Background: Identifying the diagnostic value of bitewing radiographs (BW) is highly dependent on the operator’s knowledge and experience. The aim of this study is to assess the effectiveness of machine learning (ML) to classify the BW according to their diagnostic quality. Methods: 864 BW radiographs from records of 100 patients presented at King Abdulaziz University Dental Hospital, Jeddah, Saudi Arabia were assessed. The radiographic errors in representing proximal contact areas (n = 1951) were categorized into diagnostic and non-diagnostic. Labeling and training of the BW were done using Roboflow. Data were divided into validation, training, and testing sets to train the pre-trained model Efficientdet-d0 using TensorFlow. The model’s performance was assessed by calculating recall, precision, F1 score, and log loss value. Results: The model excelled at detecting “overlap within enamel” and “overlap within restoration (clear margins) with F1 score of 0.89 and 0.76, respectively. The overall system errors made by the built model showed a log loss value of 0.15 indicating high accuracy of the model. Conclusions: The model is a “proof of concept” for the effectiveness of ML in diagnosing the quality of the BW radiographs based on the contact areas. More dataset specification and optimization are needed to overcome the class imbalance.

High-speed sintering has emerged as a promising innovation for enhancing the efficiency of dental prosthesis fabrication. However, its impact on marginal a

A dental laboratory remount-free technique for fabricating 3-dimensional (3D) printed complete dentures is presented. The method streamlines the workflow by eliminating the laboratory procedures required in conventional manufacturing to correct occlusal errors. This approach may reduce the fabrication errors, minimize postdelivery adjustments, and enhance patient comfort.

This in vitro study aims to investigate the fracture properties of 3D-printed resin provisional material designed with different connector dimensions for two-unit fixed dental prostheses (FDPs). The master model was digitally designed following Shillingburg’s all-ceramic restoration tooth preparation guidelines and milled from aluminum. Four two-unit FDPs with different connector dimensions were designed: 2 × 3 mm, 3 × 3 mm, 3 × 4 mm, and 4 × 4 mm (width × length) (Groups A, B, C, and D, respectively; n = 10 for each group). These specimens were printed using 3D-printed resin material (Detax FREEPRINT^® temp). Forty specimens were subjected to a three-point test using a universal testing machine until fracture. The failure mode was examined under a stereomicroscope. The Kruskal–Wallis test at α = 0.05 revealed non-significant differences in fracture resistance load but significantly different elastic modulus, yield strength, and compressive strength (p = 0.061, p < 0.001, p < 0.001, and p < 0.001, respectively) among the different groups. The 2 × 3 mm connectors had higher means of modulus, yield strength, and compressive strength compared to the other groups. The study found that the maximum load causing fractures in 3D-printed provisional material connectors was consistent, regardless of connector cross-section variations. The 2 × 3 mm group performed best, while the 4 × 4 mm group performed worst.

Managing implants with unknown systems presents a significant clinical challenge when obtaining an accurate master impression. This case report describes a simple technique for fabricating a customized closed‐tray implant impression post and laboratory analog when the implant system cannot be identified. The use of these customized components enabled accurate transfer of the implant position and facilitated the fabrication of a definitive prosthesis. This case report highlights a practical solution for clinicians facing similar cases involving unknown implant systems.