Background/Objectives: This study aimed to evaluate the volumes of the maxillary sinus, nasal cavity, and nasolacrimal duct in individuals with unilateral and bilateral cleft lip and palate (CLP) using an artificial intelligence-assisted segmentation method and to compare the findings with those of healthy controls. Methods: This retrospective study included 25 unilateral CLP patients, 20 bilateral CLP patients, and 25 healthy controls. Maxillary sinus, nasal cavity, and nasolacrimal duct volumes were measured on cone-beam computed tomography (CBCT) images using an artificial intelligence-assisted segmentation method. Total volume differences among groups were analyzed using analysis of covariance (ANCOVA) adjusted for age and sex. Side-based comparisons were performed using linear mixed-effects models. Benjamini–Hochberg correction was applied for multiple comparisons. Results: The control group exhibited greater maxillary sinus, nasal cavity, and nasolacrimal duct volumes than the CLP groups. ANCOVA demonstrated nominally significant group differences for the maxillary sinus (p = 0.008), nasal cavity (p = 0.034), and nasolacrimal duct (p = 0.023); however, these differences were no longer significant after Benjamini–Hochberg correction (q > 0.05). Pairwise comparisons showed greater maxillary sinus volumes in controls than in the unilateral (p = 0.037) and bilateral CLP groups (p = 0.007), and greater nasal cavity volumes than in the unilateral (p = 0.049) and bilateral CLP groups (p = 0.045). Nasolacrimal duct volume differed only between the bilateral CLP and control groups (p = 0.021). No significant volumetric differences were found between unilateral and bilateral CLP groups. Conclusions: Although individuals with CLP showed a trend toward reduced maxillary sinus, nasal cavity, and nasolacrimal duct volumes, the total-volume differences did not remain significant after correction for multiple comparisons; reductions relative to the control sides persisted after correction only for the maxillary sinus and the nasolacrimal duct in the side-based analysis. No significant differences were observed between unilateral and bilateral CLP or between the two sides within any group.
Background/Objectives: The aim of this study was to assess the diagnostic capabilities of three large language model-based artificial intelligence chatbots (ChatGPT 4.0, Gemini 2.5, and Microsoft Copilot) in the radiographic evaluation of jaw lesions on panoramic images with different densities (mixed, radiolucent, and radiopaque). Methods: 120 panoramic radiographs showing jaw lesions with varying radiographic appearances were independently analyzed using three artificial intelligence chatbot systems. Each model was provided with the same single-round prompt and a standardized diagnostic scoring framework encompassing lesion structure, configuration, border characteristics, morphology, relationship with teeth, effects on adjacent structures, biological behavior indicators, and total diagnostic scores. Descriptive statistics were reported as mean ± standard deviation and median (minimum-maximum). Differences between LLM scores were analyzed using the Kruskal–Wallis test, followed by Bonferroni-corrected post hoc comparisons. The statistical significance level was set at p < 0.05. Results: Significant differences were observed among the LLMs across multiple diagnostic categories, including lesion structure, configuration, border characteristics, and total scores (p < 0.05). Gemini achieved the highest total scores in radiolucent (11.49 ± 4.97) and mixed lesions (9.01 ± 5.78), whereas ChatGPT showed slightly higher performance in radiopaque lesions (10.93 ± 2.88). Copilot demonstrated the lowest overall performance across all lesion categories. Conclusions: Large language model–based artificial intelligence chatbots showed variable performance in the panoramic radiographic evaluation of jaw lesions with radiolucent, radiopaque, and mixed patterns, suggesting potential utility as supportive tools. However, further validation studies are required before routine clinical implementation.