6.","journal-title":"BMC Med Genomics"},{"key":"1525_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cegh.2024.101760","author":"NA Barnes","year":"2024","unstructured":"Barnes NA, Sharath S, Dkhar W, Chhaparwal Y, Nayak K. CBCT segmentation of the mandibular canal with both semi-automated and fully automated methods: a systematic review. Clin Epidemiol Glob Health. 2024. https:\/\/doi.org\/10.1016\/j.cegh.2024.101760.","journal-title":"Clin Epidemiol Glob Health"},{"key":"1525_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/dmfr\/twae055","volume":"54","author":"M Manek","year":"2025","unstructured":"Manek M, Maita I, Bezerra Silva DF, de Pita Melo D, Major PW, Jaremko JL, et al. Temporomandibular joint assessment in MRI images using artificial intelligence tools: where are we now? A systematic review. Dentomaxillofac Radiol. 2025;54:1\u201311. https:\/\/doi.org\/10.1093\/dmfr\/twae055.","journal-title":"Dentomaxillofac Radiol"}],"container-title":["BioMedical Engineering OnLine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12938-026-01525-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-026-01525-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12938-026-01525-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T09:31:21Z","timestamp":1772443881000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12938-026-01525-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1525"],"URL":"https:\/\/doi.org\/10.1186\/s12938-026-01525-6","relation":{},"ISSN":["1475-925X"],"issn-type":[{"value":"1475-925X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,31]]},"assertion":[{"value":"7 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 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":"Not applicable.","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 declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"39"}}