Detection of caries around restorations on bitewings using deep learning

OBJECTIVE

Secondary caries lesions adjacent to restorations, a leading cause of restoration failure, require accurate diagnostic methods to ensure an optimal treatment outcome. Traditional diagnostic strategies rely on visual inspection complemented by radiographs. Recent advancements in artificial intelligence (AI), particularly deep learning, provide potential improvements in caries detection. This study aimed to develop a convolutional neural network (CNN)-based algorithm for detecting primary caries and secondary caries around restorations using bitewings.

METHODS

Clinical data from 7 general dental practices in the Netherlands, comprising 425 bitewings of 383 patients, were utilized. The study used the Mask-RCNN architecture, for instance, segmentation, supported by the Swin Transformer backbone. After data augmentation, model training was performed through a ten-fold cross-validation. The diagnostic accuracy of the algorithm was evaluated by calculating the area under the Free-Response Receiver Operating Characteristics curve, sensitivity, precision, and F1 scores.

RESULTS

The model achieved areas under FROC curves of 0.806 and 0.804, and F1-scores of 0.689 and 0.719 for primary and secondary caries detection, respectively.

CONCLUSION

An accurate CNN-based automated system was developed to detect primary and secondary caries lesions on bitewings, highlighting a significant advancement in automated caries diagnostics.

CLINICAL SIGNIFICANCE

An accurate algorithm that integrates the detection of both primary and secondary caries will permit the development of automated systems to aid clinicians in their daily clinical practice.

Full analysis of the effects of modeler liquids on the properties of direct resin-based composites: a meta-analysis review of in vitro studies

OBJECTIVES

This study systematically revised the literature to answer the following question: do modeler liquids (MLs) affect the properties of direct resin-based composites (RBCs)?

MATERIALS AND METHODS

The review followed the PRISMA statement, and the search was conducted in PubMed, Scopus, Web of Science, Embase, and Lilacs databases. Studies were included if they investigated the properties of RBCs prepared using the restorative dental modeling insertion technique (RDMIT). The risk of bias was performed with the RoBDEMAT tool. Statistical analyses were conducted using Review Manager, and heterogeneity was assessed with the Cochran Q test and I² statistics.

RESULTS

From 309 studies identified, 25 met the eligibility criteria, and 23 were meta-analyzed. In total, 27 MLs and 23 RBCs were evaluated. Modeled and non-modeled RBCs showed similar results in terms of cohesive strength, flexural strength, load-to-fracture, modulus of elasticity, work of fracture, degree of conversion, solubility, weight change, microhardness, and color change. Sorption and roughness benefited from the use of MLs, whereas translucency and whitening index were more adequate in the non-modeled RBCs. Aging affected similarly the modeled and non-modeled RBCs. Most studies showed a moderate risk of bias.

CONCLUSIONS

Modeled and non-modeled RBCs performed similarly in most of the properties, and the use of non-solvated lubricants offered beneficial effects in some cases.

CLINICAL RELEVANCE

When a balance has to be made between the RDMIT and the conventional technique, our review supports the safe application of modeler liquids for the handling of composite increments during the sculpting fabrication of direct resin-based restorations.

Surface Treatments and Adhesives Used to Increase the Bond Strength Between Polyetheretherketone and Resin-based Dental Materials: A Scoping Review

PURPOSE

To identify and discuss the available surface treatments and adhesives for polyetheretherketone (PEEK) to increase its bond strength to resin-based materials used in dentistry.

MATERIALS AND METHODS

The reporting of this scoping review was based on PRISMA. The study protocol was made available at: https://osf.io/4nur9/. Studies which evaluated PEEK surface treatments and its bond strength to resin-based materials were selected. The search was performed in PubMed, Scopus, Web of Sciences and Cochrane databases. The screening was undertaken by 3 independent researchers using the Rayyan program. A descriptive analysis was performed considering study characteristics and main findings (title, data of publication, authors, PEEK characteristics, surface treatments, control group, bonded set, luting agent, specimen geometry, storage, thermocycling, pre-test failures, test geometry, failure analysis, main findings, and compliance with normative guidelines).

RESULTS

The initial search yielded 1965 articles, of which 32 were included for descriptive analysis. The review showed that the use of surface treatments and adhesives are important to promote bond strength to PEEK. Up until now, various surface treatments have been explored for bond improvement to PEEK. Sulfuric acid etching is commonly reported as promoting the highest bond strength, followed by alumina-particle air abrasion. Regarding adhesives, the use of a specific adhesive containing MMA, PETIA (pentaerythritol triacrylate), and dimethacrylates yields the best adhesive performance.

CONCLUSION

Sulfuric acid etching and alumina particle air abrasion followed by application of bonding agents containing MMA, PETIA and dimethacrylates are the most effective choices to increase resin-based materials' adhesion to PEEK.