CBCT assisted diagnosis system for temporomandibular joint disc displacement based on deep learning.

Residents' journal review

Purpose: The purpose of this study was to analyze the size and morphology of mandibular condyle and mandibular fossa between temporomandibular joint (TMJ) disc displacement (DD) patients and healthy subjects using cone-beam computed tomography (CBCT). Methods: Twenty healthy subjects and twenty TMJ DD patients participated in this study respectively. We made five measurements in mandibular condyle (medio-lateral dimension, antero-posterior dimension, condyle height, intercondylar distance and intercondylar angle) and two measurements in mandibular fossa (mandibular fossa depth and articular eminence angle) using CBCT image. Results: There was no difference between two groups in medio-lateral dimension. In case of antero-posterior dimension, average of healthy controls was larger than that of TMJ DD patients, but that was not significant statistically. There were no significant differences between two groups in condyle height. Comparing intercondylar distance and intercondylar angle between two groups, there was no significant difference between two groups. In comparison of mandibular fossa depth and articular eminence angle, there was no significant difference between two groups. Conclusions: We couldn't find any definite relationship between TMJ morphology and TMJ DD.

Influence of temporomandibular joint disc displacement on craniocervical posture and hyoid bone position

The purpose of this study was to propose a machine learning model and assess its ability to classify temporomandibular joint (TMJ) disc displacements on MR T1-weighted and proton density-weighted images. This retrospective cohort study included 180 TMJs from 90 patients with TMJ signs and symptoms. A radiomics platform was used to extract imaging features of disc displacements. Thereafter, different machine learning algorithms and logistic regression were implemented on radiomics features for feature selection, classification, and prediction. The radiomics features included first-order statistics, size- and shape-based features, and texture features. Six classifiers, including logistic regression, random forest, decision tree, k-nearest neighbours (KNN), XGBoost, and support vector machine were used for a model building which could predict the TMJ disc displacements. The performance of models was evaluated by sensitivity, specificity, and ROC curve. KNN classifier was found to be the most optimal machine learning model for prediction of TMJ disc displacements. The AUC, sensitivity, and specificity for the training set were 0.944, 0.771, 0.918 for normal, anterior disc displacement with reduction (ADDwR) and anterior disc displacement without reduction (ADDwoR) while testing set were 0.913, 0.716, and 1 for normal, ADDwR, and ADDwoR. For TMJ disc displacements, skewness, root mean squared, kurtosis, minimum, large area low grey level emphasis, grey level non-uniformity, and long-run high grey level emphasis, were selected as optimal features. This study has proposed a machine learning model by KNN analysis on TMJ MR images, which can be used for TMJ disc displacements.

Skeletal Differences in Patients With Temporomandibular Joint Disc Displacement According to Sagittal Jaw Relationship

Magnetic resonance imaging-verified temporomandibular joint disk displacement in relation to sagittal and vertical jaw deformities

To compare the prevalence and type of temporomandibular joint (TMJ) disk displacement in asymptomatic volunteers with those in patients. Bilateral oblique sagittal and oblique coronal intermediate-weighted magnetic resonance (MR) images of the TMJs in 58 patients with pain and dysfunction were analyzed and compared with corresponding MR images of 62 asymptomatic volunteers. Forty-five (78%) of 58 patients had disk displacement compared with 22 (35%) of 62 asymptomatic volunteers. Complete disk displacement was found in 46 (40%) of 115 joints in patients compared with three (2.4%) of 124 joints in asymptomatic volunteers, whereas partial disk displacement occurred in 26 (22.6%) and 27 (21.8%) joints, respectively. Two types of complete disk displacement, anterolateral and anterior, occurred frequently in patients, seldom in volunteers. Only minor differences were found between other types of disk displacement when prevalence in patients was compared with that of volunteers. The disk reduced to a normal position on open-mouth images in all joints in the volunteers compared with 76% of the joints in patients. TMJ disk displacement was less prevalent and was of a different type in asymptomatic volunteers compared with patients with pain and dysfunction.

CPSC launches publication on product-related injuries

The present study aimed to evaluate any relationship between elongated styloid process (ESP) and temporomandibular joint disc displacement (TMJD). A retrospective cohort study. Dentomaxillofacial Radiology division of Erciyes University Dental Hospital. Ninety-four temporomandibular joints (TMJs) of 47 patients were allocated in this study. Intervention-disease: Two experienced dentomaxillofacial radiologists have interpreted all CBCT and MR images. Patients who referred with TMJ disorders were classified according to temporomandibular joint's disc status as normal disc position (ND), displacement with reduction (DWR) and displacement without reduction (DWoR). Main outcome measures: Interpretation of styloid chain calcification pattern and styloid processes length measured linearly on reconstructed sagittal slices of CBCT. Randomization: Cone beam computed tomography (CBCT) and magnetic resonance (MR) images of 154 patients who were admitted between September 1, 2012 and September 1, 2019. Only 47 of them fulfilled the study requirements. Blinding: Single blind of the outcome measurements and interpretations of MR images. Total 94 TMJs of 47 patients disc status groups were analyzed and defined as DWoR (n = 25), DWR (n = 32), and ND (n = 37). On multivariate analysis, no statistical significant differences were found between groups in terms of styloid process lengths. Mean SP length and standard deviation of disc status groups (DWoR, DWR, and ND) are 35.5 (± 9.8)mm, 34.6 (± 9.2)mm, and 38.3 (± 8.9)mm, respectively. When patients were grouped individually according to their post-MRI diagnosis, the mean styloid process length in the non-temporomandibular joint disc displacement (non-TMJD) patients (47.9 ± 10.8) was significantly higher than the TMJD patients (36.1 ± 9.3). In this study, there is no intervention to cause any harm or side effects. Our results indicate that styloid-stylohyoid syndrome may be misdiagnosed with temporomandibular joint disorder (TMD). Clinical Trials NCT04280107.

The temporomandibular joint (TMJ) disc displacement is the most common temporomandibular disorders (TMD) condition. It causes clicking, pain, limited mandibular movements, and even masticatory difficulties in many people. The aim of this study is showcasing hotspots and frontiers in the field and providing a reference for the future research by a bibliometric analysis. Studies published from 1992 to 2022 were retrieved from Web of Science Core Collection on 23 April 2023. A total of 1882 studies (1739 articles and 143 reviews) were included in the bibliometric analysis. From 1992 to 2022, the annual number of publications and citations greatly increased. The United States of America (USA) contributed the most publications about TMJ disc displacement. Shanghai Jiao Tong University was the most productive institution; meanwhile, Yang, C. from this institution was the most prolific author. The University of Washington was the most influential institution, and Brooks, S. was the most influential author. Diagnostic criteria and management of TMJ disc displacement, as well as TMJ disc displacement-associated conditions, might be a hotspot for current global research. We provided an objective and valuable reference for future research on TMJ disc displacement.

Magnetic resonance imaging (MRI) is the gold standard for diagnosing disc displacement in temporomandibular joint (TMJ) disorders, but its high cost and practical challenges limit its accessibility. This study aimed to develop a machine learning (ML) model that can predict TMJ disc displacement using only cone-beam computed tomography (CBCT)-based radiomics features without MRI. CBCT images of 247 mandibular condyles from 134 patients who also underwent MRI scans were analyzed. To conduct three experiments based on the classification of various patient groups, we trained two ML models, random forest (RF) and extreme gradient boosting (XGBoost). Experiment 1 classified the data into three groups: Normal, disc displacement with reduction (DDWR), and disc displacement without reduction (DDWOR). Experiment 2 classified Normal versus disc displacement group (DDWR and DDWOR), and Experiment 3 classified Normal and DDWR versus DDWOR group. The RF model showed higher performance than XGBoost across all three experiments, and in particular, Experiment 3, which differentiated DDWOR from other conditions, achieved the highest accuracy with an area under the receiver operating characteristic curve (AUC) values of 0.86 (RF) and 0.85 (XGBoost). Experiment 2 followed with AUC values of 0.76 (RF) and 0.75 (XGBoost), while Experiment 1, which classified all three groups, had the lowest accuracy of 0.63 (RF) and 0.59 (XGBoost). The RF model, utilizing radiomics features from CBCT images, demonstrated potential as an assistant tool for predicting DDWOR, which requires the most careful management.

Female adolescent facial pattern associated with TMJ disk displacement and reduction in disk length: Part I

Objective. The aim of this study was to investigate the effects of temporomandibular joint (TMJ) symptoms on skeletal morphologies of orthodontic patients with TMJ disc displacement (DD). Materials and methods. The sample consisted of 197 women seeking orthodontic treatment. The subjects were divided into two groups according to the presence of TMJ symptoms: the presence and absence of TMJ symptoms. Each group was sub-divided into three groups based on magnetic resonance images of bilateral TMJs: bilateral normal disc position (BN), bilateral disc displacement with reduction (DDR) and bilateral disc displacement without reduction (DDNR). Seventeen variables from lateral cephalograms were analyzed by two-way analysis of variance to identify differences in skeletal morphologies with respect to TMJ symptoms and TMJ DD status. Results. Patients with TMJ DD were more likely to have short ramus height, short mandibular body length and backward positioning of the ramus and mandible. These skeletal morphologies became more severe as TMJ DD progressed to DDNR. However, the skeletal morphologies associated with TMJ DD were not significantly different between symptomatic and asymptomatic patients. As a result, patients with TMJ DD had backward positioning and clockwise rotation compared to those with bilateral normal TMJs, irrespective of the presence of TMJ symptom. Conclusions. This study suggests that TMJ DD is associated with altered skeletal morphology, but TMJ symptoms do not significantly influence the relationships between TMJ DD and skeletal morphology.

The aim of the present study was to compare the effect of transcutaneous electric nerve stimulation (TENS) with the flat occlusal splint in the treatment of temporomandibular joint (TMJ) disk displacement without reduction. Thirty-one patients were included and randomly selected to be treated 6 weeks with either TENS (90 Hz, 30 min, three times/day) or with a flat occlusal splint (24 h/day. Those selected for the TENS group had one electrode placed over the painful TMJ and another electrode over the anterior temporal muscle. The splint group used a conventional flat occlusal splint with cuspid guidance. Both treatment groups visited the clinic once a week. Symptoms and signs were registered before and after treatment. The intensity of pain was recorded with a visual analogue scale (VAS) and with an electronic pocket-sized recorder (Pain-Track) carried 1 week before and also the last week of treatment for continuous registration of pain. Measured with the VAS, half of the patients treated with splints became pain-free or their TMJ pain improved at least 50% both at rest and with jaw function compared with only 6% in the TENS-treated group. With regard to strictly chewing pain, the VAS-registered pain improved in two-thirds of the splint group, compared with 50% of the TENS group. With the Pain-Track device it was found that in most individuals pain was aggrevated at mealtimes. The conclusion was that flat occlusal splints in several respects are better than TENS in the treatment of symptoms associated with TMJ disk displacement without reduction.

Cartilage changes link retrognathic mandibular growth to TMJ disc displacement in a rabbit model