A nomogram for classification of temporomandibular joint disk perforation based on magnetic resonance imaging

Perforation of the temporomandibular joint disc: cadaveric anatomical study

The aim of this human cadaveric study was to investigate the relationship between temporomandibular joint disc perforation and bony changes of the mandibular condyle. Overall, 135 cadaveric mandibles were used (69 male, 66 female; all White). Mean age at death was 78.7 years. Perforation of the disc was investigated. Differences in the area of the perforation according to the different types of bony change (erosion, flattening, osteophyte) were evaluated. Perforation of the disc was observed in 34.8% of all mandibles, occurring unilaterally in 53.2% of cases and bilaterally in 46.8%. The prevalence of perforation was 16.4% in cadavers <80 years old (67 heads) and 52.9% in those ≥80 years old (68 heads) (P < 0.001). Osteophyte formation was always identified along with other bony changes (21.7%) and never in isolation. The area of the perforation was significantly larger in the groups with bony changes (one, two, or three changes) than in the 'no bony change' group. The group with osteophyte formation showed a significantly larger perforated area than the group without osteophyte formation; likewise, the group with flattening showed a significantly larger perforated area than the group without flattening. Osteophytes and flattening are probably secondary bony changes that occur following disc perforation. Based on this study, disc perforation should be suspected when these findings are identified on imaging.

A Three-branch Jointed Feature and Topology Decoder guided by game-theoretic interactions for temporomandibular joint segmentation

Segmentation of the temporomandibular joint (TMJ) disc and condyle from magnetic resonance imaging (MRI) is a crucial task in TMJ internal derangement research. The automatic segmentation of the disc structure presents challenges due to its intricate and variable shapes, low contrast, and unclear boundaries. Existing TMJ segmentation methods often overlook spatial and channel information in features and neglect overall topological considerations, with few studies exploring the interaction between segmentation and topology preservation. To address these challenges, we propose a Three-Branch Jointed Feature and Topology Decoder (TFTD) for the segmentation of TMJ disc and condyle in MRI. This structure effectively preserves the topological information of the disc structure and enhances features. We introduce a cross-dimensional spatial and channel attention mechanism (SCIA) to enhance features. This mechanism captures spatial, channel, and cross-dimensional information of the decoded features, leading to improved segmentation performance. Moreover, we explore the interaction between topology preservation and segmentation from the perspective of game theory. Based on this interaction, we design the Joint Loss Function (JLF) to fully leverage the features of segmentation, topology preservation, and joint interaction branches. Results on the TMJ MRI dataset demonstrate the superior performance of our TFTD compared to existing methods.

Reliability of magnetic resonance for temporomandibular joint disc perforation: A 12 years retrospective study

The aim of this study was to evaluate the reliability of magnetic resonance imaging (MRI) in detecting disc perforations in the temporomandibular joint (TMJ), and to establish diagnostic criteria for this purpose. The retrospective analysis included patients who had undergone preoperative MRI and TMJ arthroscopy at the same hospital. Direct and indirect signs of disc abnormalities on MRI were compared with arthroscopic findings of disc perforation. Out of 355 joints evaluated in 185 patients, arthroscopy confirmed disc perforations in 14.7% of cases. Several MRI findings were significantly associated with disc perforation, including anterior disc displacement without reduction (ADDwoR), signal alterations in the mid-disc area, disc deformity (SAMD), retrocondylar disc fragments, osteophytes, condylar bone marrow degeneration (CBMD), and joint effusion in both joint spaces (ESJS-EIJS). Regression analysis revealed that SAMD, osteophytes, and CBDM were strongly associated with disc perforation. The ROC curve showed that MRI had an AUC = 0.791, with a sensitivity of 88.5% and a specificity of 61.5%. Two diagnostic methods, one based on three findings (osteophytes, ADDwoR, and SAMD) and one based on two direct signs (ADDwoR and SAMD), yielded high sensitivity and specificity values of 80.4% and 69.8%, and 84.3% and 62.5%, respectively. In conclusion, MRI demonstrated acceptable accuracy in the detection of TMJ disc perforations, with specific diagnostic criteria offering high sensitivity and specificity. Significant MRI indicators of disc perforation included SAMD, osteophytes, and CBDM. This study provides valuable information on the use of MRI as a diagnostic tool for TMJ disc perforations.

Specific tissue engineering for temporomandibular joint disc perforation

BACKGROUND

The temporomandibular joint (TMJ) disc is a critical fibrocartilaginous structure with limited regenerative capacity in the oral system. Perforation of the TMJ disc can lead to osteoarthritis and ankylosis of the TMJ because of the lack of disc protection. Clinical treatments for TMJ disc perforation, such as discectomy, hyaluronic acid injection, endoscopic surgery and high position arthroplasty of TMJ, are questionable with regard to long-term outcomes, and only three fourths of TMJ disc perforations are repairable by surgery, even in the short-term. Tissue engineering offers the potential for cure of repairable TMJ disc perforations and regeneration of unrepairable ones.

OBJECTIVES

This review discusses the classification of TMJ disc perforation and defines typical TMJ disc perforation. Advancements in the engineering-based repair of TMJ disc perforation by stem cell therapy, construction of a disc-like scaffold and functionalization by offering bioactive stimuli are also summarized in the review, and the barriers developing engineering technologies need to overcome to be popularized are discussed.

Explainable deep learning-based clinical decision support engine for MRI-based automated diagnosis of temporomandibular joint anterior disk displacement

BACKGROUND AND OBJECTIVE

MRI is considered the gold standard for diagnosing anterior disc displacement (ADD), the most common temporomandibular joint (TMJ) disorder. However, even highly trained clinicians find it difficult to integrate the dynamic nature of MRI with the complicated anatomical features of the TMJ. As the first validated study for MRI-based automatic TMJ ADD diagnosis, we propose a clinical decision support engine that diagnoses TMJ ADD using MR images and provides heat maps as the visualized rationale of diagnostic predictions using explainable artificial intelligence.

METHODS

The engine builds on two deep learning models. The first deep learning model detects a region of interest (ROI) containing three TMJ components (i.e., temporal bone, disc, and condyle) in the entire sagittal MR image. The second deep learning model classifies TMJ ADD into three classes (i.e., normal, ADD without reduction, and ADD with reduction) within the detected ROI. In this retrospective study, the models were developed and tested on the dataset acquired between April 2005 to April 2020. The additional independent dataset acquired at a different hospital between January 2016 to February 2019 was used for the external test of the classification model. Detection performance was assessed by mean average precision (mAP). Classification performance was assessed by the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and Youden's index. 95% confidence intervals were calculated via non-parametric bootstrap to assess the statistical significance of model performances.

RESULTS

The ROI detection model achieved mAP of 0.819 at 0.75 intersection over union (IoU) thresholds in the internal test. In internal and external tests, the ADD classification model achieved AUROC values of 0.985 and 0.960, sensitivities of 0.950 and 0.926, and specificities of 0.919 and 0.892, respectively.

CONCLUSIONS

The proposed explainable deep learning-based engine provides clinicians with the predictive result and its visualized rationale. The clinicians can make the final diagnosis by integrating primary diagnostic prediction obtained from the proposed engine with the patient's clinical examination findings.

Correlation between the main clinical, imaging, and arthroscopy findings in patients with temporomandibular disorders

The purpose of this work was to prospectively correlate the most characteristic clinical symptoms of temporomandibular disorders, such as pain and limitation of mouth opening, with the findings of magnetic resonance imaging (disc position, degenerative changes, and effusion) and arthroscopy findings (roofing, synovitis, chondromalacia, adhesions, and perforations). These examinations were performed in 298 patients diagnosed with internal derangement refractory to conservative treatment. The mean age of the patients was 38.59 years; 92.6% were female. The t-test and one-way analysis of variance (ANOVA) were used to correlate the findings. Significant relationships were found between pain and disc displacement without reduction (P = 0.033) and effusion (P = 0.003) on MRI, coinciding with correlations between pain and roofing of 0-25% (P = 0.016) and synovitis (P = 0.001) on arthroscopy. A significant relationship was also observed between mouth opening limitation and the presence of osteoarthrosis (P = 0.018) on MRI, and between mouth opening limitation and synovitis (P = 0.022), chondromalacia (P = 0.002), and adhesions (P < 0.001) on arthroscopy. All of these findings were observed in patients with a poor initial clinical situation, which highlights the considerable potential of correlating these data with imaging and arthroscopy findings.

Needle orientation for temporomandibular joint arthrocentesis in Koreans

OBJECTIVE

To investigate the highest opportunity skin puncture point and needle orientation according to facial asymmetry and classification.

METHODS

Computed tomography of 136 patients was analyzed. Horizontal and vertical angles and distances from the canthal-tragal line were investigated to determine the puncture point and needle's angle.

RESULT

All patients' average points were 7.39 (±2.85) mm anterior to the tragus and 3.44 (±4.18) mm below the canthal-tragal line with an angle of 8.53 (±6.90)° anteriorly and 32.26 (±7.23)° superiorly. Regarding asymmetry, there was a statistical difference in horizontal angle, depth, and canthal-tragal distance between the deviated and non-deviated sides. Especially, vertical distances were 4.44 (±4.66) mm and 2.59 (±4.11) mm in the deviated and non-deviated sides, respectively (p < 0.001).

CONCLUSION

In closed-mouth, the puncture point was closer to the tragus and lower than the conventional point. The point in the deviated side should be considered lower than the non-deviated side.

An arthroscopic technique for closure of perforations in temporomandibular joint retrodiscal tissues

The objective of this retrospective study was to introduce and evaluate an arthroscopic discopexy for closure of retrodiscal tissue perforations. A total of 112 patients (135 joints) receiving an arthroscopic discopexy for management of retrodiscal tissue perforations between January 2016 and September 2019 were included. Pre- and postoperative visual analogue scale (VAS) pain scores and maximum inter-incisal opening (MIO), as well as magnetic resonance imaging (MRI) data, were collected and analysed. Success was recorded when the disc position was >11 o'clock, VAS pain score <3, and MIO>25 mm. For patients with a condyle deformity, postoperative bone remodelling was also recorded. The VAS pain score decreased from 3.04 ± 2.66 preoperatively to 0.88 ± 1.13 at 12 months postoperatively (P < 0.001) and MIO increased from 33.90 ± 7.39 mm to 35.19 ± 6.14 mm (P = 0.029). MRI evaluation revealed that 133 discs were successfully repositioned back on top of the condyle. Among these, 11 joints were associated with either VAS pain score ≥3 or MIO ≤25 mm. Therefore, a success rate of 90.4% (122/135) was achieved at 12 months postoperative. Bone remodelling was detected in 72 joints. Arthroscopic discopexy is a minimally invasive and effective treatment for retrodiscal tissue perforations that achieves the purpose of simultaneously restoring the intra-articular structures and relieving clinical symptoms.

Biological Treatments for Temporomandibular Joint Disc Disorders: Strategies in Tissue Engineering

The temporomandibular joint (TMJ) is an important structure for the masticatory system and the pathologies associated with it affect a large part of the population and impair people's lifestyle. It comprises an articular disc, that presents low regeneration capacities and the existing clinical options for repairing it are not effective. This way, it is imperative to achieve a permanent solution to guarantee a good quality of life for people who suffer from these pathologies. Complete knowledge of the unique characteristics of the disc will make it easier to achieve a successful tissue engineering (TE) construct. Thus, the search for an effective, safe and lasting solution has already started, including materials that replace the disc, is currently growing. The search for a solution based on TE approaches, which involve regenerating the disc. The present work revises the TMJ disc characteristics and its associated diseases. The different materials used for a total disc replacement are presented, highlighting the TE area. A special focus on future trends in the field and part of the solution for the TMJ problems described in this review will involve the development of a promising engineered disc approach through the use of decellularized extracellular matrices.

Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging

The goal of this study was to develop a deep learning-based algorithm to predict temporomandibular joint (TMJ) disc perforation based on the findings of magnetic resonance imaging (MRI) and to validate its performance through comparison with previously reported results. The study objects were obtained by reviewing medical records from January 2005 to June 2018. 299 joints from 289 patients were divided into perforated and non-perforated groups based on the existence of disc perforation confirmed during surgery. Experienced observers interpreted the TMJ MRI images to extract features. Data containing those features were applied to build and validate prediction models using random forest and multilayer perceptron (MLP) techniques, the latter using the Keras framework, a recent deep learning architecture. The area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the performances of the models. MLP produced the best performance (AUC 0.940), followed by random forest (AUC 0.918) and disc shape alone (AUC 0.791). The MLP and random forest were also superior to previously reported results using MRI (AUC 0.808) and MRI-based nomogram (AUC 0.889). Implementing deep learning showed superior performance in predicting disc perforation in TMJ compared to conventional methods and previous reports.