Objectives To develop and evaluate the performance of a deep learning system based on convolutional neural network (ConvNet) to detect dental caries from oral photographs. Methods 3,932 oral photographs obtained from 625 volunteers with consumer cameras were included for the development and evaluation of the model. A deep ConvNet was developed by adapting from Single Shot MultiBox Detector. The hard negative mining algorithm was applied to automatically train the model. The model was evaluated for: (i) classification accuracy for telling the existence of dental caries from a photograph and (ii) localization accuracy for locations of predicted dental caries. Results The system exhibited a classification area under the curve (AUC) of 85.65% (95% confidence interval: 82.48% to 88.71%). The model also achieved an image‐wise sensitivity of 81.90%, and a box‐wise sensitivity of 64.60% at a high‐sensitivity operating point. The hard negative mining algorithm significantly boosted both classification (p < .001) and localization (p < .001) performance of the model by reducing false‐positive predictions. Conclusions The deep learning model is promising to detect dental caries on oral photographs captured with consumer cameras. It can be useful for enabling the preliminary and cost‐effective screening of dental caries among large populations.

Periodontitis, an inflammatory disease of oxidative stress, occurs due to the excess reactive oxygen species (ROS) contributing to cell and tissue damage that in turn leads to alveolar bone resorption...

Introduction Antibacterial photodynamic treatment (aPDT) has indispensable significance as a means of treating periodontal disorders because of its extraordinary potential for killing pathogenic bacteria by generating an overpowering amount of reactive oxygen species (ROS). The elevated ROS that may result from the antibacterial treatment procedure, however, could exert oxidative pressure inside periodontal pockets, causing irreparable damage to surrounding tissue, an issue that has severely restricted its medicinal applications. Accordingly, herein, we report the use of black phosphorus nanosheets (BPNSs) that can eliminate the side effects of ROS-based aPDT as well as scavenge ROS to produce an antibacterial effect. Methods The antibacterial effect of ICG/aPDT was observed by direct microscopic colony counting. A microplate reader and confocal microscope enabled measurements of cell viability and the quantification of ROS fluorescence. BPNS administration regulated the oxidative environment. IL-1β, IL-6, TNF-α, IL-10, TGF-β, and Arg-1 mRNA expression levels were used to assess the inflammatory response after BPNS treatment. In vivo, the efficacy of the combination of BPNSs and ICG/aPDT was evaluated in rats with periodontal disease by histomorphometric and immunohistochemical analyses. Results The CFU assay results verified the antibacterial effect of ICG/aPDT treatment, and ROS fluorescence quantification by CLSM indicated the antioxidative ability of the BPNSs. IL-1β, IL-6, TNF-α, IL-10, TGF-β, and Arg-1 mRNA expression levels were significantly decreased after BPNS treatment, confirming the in vitro anti-inflammatory effect of this nanomaterial. The histomorphometric and immunohistochemical analyses showed that the levels of proinflammatory factors decreased, suggesting that the BPNSs had anti-inflammatory effects in vivo. Conclusion Treatment with antioxidative BPNSs gives new insights into future anti-inflammatory therapies for periodontal disease and other infection-related inflammatory illnesses and provides an approach to combat the flaws of aPDT.

Graphical AbstractWe introduce novel mitophagy enhancer, MitoQ@PssL NPs exert excellently anti-inflammatory effects by activating mitophagy and clearing partial mitochondrial ROS, thereby accelarating osteogenesis in periodontitis.

Graphical AbstractIn TMJ-OA, CNPs could effectively remove ROS in chondrocytes by activating the Nrf2/HO-1 signaling pathway and exert excellent antioxidant and anti-inflammatory effects.