{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:33:44Z","timestamp":1786469624845,"version":"build-2736575974"},"reference-count":23,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Fujian Natural Science Foundation","doi-asserted-by":"publisher","award":["2024J01548"],"award-info":[{"award-number":["2024J01548"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence Application Promotion project of Fujian Provincial Department of Industry and Information Technology","award":["2024RGZNCJ-ZXF"],"award-info":[{"award-number":["2024RGZNCJ-ZXF"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Clin. Med.","JCM"],"abstract":"<jats:p>Background: This study aimed to develop and evaluate a deep learning (DL) algorithm based on magnetic resonance imaging (MRI) for the classification of temporomandibular joint degenerative joint disease (TMJDJD), thereby exploring its potential role in assisting cone-beam computed tomography (CBCT) examinations and minimizing patient radiation exposure. Methods: A retrospective analysis was conducted on 104 patients who had undergone both MRI and CBCT examinations of the temporomandibular joint. A total of 1769 sagittal and 1448 coronal MRI images were collected. After image preprocessing, the datasets were grouped according to different imaging features. Three DL frameworks\u2014ResNet101, DenseNet201, and MobileNetV2\u2014were developed to classify TMJDJD using various MRI image categories. The classification performance of these models was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), and the results were compared with classifications made by two senior clinical experts in a blinded image-level reader experiment. Results: DenseNet201 achieved the best performance in the sagittal (Sg) group, with an accuracy of 80.11%, precision of 80.26%, recall of 75.31%, and an MCC of 0.60. DenseNet201 achieved the best performance among the evaluated DL models, with higher overall performance metrics than ResNet101 and MobileNetV2. In a constrained image-level reader comparison, DenseNet201 demonstrated comparable overall agreement metrics to the two experts, although one expert achieved higher recall and a lower false-negative rate. t-Distributed Stochastic Neighbor Embedding (t-SNE) and training curve analyses confirmed that DenseNet201 demonstrated superior feature extraction capability and a more stable training process. Grouping MRI images, however, did not improve model accuracy. Conclusions: DenseNet201 showed preliminary potential for MRI-based TMJDJD classification, particularly on sagittal images. Based on image-level classification results, the model may provide preliminary support for identifying MRI findings associated with TMJDJD and assisting decisions regarding further CBCT evaluation.<\/jats:p>","DOI":"10.3390\/jcm15166225","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T16:30:32Z","timestamp":1786465832000},"page":"6225","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MRI-Based Deep Learning Image Classification for Screening Temporomandibular Joint Degenerative Joint Disease"],"prefix":"10.3390","volume":"15","author":[{"given":"Liang","family":"Xu","sequence":"first","affiliation":[{"name":"School of Stomatology, Fujian Medical University, Fuzhou 350000, China"},{"name":"Department of Stomatology, The First Affiliated Hospital of Fujian Medical University, Fuzhou 350005, China"},{"name":"Department of Stomatology, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou 350212, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixi","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Stomatology, Fuzhou General Hospital Affiliated with Fujian Medical University, Fuzhou 350005, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiliang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Stomatology, Fujian Medical University, Fuzhou 350000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Stomatology, The First Affiliated Hospital of Fujian Medical University, Fuzhou 350005, China"},{"name":"Department of Stomatology, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou 350212, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Stomatology, Fujian Medical University, Fuzhou 350000, China"},{"name":"School and Hospital of Stomatology, Fujian Medical University, Fuzhou 350000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"20140235","DOI":"10.1259\/dmfr.20140235","article-title":"Temporomandibular joint diagnostics using CBCT","volume":"44","author":"Larheim","year":"2015","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1159\/000086194","article-title":"Role of magnetic resonance imaging in the clinical diagnosis of the temporomandibular joint","volume":"180","author":"Larheim","year":"2005","journal-title":"Cells Tissues Organs"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"S1795","DOI":"10.4103\/jpbs.jpbs_1145_23","article-title":"Comparing Radiation Doses in CBCT and Medical CT Imaging for Dental Ap-plications","volume":"16","author":"Khader","year":"2024","journal-title":"J. Pharm. Bioallied Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.ejmp.2021.07.007","article-title":"Dental cone beam CT: An updated review","volume":"88","author":"Kaasalainen","year":"2021","journal-title":"Phys. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2058460120938738","DOI":"10.1177\/2058460120938738","article-title":"Temporomandibular joint pain and associated mag-netic resonance findings: A retrospective study with a control group","volume":"9","author":"Eriksen","year":"2020","journal-title":"Acta Radiol. Open"},{"key":"ref_6","first-page":"101","article-title":"Reliability of magnetic resonance imaging on detecting degenerative bone changes of the temporomandibular joint","volume":"34","author":"Araujo","year":"2021","journal-title":"Am. J. Dent."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1016\/j.joca.2023.03.005","article-title":"Osteoarthritis year in review 2022: Imaging","volume":"31","author":"Demehri","year":"2023","journal-title":"Osteoarthr. Cartil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1007\/s11547-022-01476-7","article-title":"Automatic detection and classification of knee osteoarthritis using deep learning approach","volume":"127","author":"Abdullah","year":"2022","journal-title":"Radiol. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"20093","DOI":"10.1038\/s41598-023-46953-9","article-title":"Association of AI-determined Kellgren-Lawrence grade with me-dial meniscus extrusion and cartilage thickness by AI-based 3D MRI analysis in early knee osteoarthritis","volume":"13","author":"Sekiya","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1016\/j.jcms.2024.04.006","article-title":"Association between clinical symptoms and MRI image findings in sympto-matic temporomandibular joint (TMJ) disease: A systematic review","volume":"52","author":"Sang","year":"2024","journal-title":"J. Craniomaxillofac. Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"76.e21","DOI":"10.1016\/j.crad.2020.06.020","article-title":"Imaging of the temporomandibular joint","volume":"76","author":"Whyte","year":"2021","journal-title":"Clin. Radiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"S844","DOI":"10.4103\/jpbs.jpbs_1056_23","article-title":"Comparative evaluation of CBCT and MRI in temporomandibular joint (TMJ) disorders and their relationship to periodontal health","volume":"16","author":"Jadeja","year":"2024","journal-title":"J. Pharm. Bioallied Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"20210286","DOI":"10.1259\/dmfr.20210286","article-title":"Diagnostic efficacy of CBCT, MRI and CBCT-MRI fused images in determining anterior disc displacement and bone changes of temporomandibular joint","volume":"51","author":"Wang","year":"2022","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"20200584","DOI":"10.1259\/dmfr.20200584","article-title":"Synthetic magnetic resonance imaging for quantitative parameter evaluation of temporomandibular joint disorders","volume":"50","author":"Lee","year":"2021","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1109\/TMI.2020.2973595","article-title":"Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation","volume":"39","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1137\/18M1216134","article-title":"Clustering with t-SNE, provably","volume":"1","author":"Linderman","year":"2019","journal-title":"SIAM J. Math. Data Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e14219","DOI":"10.1111\/apha.14219","article-title":"How to visualize high-dimensional data","volume":"240","author":"Mrowka","year":"2024","journal-title":"Acta Physiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.1162\/neco_a_01403","article-title":"Artificial neural variability for deep learning: On overfitting, noise memorization, and catastrophic forgetting","volume":"33","author":"Xie","year":"2021","journal-title":"Neural Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1111\/1754-9485.13054","article-title":"Characteristics of patients with temporomandibular joint osteoarthrosis on magnetic resonance imaging","volume":"64","author":"Toshima","year":"2020","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"20140279","DOI":"10.1259\/dmfr.20140279","article-title":"Bayesian belief network analysis applied to determine the progression of temporomandibular disorders using MRI","volume":"44","author":"Iwasaki","year":"2014","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6656773","DOI":"10.1155\/2021\/6656773","article-title":"Development and validation of a magnetic resonance imaging-based machine learning model for TMJ pathologies","volume":"2021","author":"Orhan","year":"2021","journal-title":"BioMed Res. Int."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1093\/dmfr\/twae040","article-title":"Can temporomandibular joint osteoarthritis be diagnosed on MRI proton density-weighted images with diagnostic support from the latest deep learning classification models?","volume":"54","author":"Nozawa","year":"2025","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/16\/6225\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T16:39:14Z","timestamp":1786466354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/16\/6225"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":23,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["jcm15166225"],"URL":"https:\/\/doi.org\/10.3390\/jcm15166225","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]}}}