MODERN CONCEPT OF VISUALIZATION OF DYSFUNCTIONS OF THE TEMPOROMANDIBIAL JOINT WITH ELEMENTS OF ARTIFICIAL INTELLIGENCE INTEGRATION
DOI:
https://doi.org/10.32782/3041-1394.2025-2.10Keywords:
magnetic resonance imaging (MRI), temporomandibular joint (TMJ), artificial intelligence (AI), pathology, imaging, dentistry, maxillofacial region.Abstract
Introduction. The incorporation of magnetic resonance imaging (MRI) into routine dental practice is challenged by issues such as cost, limited accessibility, and the lack of standardized imaging protocols. Currently, both researchers and clinicians are actively investigating strategies to optimize MRI use in the dentomaxillofacial region, with the goal of enhancing patient care and facilitating early detection of pathological conditions. The aim. To review and analyze current scientific evidence regarding the feasibility and effectiveness of advanced imaging techniques for temporomandibular joint disorders, with the integration of artificial intelligence components. Materials and Methods. Relevant publications were identified through searches of the Scopus, PubMed, BVS, and SciELO databases using the following keywords: magnetic resonance imaging (MRI), temporomandibular joint (TMJ), artificial intelligence (AI), pathology, imaging, dentistry, and the maxillofacial region. The review included original research articles, study findings, and official guidelines issued by medical associations. Only studies reporting positive outcomes in the investigated groups were considered eligible. The selected materials were analyzed using content analysis methods, followed by data organization and classification with the support of CADIMA software. Results. To date, advanced AI-based approaches have not been widely implemented for TMJ evaluation. Vision transformers, an emerging architecture capable of modeling global image relationships, may help overcome the inherent limitations of convolutional neural networks (CNNs), particularly their focus on local pixel-level features. Hybrid models combining CNNs and transformers have been proposed to enhance performance. However, only one study referenced transformer-based methods without presenting corresponding results, highlighting an area for future research. This systematic review assessed the performance of AI models in detecting the TMJ disc and diagnosing internal derangements based on MRI data. The algorithms demonstrated encouraging performance in identifying key anatomical structures, including the TMJ disc, condylar process, and articular eminence, as well as in classifying disc position, achieving accuracy levels ranging from 0.70 to 0.99 compared to expert radiologists. A meta-analysis could not be conducted due to substantial heterogeneity among AI models and dataset characteristics. Conclusions. The application of AI, particularly deep learning techniques, in MRI-based evaluation of the TMJ shows consistently strong potential as a diagnostic support tool, especially for structural segmentation and disc position classification. Further multicenter studies incorporating diverse datasets are necessary to enhance the validity and generalizability of findings prior to clinical implementation.
References
Lau Rui Han S., Xiang J., Zeng X. X., Fan P. D., Cheng Q. Y., Zhou X. M., et al. Relationship between temporomandibular joint effusion, pain, and jaw function limitation: a 2D and 3D comparative study. J Pain Res. 2024. Vol. 17. P. 2051–2062.
Schiffman E., Ohrbach R., Truelove E., Look J., Anderson G., Goulet J. P., et al. Diagnostic criteria for temporomandibular disorders (DC/TMD) for clinical and research applications. J Oral Facial Pain Headache. 2014. Vol. 28, No. 1. P. 6–27. DOI: 10.11607/jop.1151
Riley J. L., Rindal D. B., Velly A. M., Anderson G. C., Johnson K. S., Gilbert G. H., et al. Practitioner-, practice-, and patient-based factors contributing to treatment recommendations for pain-related TMDs. J Oral Facial Pain Headache. 2023. Vol. 37. P. 195–206.
Velly A. M., Anderson G. C., Look J. O., Riley J. L., Rindal D. B., Johnson K., et al. Management of painful temporomandibular disorders. J Am Dent Assoc. 2022. Vol. 153. P. 144–157.
Monje Gil F., Martínez Artal P., Cuevas Queipo De Llano A., Muñoz Guerra M., González Ballester D., López Arcas J. M., et al. Consensus report and recommendations on the management of late-stage internal derangement of the temporomandibular joint. J Clin Med. 2024. Vol. 13. P. 3319.
Yap A. U., Lai Y. C., Ho H. C. W. Prevalence of temporomandibular disorders and their associated factors in Confucian heritage cultures: a systematic review and meta-analysis. J Oral Rehabil. 2024. DOI: 10.1111/joor.13569
Shao B., Teng H., Dong S., Liu Z. Finite element contact stress analysis of the temporomandibular joints of patients with temporomandibular disorders under mastication. Comput Methods Programs Biomed. 2022. Vol. 213. P. 106526. DOI: 10.1016/j. cmpb.2021.106526
Cadar M., Almășan O. Dental occlusion characteristics in subjects with bruxism. Med Pharm Rep. 2023. Vol. 97. P. 70–75. DOI: 10.15386/ mpr-2523
Almășan O., Leucuța D. C., Dinu C., Buduru S., Băciuț M., Hedeșiu M. Petrotympanic fissure architecture and malleus location in temporomandibular joint disorders. Tomography. 2022. Vol. 8. P. 2460–2470. DOI: 10.3390/tomography8050205
Jha N., Lee K., Kim Y. J. Diagnosis of temporomandibular disorders using artificial intelligence technologies: a systematic review and meta-analysis. PLoS One. 2022. Vol. 17. P. e0272715. DOI: 10.1371/ journal.pone.0272715
Ozsari S., Güzel M. S., Yılmaz D., Kamburoğlu K. A comprehensive review of artificial intelligence-based algorithms regarding temporomandibular joint-related diseases. Diagnostics (Basel). 2023. Vol. 13. P. 2700. DOI: 10.3390/ diagnostics13162700
Li M., Punithakumar K., Major P. W., Le L. H., Nguyen K. C. T., Pacheco-Pereira C., et al. Temporomandibular joint segmentation in MRI images using deep learning. J Dent. 2022. Vol. 127. P. 104345. DOI: 10.1016/j.jdent.2022.104345
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. Vol. 138. P. 128–141. DOI: 10.1016/ j.oooo.2024.04.012
Nozawa M., Ito H., Ariji Y., Fukuda M., Igarashi C., Nishiyama M., et al. Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique. Dentomaxillofac Radiol. 2022. Vol. 51. P. 20210185. DOI: 10.1259/dmfr.20210185
Ito S., Mine Y., Yoshimi Y., Takeda S., Tanaka A., Onishi A., et al. Automated segmentation of articular disc of the temporomandibular joint on magnetic resonance images using deep learning. Sci Rep. 2022. Vol. 12. P. 221. DOI: 10.1038/ s41598-021-04308-3
Taborri J., Molinaro L., Russo L., Palmerini V., Larion A., Rossi S. Comparison of machine learning algorithms fed with mobility-related and baropodometric measurements to identify temporomandibular disorders. Sensors (Basel). 2024. Vol. 24. P. 3646. DOI: 10.3390/s24113646
Rokhshad R., Mohammad-Rahimi H., Sohrabniya F., Jafari B., Shobeiri P., Tsolakis I. A., et al. Deep learning for temporomandibular joint arthropathies: a systematic review and meta-analysis. J Oral Rehabil. 2024. Vol. 51. P. 1632–1644. DOI: 10.1111/ joor.13639
Zhang Y., Zhu T., Zheng Y., Xiong Y., Liu W., Zeng W., et al. Machine learning-based medical imaging diagnosis in patients with temporomandibular disorders: a diagnostic test accuracy systematic review and meta-analysis. Clin Oral Investig. 2024. Vol. 28. P. 186. DOI: 10.1007/ s00784-023-05366-5
Mureșanu S., Almășan O., Hedeșiu M., Dioșan L., Dinu C., Jacobs R. Artificial intelligence models for clinical usage in dentistry with a focus on dentomaxillofacial CBCT: a systematic review. Oral Radiol. 2023. Vol. 39. P. 18–40. DOI: 10.1007/ s11282-022-00623-4
Thanathornwong B., Treebupachatsakul T., Teechot T., Poomrittigul S., Warin K., Suebnukarn S. Temporomandibular joint disorders multiclass classification using deep learning. Stud Health Technol Inform. 2024. Vol. 310. P. 1495–1496. DOI: 10.3233/ SHTI240456
Dong K., Zhou C., Ruan Y., Li Y. MobileNetV2 model for image classification. In: Proceedings of the 2020 2nd International Conference on Information Technology and Computer Application (ITCA); 2020 Dec 18–20; Guangzhou, China. Guangzhou: IEEE; 2020. P. 476–480. DOI: 10.1109/ ITCA52113.2020.00098
Salehi A. W., Khan S., Gupta G., Alabduallah B. I., Almjally A., Alsolai H., et al. A study of CNN and transfer learning in medical imaging: advantages, challenges, future scope. Sustainability. 2023. Vol. 15. P. 5930. DOI: 10.3390/su15075930
Shrivastava M., Ye L. Neuroimaging and artificial intelligence for assessment of chronic painful temporomandibular disorders: a comprehensive review. Int J Oral Sci. 2023. Vol. 15. P. 58. DOI: 10.1038/ s41368-023-00249-5
Yoon K., Kim J. Y., Kim S. J., Huh J. K., Kim J. W., Choi J. Explainable deep learning-based clinical decision support engine for MRI-based automated diagnosis of temporomandibular joint anterior disk displacement. Comput Methods Programs Biomed. 2023. Vol. 233. P. 107465. DOI: 10.1016/ j.cmpb.2023.107465
Talaat W. M., Shetty S., Al Bayatti S., Talaat S., Mourad L., Shetty S., et al. An artificial intelligence model for the radiographic diagnosis of osteoarthritis of the temporomandibular joint. Sci Rep. 2023. Vol. 13. P. 15972. DOI: 10.1038/ s41598-023-43041-7
Sandler M., Howard A., Zhu M., Zhmoginov A., Chen L. C. MobileNetV2: inverted residuals and linear bottlenecks [preprint]. arXiv. 2019. P. 1801.04381. DOI: 10.48550/arXiv.1801.04381
Reda B., Contardo L., Prenassi M., Guerra E., Derchi G., Marceglia S. Artificial intelligence to support early diagnosis of temporomandibular disorders: a preliminary case study. J Oral Rehabil. 2023. Vol. 50. P. 31–38. DOI: 10.1111/joor.13456
Kao Z. K., Chiu N. T., Wu H. T. H., Chang W. C., Wang D. H., Kung Y. Y., et al. Classifying temporomandibular disorder with artificial intelligent architecture using magnetic resonance imaging. Ann Biomed Eng. 2023. Vol. 51. P. 517–526. DOI: 10.1007/s10439-022-03120-1
Kim J. Y., Kim D., Jeon K. J., Kim H., Huh J. K. Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging. Sci Rep. 2021. Vol. 11. P. 6680. DOI: 10.1038/ s41598-021-86127-7
Lee Y. H., Won J. H., Kim S., Auh Q. S., Noh Y. K. Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging. Sci Rep. 2022. Vol. 12. P. 11352. DOI: 10.1038/s41598-022-15259-5
Sano T., Widmalm S. E., Yamamoto M., Sakuma K., Araki K., Matsuda Y., et al. Usefulness of proton density and T2-weighted vs. T1-weighted MRI in diagnoses of TMJ disk status. Cranio. 2003. Vol. 21. P. 253–258. DOI: 10.1080/08869634.2003.11746252
Lee C., Ha E. G., Choi Y. J., Jeon K. J., Han S. S. Synthesis of T2-weighted images from proton density images using a generative adversarial network in a temporomandibular joint magnetic resonance imaging protocol. Imaging Sci Dent. 2022. Vol. 52. P. 393. DOI: 10.5624/isd.2022.52.4.393
Lin B., Cheng M., Wang S., Li F., Zhou Q. Automatic detection of anteriorly displaced temporomandibular joint discs on magnetic resonance images using a deep learning algorithm. Dentomaxillofac Radiol. 2022. Vol. 51. P. 20210341. DOI: 10.1259/ dmfr.20210341
Vinayahalingam S., Berends B., Baan F., Moin D. A., van Luijn R., Bergé S., et al. Deep learning for automated segmentation of the temporomandibular joint. J Dent. 2023. Vol. 132. P. 104475. DOI: 10.1016/ j.jdent.2023.104475
Kreiner M., Viloria J. A novel artificial neural network for the diagnosis of orofacial pain and temporomandibular disorders. J Oral Rehabil. 2022. Vol. 49. P. 884–889. DOI: 10.1111/joor.13358
Quinn T. P., Jacobs S., Senadeera M., Le V., Coghlan S. The three ghosts of medical AI: can the black-box present deliver? Artif Intell Med. 2022. Vol. 124. P. 102158. DOI: 10.1016/ j.artmed.2022.102158
Xiao M., Zhang L., Shi W., Liu J., He W., Jiang Z. A visualization method based on the Grad-CAM for medical image segmentation model. In: Proceedings of the 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS); 2021 Sep 23–26; Changchun, China. Changchun: IEEE; 2021. P. 242–247. DOI: 10.1109/ EIECS53707.2021.9587804
Schiffman E., Ohrbach R., Truelove E., et al. Diagnostic criteria for temporomandibular disorders (DC/ TMD) for clinical and research applications. J Oral Facial Pain Headache. 2014. Vol. 28, No. 1. P. 6–27. DOI: 10.11607/jop.1151
Valesan L. F., Da-Cas C. D., Réus J. C., et al. Prevalence of temporomandibular joint disorders: a systematic review and meta-analysis. Clin Oral Investig. 2021. Vol. 25, No. 2. P. 441–453. DOI: 10.1007/ s00784-020-03710-w
Tanimoto K., Awada T., Onishi A., Kubo N., Asakawa Y., Kunimatsu R., et al. Characteristics of the maxillofacial morphology in patients with idiopathic mandibular condylar resorption. J Clin Med. 2022. Vol. 11. P. 952. DOI: 10.3390/jcm11040952
Dujic H., Meyer O., Hoss P., et al. Automatized detection of periodontal bone loss on periapical radiographs by vision transformer networks. Diagnostics (Basel). 2023. Vol. 13, No. 23. P. 3562. DOI: 10.3390/diagnostics13233562
