Relative risk of positional and dynamic temporomandibular disc abnormality for osteoarthritis—magnetic resonance imaging study

Takaoka, Ryota; Yatani, Hirofumi; Senzaki, Yuki; Koishi, Yukiko; Moriguchi, Daisuke; Ishigaki, Shoichi

doi:10.1111/joor.13138

Cited by 8 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Joints with ADD with and without reduction were 2.73 and 8.25 times more likely to have osteoarthritis, respectively 32 . Additionally, complete ADD increased the risk of osteoarthritis by 10.88-fold 33 . Thus, disc displacement initially begins with symptoms such as clicking or popping in the TMJ area.…”

Section: Discussionmentioning

confidence: 99%

Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging

Lee

Won

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

This study investigated the usefulness of deep learning-based automatic detection of anterior disc displacement (ADD) from magnetic resonance imaging (MRI) of patients with temporomandibular joint disorder (TMD). Sagittal MRI images of 2520 TMJs were collected from 861 men and 399 women (average age 37.33 ± 18.83 years). A deep learning algorithm with a convolutional neural network was developed. Data augmentation and the Adam optimizer were applied to reduce the risk of overfitting the deep-learning model. The prediction performances were compared between the models and human experts based on areas under the curve (AUCs). The fine-tuning model showed excellent prediction performance (AUC = 0.8775) and acceptable accuracy (approximately 77%). Comparing the AUC values of the from-scratch (0.8269) and freeze models (0.5858) showed lower performances of the other models compared to the fine-tuning model. In Grad-CAM visualizations, the fine-tuning scheme focused more on the TMJ disc when judging ADD, and the sparsity was higher than that of the from-scratch scheme (84.69% vs. 55.61%, p < 0.05). The three fine-tuned ensemble models using different data augmentation techniques showed a prediction accuracy of 83%. Moreover, the AUC values of ADD were higher when patients with TMD were divided by age (0.8549–0.9275) and sex (male: 0.8483, female: 0.9276). While the accuracy of the ensemble model was higher than that of human experts, the difference was not significant (p = 0.1987–0.0671). Learning from pre-trained weights allowed the fine-tuning model to outperform the from-scratch model. Another benefit of the fine-tuning model for diagnosing ADD of TMJ in Grad-CAM analysis was the deactivation of unwanted gradient values to provide clearer visualizations compared to the from-scratch model. The Grad-CAM visualizations also agreed with the model learned through important features in the joint disc area. The accuracy was further improved by an ensemble of three fine-tuning models using diversified data. The main benefits of this model were the higher specificity compared to human experts, which may be useful for preventing true negative cases, and the maintenance of its prediction accuracy across sexes and ages, suggesting a generalized prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging

Lee

Won

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Posterior disc displacement (PDD): The disc is displaced posterior to the 12:00 position on top of the condyle 24,25 Single sideways disc displacement (single SW): The disc is laterally displaced in the coronal direction towards the medial or lateral pole; no anteroposterior abnormalities are observed in the sagittal plane 26 ADDR with SW: ADDR and SW coexisting. ADDNR with SW: ADDNR and SW coexisting. PDD with SW: PDD and SW coexisting. …”

Section: Methodsmentioning

confidence: 99%

“…24,25 e. Single sideways disc displacement (single SW): The disc is laterally displaced in the coronal direction towards the medial or lateral pole; no anteroposterior abnormalities are observed in the sagittal plane. 26 f. ADDR with SW: ADDR and SW coexisting. g. ADDNR with SW: ADDNR and SW coexisting.…”

Section: Evaluationofosseouschangesofthecondylementioning

confidence: 99%

Risk estimation of degenerative joint disease in temporomandibular disorder patients with different types of sagittal and coronal disc displacements: MRI and CBCT analysis

Fan

Xiong

Cheng

et al. 2022

J of Oral Rehabilitation

View full text Add to dashboard Cite

Background Degenerative joint disease (DJD) can be associated with disc displacement (DD) in temporomandibular disorder (TMD) patients. However, the relationship between different types of DDs and DJD remains unclear. Objectives To investigate the odds ratios of different types of sagittal and coronal DDs confirmed by magnetic resonance imaging (MRI) and DJD confirmed by cone‐beam computed tomography (CBCT) in TMD patients. Methods Radiographic data from 69 males and 232 females were collected for analysis. CBCT was used to diagnose DJD, with criteria including erosion, osteophytes, generalised sclerosis and cysts in the joint. Eight types of DDs were evaluated by sagittal and coronal MRIs: NA, no abnormality; SW, sideways; ADDR, anterior with reduction; ADDR+SW; ADDNR, anterior without reduction; ADDNR + SW; single SW; PDD, posterior; PDD + SW. The odds ratios of DJD in joints with different types of DDs were determined after joint correlation, age and gender adjustment. Results Compared with NA, the odds ratio of DJD in ADDR was 2.397 (95% CI [confidence interval]: 1.070–5.368), ADDR + SW was 4.808 (95% CI: 1.709–3.528), ADDNR was 29.982 (95% CI: 15.512–57.950) and ADDNR + SW was 25.974 (95% CI: 12.743–52.945). Erosion was significantly increased in ADDR, ADDR + SW, ADDNR and ADDNR + SW; osteophytes were significantly increased in ADDR + SW, ADDNR and ADDNR + SW; and generalised sclerosis and cysts were significantly increased in ADDNR and ADDNR + SW. There were no significant associations between single SW, PDD, PDD + SW and the DJD. Conclusions ADDR, ADDR+SW, ADDNR and ADDNR+SW were associated with DJD. ADDNR had a significantly higher prevalence of DJD than ADDR. There were no significant relationships between single SW, PDD, PDD + SW and the DJD.

show abstract

“…Joints with ADD with reduction and without reduction were 2.73 and 8.25 times more likely, respectively, to have osteoarthritis 29 . Additionally, complete ADD increased the risk of osteoarthritis by 10.88 times 30 . Thus, disc displacement initially begins with symptoms such as clicking or popping in the TMJ area; however, if this problem is not resolved, there is a potential risk that can be linked to TMD-related pain, mandibular function limitation, headaches, various psychological problems, and sleep problems 6,31 .…”

Section: Discussionmentioning

confidence: 99%

Advantages of Deep Learning with Convolutional Neural Network in Detecting Disc Displacement of the Temporomandibular Joint in Magnetic Resonance Imaging

Lee

Won

Kim

et al. 2022

Preprint

View full text Add to dashboard Cite

Aim: This study aimed to investigate the usefulness of deep-learning-based automatic detection of anterior disc displacement (ADD) in patients with temporomandibular joint disorder (TMD) using magnetic resonance imaging (MRI). Methods: Sagittal MRI images of 2520 TMJs were collected from the study population (861 men, 399 women; average age 37.33±18.83 years). A deep learning algorithm with a convolutional neural network (CNN) was performed. Data augmentation and the Adam optimizer were applied to reduce the risk of overfitting the deep learning model. The prediction performance of the models and human experts was compared using area under the curve (AUC). Results: The prediction performance of the fine-tuning model was excellent with an AUC of 0.8775, with acceptable accuracy (0.83%). On comparing the AUC values of the from-scratch (0.8269) and freeze models (0.5858), the performances of the other models were lower than that of the fine-tuning model. Through Grad-CAM visualizations, the fine-tuning scheme focused more on the TMJ disc when judging ADD, and the sparsity was higher than that of the from-scratch scheme (84.69% vs. 55.61%, p-value <0.05). In the three fine-tuning ensembled models using different data augmentation techniques, the prediction accuracy was 0.8333. Moreover, the AUC values of ADD were higher when patients with TMD were divided by age group (0.8549–0.9275) and sex (male: 0.8483, female: 0.9276). The accuracy of the ensemble model was higher than that of the human experts; however, this difference was not significant (p-value: 0.1633–0.0519). Conclusion: Our CNN model had excellent and outstanding accuracy in detecting ADD and could potentially be used by clinicians to evaluate ADD on MR images of TMD patients and improve treatment outcomes.

show abstract

Relative risk of positional and dynamic temporomandibular disc abnormality for osteoarthritis—magnetic resonance imaging study

Cited by 8 publications

References 27 publications

Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging

Advantages of deep learning with convolutional neural network in detecting disc displacement of the temporomandibular joint in magnetic resonance imaging

Risk estimation of degenerative joint disease in temporomandibular disorder patients with different types of sagittal and coronal disc displacements: MRI and CBCT analysis

Advantages of Deep Learning with Convolutional Neural Network in Detecting Disc Displacement of the Temporomandibular Joint in Magnetic Resonance Imaging

Contact Info

Product

Resources

About