Clinical outcomes of self-glazed zirconia veneers produced by 3D gel deposition: a retrospective study.

BACKGROUND: Self-glazed zirconia (SZ) restorations are made by a novel additive three-dimensional gel deposition approach, which are suitable for a straightforward completely digital workflow. SZ has recently been used as minimally invasive veneer, but its clinical outcomes have not been clarified yet. This study aimed to evaluate the preliminary clinical outcomes of SZ veneers compared with the widely used lithium disilicate glass-ceramic veneers made by either pressing (PG) or milling (MG) process. METHODS: Fifty-six patients treated with SZ, PG, and MG veneers by 2 specialists between June 2018 and October 2022 were identified. Patients were recalled for follow-up at least 1 year after restoration. Clinical outcomes were assessed by 2 independent evaluators according to the modified United States Public Health Service (USPHS) criteria. Overall patient satisfaction was assessed using visual analogue scale (VAS), and analyzed by one-way ANOVA. Chi-square test was applied to compare the difference in the success and survival rates among the 3 groups. RESULTS: A total of 51 patients restored with 45 SZ, 40 PG, and 41 MG veneers completed the study, with a patient dropout rate of 8.9%. Mean and standard deviation of follow-up period was 35.0 ± 14.7 months. All restorations performed well at baseline, except for 2 SZ veneers with mismatched color (rated Bravo). During follow-up, marginal discrepancy (rated Bravo) was found in 4 MG veneers and 1 PG veneer, and partially fractured (rated Charlie) was found in another 2 PG veneers. The survival rate of SZ, PG, and MG veneers was 100%, 95%, and 100%, with a success rate of 95.56%, 92.50%, and 90.24%, respectively, none of which were significantly different (p = 0.099 and 0.628, respectively). The mean VAS score of SZ, PG, and MG was 95.00 ± 1.57, 93.93 ± 2.40, and 94.89 ± 2.00 respectively, without significant difference (p > 0.05). CONCLUSION: SZ veneers exhibited comparable preliminary clinical outcomes to PG and MG veneers, which could be considered as a feasible option for minimally invasive restorative treatment.

Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study.

BACKGROUND: Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance. METHODS: The AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden's index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05). RESULTS: Sensitivity, specificity, and Youden's index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976-0.983, impacted teeth), 0.975 (95%CI: 0.972-0.978, full crowns), and 0.935 (95%CI: 0.929-0.940, residual roots), 0.939 (95%CI: 0.934-0.944, missing teeth), and 0.772 (95%CI: 0.764-0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001). CONCLUSIONS: The AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3-10 years of experience. However, the AI framework for caries diagnosis should be improved.

Three-dimensional fit of self-glazed zirconia monolithic crowns fabricated by wet deposition.

This study evaluated the 3-dimensional (3D) fit of self-glazed zirconia monolithic crowns fabricated by wet deposition, in comparison with milled zirconia and lithium disilicate monolithic crowns. Dual-scan protocol was used to assess the fit of crowns. Root mean squares (RMS) and uniformity index (UI) were calculated to describe the gap size and uniformity. The self-glazed zirconia crowns had significantly lower RMS values for the gaps at axial wall and transition regions than the milled zirconia crowns, and for the gaps at occlusal region than both milled crowns. All 3 types of crowns had comparable RMS values for the gaps at marginal and chamfer regions and comparable UI values for both marginal and internal gaps. The 3D fit of the self-glazed zirconia monolithic crowns was clinically acceptable and they exhibited better fit at occlusal region than the milled crowns.