With the growing capabilities of language models like ChatGPT to process text and images, this study evaluated their accuracy in detecting supernumerary teeth on periapical radiographs. A customized GPT-4V model (CGPT-4V) was also developed to assess whether domain-specific training could improve diagnostic performance compared to standard GPT-4V and GPT-4o models. One hundred eighty periapical radiographs (90 with and 90 without supernumerary teeth) were evaluated using GPT-4 V, GPT-4o, and a fine-tuned CGPT-4V model. Each image was assessed separately with the standardized prompt “Are there any supernumerary teeth in the radiograph above?” to avoid contextual bias. Three dental experts scored the responses using a three-point Likert scale for positive cases and a binary scale for negatives. Chi-square tests and ROC analysis were used to compare model performances (p < 0.05). Among the three models, CGPT-4 V exhibited the highest accuracy, detecting supernumerary teeth correctly in 91% of cases, compared to 77% for GPT-4o and 63% for GPT-4V. The CGPT-4V model also demonstrated a significantly lower false positive rate (16%) than GPT-4V (42%). A statistically significant difference was found between CGPT-4V and GPT-4o (p < 0.001), while no significant difference was observed between GPT-4V and CGPT-4V or between GPT-4V and GPT-4o. Additionally, CGPT-4V successfully identified multiple supernumerary teeth in radiographs where present. These findings highlight the diagnostic potential of customized GPT models in dental radiology. Future research should focus on multicenter validation, seamless clinical integration, and cost-effectiveness to support real-world implementation.

The aim of this study is to evaluate the surface roughness (SR) and color changes of single‐shade and nanohybrid resin‐based restorative materials (RBC) after immersion in liquids at different pH values. For RBCs, a total of 120 specimens, 30 for each material, were prepared using 10 mm diameter and 2 mm thick molds. For flowable bulk fill RBC, a total of 40 specimens, 10 for each material, were prepared using 10 mm diameter and 4 mm thick molds (n = 10). After initial color and SR measurements, samples were stored in the liquids for 14 days and all of the measurements were repeated on 14th days. Scanning electron microscopy and atomic force microscopy analyzes were performed in all groups. When SR results are examined; among all liquids, the highest SR value was observed in the Carisma Diamond One (CDO) group, while the lowest SR value was observed in the Omnichroma Flow Bulk (OMF) group (p < .05). When the color changes (ΔE) results are examined; it was observed that CDO group had highest color change and OMF group had the lowest values. It has been observed that among the liquids, the liquids that affect the ΔE values of the materials the most are coffee and cola. When the ΔE values of the subgroups of the materials were examined, there was a statistically significant difference in all subgroups of RBCs (p < .05). While acidic liquids increased the SR of RBCs, coffee more affected the color change of RBCs.Research Highlights: Clinicians should keep in mind that the RBCs tested may change their surface properties and colors when exposed to various liquids. People who have RBCs should pay attention to the consumption of acidic and highly pigmented liquids.

The aim of this study was to evaluate the degree of conversion (DC), Vickers microhardness (VHN), main components and surface properties of a microhybrid and two bulk-fill composite resins polymerized with second and third generation light emitting diodes (LED). Sixty cylindrical specimens of Filtek™ Bulk-Fill, everX Posterior (bulk technique) and Filtek Z250 (incremental technique) were prepared in plexiglass molds (5 mm in diameter and 4 mm in thickness) and cured with second-generation LED (Woodpecker LED.B) and third-generation LED (Valo) resulting in six groups (n = 10). DC was determined using Fourier transform infrared spectroscopy (FT-IR), and VHN with Vickers microhardness tester. The main components were identified by means of energy-dispersive X-ray spectroscopy (EDX) microanalysis; whereas filler particles and surface properties were analyzed by scanning electron microscopy (SEM). VHN and DC data were analyzed using two-way ANOVA, followed by t-test with Bonferroni correction for pairwise comparison (p < 0.05). When DC and VHN values were evaluated, after polymerization with second and third generation LED, there was a statistical difference in bulk-fill composites, while there was no statistical difference in microhybrid composite. While, the highest DC and VHN values were obtained after polymerization of Filtek Z250 with Valo, the lowest DC and VHN values were obtained with Filtek Bulk-Fill with Woodpecker LED.B. The degree of conversion and microhardness are affected by the structure of the composite resin and LEDs.

Purpose: The aim of this study is to evaluate and compare flexural strength and microhardness of different types of glass ionomer cements (Fuji IX GP® Fast, Riva LC HV, EQUIA Forte Fil). Materials and Methods: A total of 30 samples (n = 10) were prepared for microhardness test, and an additional total of 30 samples (n = 10) were prepared for the flexural strength test. Customized stainless steel molds (25×2×2 mm³) were produced for the flexural strength test, and 10 mm and 2 mm plexiglass molds were produced for the microhardness test. The prepared samples were stored in distilled water in a dark bottle at 37 °C (±1 °C) for 24 hours. A three-point bending test was performed using a universal testing device, and the maximum force values required to fracture the samples were determined in Newton by the device after the fracture. For the Vickers microhardness test measurements were made from different areas of the upper surfaces of each sample and the average of five measurements was calculated in MPa. Results: When comparing the flexural strength values, EQUIA Forte Fil group observed the highest flexural strength value, while Riva LC HV group had lowest flexural strength value. When comparing the microhardness values, EQUIA Forte Fil group showed the highest microhardness value, whereas Riva LC HV group observed the lowest microhardness value. Conclusion: The use of EQUIA Forte Fil, which has the highest microhardness and flexural strength values, and similarly strengthened glass ionomer cements may enhance clinical success. Key Words: glass ionomer cements; microhardness; flexural strength