Cone beam computed tomography (CBCT) is widely utilized tool in routine clinical practice for TMJ assessment. This retrospective study investigated the presence of changes associated with disc displacement (DD) detected in CBCT and to correlate it with gender and condylar morphology. A retrospective study was conducted on 294 joints from 147 patients (105 females, 42 males) aged 18 to 41 years. Based on TMD clinical diagnosis and magnetic resonance imaging (MRI) findings, joints were categorized into three groups: control (with normal discs), disc displacement with reduction (DDR), and disc displacement without reduction DDWR. CBCT images were evaluated for joint spaces, glenoid fossa characteristics, condylar inclination, and condyle morphology. Kruskal-Wallis, Mann-Whitney U tests, and Pearson Chi-Square tests were performed to identify differences among groups, and assess correlations of DD with condylar morphology, Multinomial logistic regression (MLR) was performed to assess and predict the influence of CBCT-derived morphological variables on TMJ DD, with the control group as the reference. DDR and DDWR groups showed significantly smaller superior (SS) and larger anterior spaces (AS) versus controls. Reduced anterior eminence inclination (AEI) and fossa height (HF) were observed in DD groups, with distal condylar inclination in DDR. Flat condyles predominated in DDWR. Females exhibited more pronounced DD-associated changes. MLR identified key predictors: reduced medial space, AEI and increased eminence height predicted DD (χ² = 192.92, P < .001; pseudo-R² 31-55%); DDWR was additionally associated with wider PS and reduced HF. CBCT can effectively detect TMJ morphological changes associated with DD. These findings provide valuable insights into the progression of DD and its demographic correlations, emphasizing the importance of CBCT in clinical diagnostics. The current study identified specific CBCT-derived radiographic features that offer insights into the condition of the TMJ articular disc, thereby enhancing the practitioner's ability to diagnose, assess, and prognosticate TMD.

This retrospective study aims to: (1) determine whether craniofacial skeletal characteristics differ based on the type of temporomandibular joint (TMJ) disc displacement (DD); and (2) identify cephalometric variables that correlate with and predict articular disc position. A total of 294 joints corresponding to 147 female patients, aged 18 to 41 years, were included. Based on the criteria of DC/TMD and subsequently magnetic resonance imaging (MRI) findings, the joints were categorized into three groups: 1) bilateral normal disc position (BN), 2) disc displacement with reduction (DDR), and 3) disc displacement without reduction (DDWR). The lateral cephalograms were assessed, and twelve landmarks were marked on each radiograph, from which fifteen variables were derived. Cone beam computed tomography (CBCT) images were evaluated for joint spaces, glenoid fossa characteristics, and condylar inclination. One-way ANOVA and post-hoc Tukey tests were used to compare variables across groups. Bivariate Pearson correlation analysis was conducted to assess relationships between glenoid fossa characteristics, disc position, condylar position, and skeletal morphology. Multiple linear regression (MLR) was applied to determine cephalometric predictors of disc position. Significant differences were observed in joint spaces, condylar inclination, and fossa morphology across the three groups. ANB, FMA, y-axis, gonial angle, and ramus height showed significant correlations with disc position. MLR demonstrated that FMA, ramus height, and articular angle were the strongest predictors of DD, particularly in DDWR, with an explanatory power of 55% (R² = 0.55, p < 0.001). Craniofacial morphology plays a key role in the pathophysiology of DD. Patients with a steeper mandibular plane (higher FMA) and reduced ramus height were more prone to DDWR. These findings highlight the importance of cephalometric evaluation in assessing TMD and predicting disc position.

Background: Childhood and adolescence constitute a critical period for craniofacial growth. Understanding its developmental patterns is essential for clinical decision-making in orthodontics and maxillofacial surgery. Traditional cephalometric analysis relies on manual landmarking, which oversimplifies complex morphology and introduces subjectivity. Although deep learning, a key artificial intelligence (AI) technology, has demonstrated remarkable performance in image analysis and classification, most methods still depend on manual annotations during training, perpetuating subjectivity and limiting model generalizability and robustness on large datasets. This hinders the development of objective, comprehensive methods to quantify craniofacial growth that account for its multi-tissue complexity. Methods: To address these limitations, this study developed an end-to-end deep learning framework based on lateral cephalometric radiographs from 41,625 individuals aged 4–18 years. Without relying on manual annotations, the model is designed to autonomously extract dynamic imaging features associated with continuous age intervals in craniofacial development and further discern features related to sexual dimorphism. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize the learned features, generating population-averaged saliency maps that highlight age-related and sex-related patterns. Furthermore, we introduced two novel quantitative metrics, the Age-related Saliency Index (ASI) and the Sex-related Saliency Index (SSI), to evaluate the significance of developmental and dimorphic characteristics in key craniofacial regions. Results: Age-related saliency maps extended the focus from external contours to internal anatomical details of the bones, intuitively visualizing the relative importance of multiple bone regions during dynamic development, with the ASI providing a quantitative prioritization of these regions. The Sex-related Saliency Index (SSI) quantified the dynamic evolution of sexual dimorphism, demonstrating that early-stage differences were widely distributed across cranial bones and gradually became concentrated in the mandibular region by adulthood. Conclusions: This study established an end-to-end deep learning framework for analyzing large-scale lateral cephalometric radiographs. By generating age- and sex-related average saliency maps and their corresponding quantitative indices, we visualized and quantified the spatiotemporal growth dynamics and sexual dimorphism across distinct craniofacial skeletal regions throughout development. These findings not only validate established developmental theories but also provide novel insights into the coordinated growth patterns of craniofacial bones and sex-specific radiological characteristics, offering clinicians objective quantitative references for assessing developmental stages and guiding the timing of interventions targeting specific craniofacial regions.

This study aimed to comprehensively analyse the interrelationships between temporomandibular joint (TMJ) morphology, craniofacial skeletal patterns, and or