{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T02:32:30Z","timestamp":1789871550716,"version":"4.0.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This study aimed to develop a deep learning-based method for interpreting magnetic resonance imaging (MRI) scans of temporomandibular joint (TMJ) anterior disc displacement (ADD) and to formulate an automated diagnostic system for clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The deep learning models were utilized to identify regions of interest (ROI), segment TMJ structures including the articular disc, condyle, glenoid fossa, and articular tubercle, and classify TMJ ADD. The models employed Grad-CAM heatmaps and segmentation annotation diagrams for visual diagnostic predictions and were deployed for clinical application. We constructed four deep-learning models based on the ResNet101_vd framework utilizing an MRI dataset of 618 TMJ cases collected from two hospitals (Hospitals SS and SG) and a dataset of 840 TMJ MRI scans from October 2022 to July 2023. The training and validation datasets included 700 images from Hospital SS, which were used to develop the models. Model performance was assessed using 140 images from Hospital SS (internal validity test) and 140 images from Hospital SG (external validity test). The first model identified the ROI, the second automated the segmentation of anatomical components, and the third and fourth models performed classification tasks based on segmentation and non-segmentation approaches. MRI images were classified into four categories: normal (closed mouth), ADD (closed mouth), normal (open mouth), and ADD (open mouth). Combined findings from open and closed-mouth positions provided conclusive diagnoses. Data augmentation techniques were used to prevent overfitting and enhance model robustness. The models were assessed using performance metrics such as precision, recall, mean average precision (mAP), F1-score, Matthews Correlation Coefficient (MCC), and confusion matrix analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Despite lower performance with Hospital SG\u2019s data than Hospital SS\u2019s, both achieved satisfactory results. Classification models demonstrated high precision rates above 92%, with the segmentation-based model outperforming the non-segmentation model in overall and category-specific metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>In summary, our deep learning models exhibited high accuracy in detecting TMJ ADD and provided interpretable, visualized predictive results. These models can be integrated with clinical examinations to enhance diagnostic precision.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2024.1445258","type":"journal-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T01:21:48Z","timestamp":1734052908000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Deep learning-based automated diagnosis of temporomandibular joint anterior disc displacement and its clinical application"],"prefix":"10.3389","volume":"15","author":[{"given":"Yue","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao Min","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,12,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/s0889-5406(98)70206-9","article-title":"Lateral cephalometric analysis of asymptomatic volunteers and symptomatic patients with and without bilateral temporomandibular joint disk displacement","volume":"114","author":"B\u00f3sio","year":"1998","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"B3","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.joms.2018.06.175","article-title":"Effect of measurement technique on TMJ mandibular condyle and articular disc morphometry: CBCT, MRI, and physical measurements","volume":"77","author":"Coombs","year":"2019","journal-title":"J. Oral Maxillofac. Surg."},{"key":"B4","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s00276-008-0400-z","article-title":"Comparison of conventional MRI and 3D reconstruction model for evaluation of temporomandibular joint","volume":"30","author":"Costa","year":"2008","journal-title":"Surg. Radiol. Anat."},{"key":"B5","doi-asserted-by":"publisher","first-page":"17910","DOI":"10.1038\/s41598-022-22745-5","article-title":"Static mandibular condyle positions studied by MRI and condylar position indicator","volume":"12","author":"Freudenthaler","year":"2022","journal-title":"Sci. Rep."},{"key":"B6","doi-asserted-by":"publisher","first-page":"608","DOI":"10.3760\/cma.j.cn112144-20200514-00268","article-title":"Experts consensus on MRI examination specification and diagnostic criteria of temporomandibular joint disc displacement","volume":"55","author":"Fu","year":"2020","journal-title":"Zhonghua Kou Qiang Yi Xue Za Zhi."},{"key":"B7","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1080\/08869634.1998.11746063","article-title":"A protocol for magnetic resonance imaging of the temporomandibular joints","volume":"16","author":"Gibbs","year":"1998","journal-title":"Cranio"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1016\/0278-2391(95)90127-2","article-title":"Intra-articular disc displacement Part II: its significant role in temporomandibular joint pathology","volume":"53","author":"Hall","year":"1995","journal-title":"J. Oral Maxillofac Surg."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B10","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/sj\/dmfr\/4600580","article-title":"An optimized fast protocol for magnetic resonance imaging of the temporomandibular joint","volume":"30","author":"Honda","year":"2001","journal-title":"Dentomaxillofac Radiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"213","DOI":"10.3109\/00016357.2011.634832","article-title":"Prevalence of symptoms indicative of temporomandibular disorders in adults: cross-sectional epidemiological investigations covering two decades","volume":"70","author":"Hugoson","year":"2011","journal-title":"Acta Odontol. Scand."},{"key":"B12","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1016\/s0889-5406(97)70228-2","article-title":"Morphologic study of the mandibular fossa and the eminence of the temporomandibular joint in relation to the facial structures","volume":"112","author":"Ikai","year":"1997","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B13","doi-asserted-by":"publisher","first-page":"84227642","DOI":"10.1259\/dmfr\/84227642","article-title":"Disc displacement and changes in condylar position","volume":"42","author":"Ikeda","year":"2013","journal-title":"Dentomaxillofac. Radiol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1038\/s41598-021-04354-w","article-title":"Automated segmentation of articular disc of the temporomandibular joint on magnetic resonance images using deep learning","volume":"12","author":"Ito","year":"2022","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s11282-021-00521-x","article-title":"Actual applications of magnetic resonance imaging in dentomaxillofacial region","volume":"38","author":"Johnson","year":"2022","journal-title":"Oral Radiol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"6680","DOI":"10.1038\/s41598-021-86115-3","article-title":"Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging","volume":"11","author":"Kim","year":"2021","journal-title":"Sci. Rep."},{"key":"B17","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1038\/sj\/dmfr\/4600603","article-title":"A study of the relationship between the position of the condylar head and displacement of the temporomandibular joint disk","volume":"30","author":"Kurita","year":"2001","journal-title":"Dentomaxillofac. Radiol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"11352","DOI":"10.1038\/s41598-022-15231-5","article-title":"Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging","volume":"12","author":"Lee","year":"2022","journal-title":"Sci. Rep."},{"key":"B19","doi-asserted-by":"publisher","first-page":"104345","DOI":"10.1016\/j.jdent.2022.104345","article-title":"Temporomandibular joint segmentation in MRI images using deep learning","volume":"127","author":"Li","year":"2022","journal-title":"J. Dent."},{"key":"B20","doi-asserted-by":"publisher","first-page":"20210341","DOI":"10.1259\/dmfr.20210341","article-title":"Automatic detection of anteriorly displaced temporomandibular joint discs on magnetic resonance images using a deep learning algorithm","volume":"51","author":"Lin","year":"2022","journal-title":"Dentomaxillofac Radiol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"212","DOI":"10.4103\/0970-9290.51365","article-title":"Etiopathogenesis of disk displacement of the temporomandibular joint: a review of the mechanisms","volume":"20","author":"Manfredini","year":"2009","journal-title":"Indian J. Dent. Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1093\/dmfr\/twae033","article-title":"Enhanced multistage deep learning for diagnosing anterior disc displacement in the temporomandibular joint using MRI","volume":"53","author":"Min","year":"2024","journal-title":"Dentomaxillofac Radiol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/s0889-5406(99)70241-6","article-title":"Male adolescent facial pattern associated with TMJ disk displacement and reduction in disk length: Part II","volume":"116","author":"Nebbe","year":"","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B24","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/s0889-5406(99)70214-3","article-title":"Female adolescent facial pattern associated with TMJ disk displacement and reduction in disk length: part I","volume":"116","author":"Nebbe","year":"","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B25","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-319-67389-9_31","article-title":"Segmentation of craniomaxillofacial bony structures from MRI with a 3D deep-learning based cascade framework","volume":"10541","author":"Nie","year":"2017","journal-title":"Mach. Learn Med. Imaging"},{"key":"B26","doi-asserted-by":"publisher","first-page":"20210185","DOI":"10.1259\/dmfr.20210185","article-title":"Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique","volume":"51","author":"Nozawa","year":"2022","journal-title":"Dentomaxillofac Radiol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"49102","DOI":"10.1109\/access.2023.3277756","article-title":"Interpretation of magnetic resonance images of temporomandibular joint disorders by using deep learning","volume":"11","author":"Ozsari","year":"2023","journal-title":"IEEE Access"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2475","DOI":"10.1007\/s00784-018-2664-y","article-title":"Prevalence of degenerative joint disease of the temporomandibular joint: a systematic review","volume":"23","author":"Pantoja","year":"2019","journal-title":"a Syst. Rev."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.3390\/diagnostics13091571","article-title":"Recent advances in explainable artificial intelligence for magnetic resonance imaging","volume":"13","author":"Qian","year":"2023","journal-title":"Diagn. (Basel)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"6","DOI":"10.11607\/jop.1151","article-title":"Diagnostic criteria for temporomandibular disorders (DC\/TMD) for clinical and research applications: recommendations of the international RDC\/TMD consortium network* and orofacial pain special interest group\u2020","volume":"28","author":"Schiffman","year":"2014","journal-title":"J. Oral Facial Pain Headache"},{"key":"B31","doi-asserted-by":"publisher","first-page":"8972","DOI":"10.3390\/app12188972","article-title":"Deep residual learning for image recognition: a survey","volume":"12","author":"Shafiq","year":"2022","journal-title":"Appl. Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1111\/joor.13138","article-title":"Relative risk of positional and dynamic temporomandibular disc abnormality for osteoarthritis-magnetic resonance imaging study","volume":"48","author":"Takaoka","year":"2021","journal-title":"Magn. Reson. imaging study."},{"key":"B33","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/s00784-020-03710-w","article-title":"Prevalence of temporomandibular joint disorders: a systematic review and meta-analysis","volume":"25","author":"Valesan","year":"2021","journal-title":"Clin. Oral Investig."},{"key":"B34","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1186\/s12885-024-12619-6","article-title":"Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer","volume":"24","author":"Wang","year":"2024","journal-title":"BMC Cancer"},{"key":"B35","doi-asserted-by":"publisher","first-page":"107465","DOI":"10.1016\/j.cmpb.2023.107465","article-title":"Explainable deep learning-based clinical decision support engine for MRI-based automated diagnosis of temporomandibular joint anterior disk displacement","volume":"233","author":"Yoon","year":"2023","journal-title":"Comput. Methods Programs Biomed."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2024.1445258\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T01:21:50Z","timestamp":1734052910000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2024.1445258\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":35,"alternative-id":["10.3389\/fphys.2024.1445258"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2024.1445258","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,13]]},"article-number":"1445258"}}