Automatic Classification of Temporomandibular Joint Disorders by Magnetic Resonance Imaging and Convolutional Neural Networks

Overview

Journal J Dent Sci

Date 2025 Jan 28

PMID 39873009

Authors

Ting-Yi Su

Jacky Chung-Hao Wu

Wen-Chi Chiu

Tzeng-Ji Chen

Wen-Liang Lo

Henry Horng-Shing Lu

Affiliations

Soon will be listed here.

Abstract

Background/purpose: In this study, we utilized magnetic resonance imaging data of the temporomandibular joint, collected from the Division of Oral and Maxillofacial Surgery at Taipei Veterans General Hospital. Our research focuses on the classification and severity analysis of temporomandibular joint disease using convolutional neural networks.

Materials And Methods: In gray-scale image series, the most critical features often lie within the articular disc cartilage, situated at the junction of the temporal bone and the condyles. To identify this region efficiently, we harnessed the power of You Only Look Once deep learning technology. This technology allowed us to pinpoint and crop the articular disc cartilage area. Subsequently, we processed the image by converting it into the HSV format, eliminating surrounding noise, and storing essential image information in the V value. To simplify age and left-right ear information, we employed linear discriminant analysis and condensed this data into the S and H values.

Results: We developed the convolutional neural network with six categories to identify severe stages in patients with temporomandibular joint (TMJ) disease. Our model achieved an impressive prediction accuracy of 84.73%.

Conclusion: This technology has the potential to significantly reduce the time required for clinical imaging diagnosis, ultimately improving the quality of patient care. Furthermore, it can aid clinical specialists by automating the identification of TMJ disorders.

References

De Rossi S, Greenberg M, Liu F, Steinkeler A . Temporomandibular disorders: evaluation and management. Med Clin North Am. 2014; 98(6):1353-84. DOI: 10.1016/j.mcna.2014.08.009. View

Choi E, Kim D, Lee J, Park H . Artificial intelligence in detecting temporomandibular joint osteoarthritis on orthopantomogram. Sci Rep. 2021; 11(1):10246. PMC: 8119725. DOI: 10.1038/s41598-021-89742-y. View

Cai X, Jin J, Yang C . Changes in disc position, disc length, and condylar height in the temporomandibular joint with anterior disc displacement: a longitudinal retrospective magnetic resonance imaging study. J Oral Maxillofac Surg. 2011; 69(11):e340-6. DOI: 10.1016/j.joms.2011.02.038. View

Kao Z, Chiu N, Wu H, Chang W, Wang D, Kung Y . Classifying Temporomandibular Disorder with Artificial Intelligent Architecture Using Magnetic Resonance Imaging. Ann Biomed Eng. 2022; 51(3):517-526. DOI: 10.1007/s10439-022-03056-2. View

Ottria L, Candotto V, Guzzo F, Gargari M, Barlattani A . Temporomandibular joint and related structures: anatomical and Histological aspects. J Biol Regul Homeost Agents. 2018; 32(2 Suppl. 1):203-207. View

Racich M . Occlusion, temporomandibular disorders, and orofacial pain: An evidence-based overview and update with recommendations. J Prosthet Dent. 2018; 120(5):678-685. DOI: 10.1016/j.prosdent.2018.01.033. View

Lee Y, Won J, Kim S, Auh Q, Noh Y . Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging. Sci Rep. 2022; 12(1):11352. PMC: 9256683. DOI: 10.1038/s41598-022-15231-5. View

Ferreira L, Grossmann E, Januzzi E, de Paula M, Carvalho A . Diagnosis of temporomandibular joint disorders: indication of imaging exams. Braz J Otorhinolaryngol. 2016; 82(3):341-52. PMC: 9444643. DOI: 10.1016/j.bjorl.2015.06.010. View

Lopes S, Costa A, Cruz A, Li L, De Almeida S . Clinical and MRI investigation of temporomandibular joint in major depressed patients. Dentomaxillofac Radiol. 2012; 41(4):316-22. PMC: 3729006. DOI: 10.1259/dmfr/27328352. View

10.

Talaat W, Adel O, Al Bayatti S . Prevalence of temporomandibular disorders discovered incidentally during routine dental examination using the Research Diagnostic Criteria for Temporomandibular Disorders. Oral Surg Oral Med Oral Pathol Oral Radiol. 2017; 125(3):250-259. DOI: 10.1016/j.oooo.2017.11.012. View

11.

Ozsari S, Guzel M, Yilmaz D, Kamburoglu K . A Comprehensive Review of Artificial Intelligence Based Algorithms Regarding Temporomandibular Joint Related Diseases. Diagnostics (Basel). 2023; 13(16). PMC: 10453523. DOI: 10.3390/diagnostics13162700. View

12.

Humayun A, Ghaffarzadegan S, Feng Z, Hasan T . Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection. Annu Int Conf IEEE Eng Med Biol Soc. 2018; 2018:1408-1411. DOI: 10.1109/EMBC.2018.8512578. View

13.

Nozawa M, Ito H, Ariji Y, Fukuda M, Igarashi C, Nishiyama M . Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique. Dentomaxillofac Radiol. 2021; 51(1):20210185. PMC: 8693319. DOI: 10.1259/dmfr.20210185. View