Elaine Dinardi Barioni

Background: Temporomandibular disorders (TMD) may be accompanied by adaptive and degenerative remodelling of the mandibular condyle. Although computed tomography (CT) depicts established osseous changes, quantitative assessment of trabecular bone may provide additional information on local bone organization that is not captured by morphological evaluation alone. Texture analysis offers a means of characterising these differences within the condylar trabecular compartment. Objective: To investigate whether CT texture analysis can detect differences in condylar trabecular bone among patients with TMD with and without subchondral cysts and asymptomatic controls, with particular attention to peri‐cystic trabecular bone in condyles presenting subchondral cysts. Methods: In this retrospective study, 250 CT examinations were screened, and 116 patients met the inclusion criteria. Participants were allocated into three groups: TMD with subchondral cysts (TMD + Cyst; n = 60), TMD without subchondral cysts ( n = 16) and asymptomatic controls ( n = 40). Eleven grey‐level co‐occurrence matrix texture features were extracted from manually defined trabecular bone regions of interest on three central sagittal slices. In the TMD + Cyst group, the ROI was positioned adjacent to the cyst, whereas in cyst‐free condyles it was placed in the superior subchondral trabecular bone. Group comparisons were performed using the Kruskal–Wallis test with Dunn's post hoc test, false discovery rate correction and adjustment for age and gender. Receiver operating characteristic analysis evaluated the discriminatory performance of significant texture features. Results: Four texture features remained significantly different among the groups after false discovery rate correction and adjustment for age and gender: Correlation (Correlat), Sum of Squares (SumOfSqs), Sum Variance (SumVarnc) and Sum Entropy (SumEntrp) ( p < 0.05). In exploratory ROC analyses, Correlat showed the highest AUC for TMD + Cyst versus controls (AUC = 0.855). In contrast, none of the four significant texture features showed discriminatory performance statistically distinguishable from chance for TMD without Cyst versus Control, with AUCs ranging from 0.537 to 0.611 and all 95% confidence intervals including 0.5. Significant pairwise differences for the four texture features were observed between the TMD + Cyst and Control groups, whereas no significant pairwise differences were found between the TMD without Cyst and Control groups. Conclusion: CT texture analysis detected quantitative differences in condylar trabecular bone among patients with TMD with and without subchondral cysts and asymptomatic controls. The findings indicate differences in trabecular texture particularly between peri‐cystic bone in the TMD + Cyst group and subchondral bone in asymptomatic controls. Because the ROIs were biologically selected but not anatomically matched across groups, the findings should be interpreted as exploratory and do not establish a temporal sequence of trabecular remodelling leading to cyst formation.

This study aimed to assess the diagnostic performance of the Brazilian-developed artificial intelligence system DIO Inteligência® for automatic detection and classification of primary and permanent teeth in panoramic radiographs of patients in mixed dentition, using expert radiologist consensus as the reference standard. In this retrospective diagnostic accuracy study, 110 digital panoramic radiographs from patients aged 6-12 years were analyzed. The AI system automatically identified and classified individual teeth according to FDI notation. A total of 4622 teeth with definitive reference classification were included. The system's output was compared with a gold standard established by consensus of two experienced dentomaxillofacial radiologists. Diagnostic performance metrics, including accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were calculated. Overall, the AI system demonstrated high diagnostic performance, achieving an accuracy of 91%, sensitivity of 92%, and specificity of 72%. The PPV was 99%, whereas the NPV was 29%. Performance remained consistently high across most permanent tooth groups, with accuracy values around 96% and PPVs close to 100%. Third molars showed slightly lower metrics compared with other permanent groups. Primary teeth also demonstrated favorable classification performance, with high sensitivity and PPV. These findings may suggest that the DIO Inteligência® system shows robust performance in detecting and classifying primary and permanent teeth in mixed dentition panoramic radiographs, supporting its potential role as a reliable adjunct tool in pediatric dental imaging interpretation.