Convolutional neural networks combined with classification algorithms for the diagnosis of periodontitis.

OBJECTIVES: We aim to develop a deep learning model based on a convolutional neural network (CNN) combined with a classification algorithm (CA) to assist dentists in quickly and accurately diagnosing the stage of periodontitis. MATERIALS AND METHODS: Periapical radiographs (PERs) and clinical data were collected. The CNNs including Alexnet, VGG16, and ResNet18 were trained on PER to establish the PER-CNN models for no periodontal bone loss (PBL) and PBL. The CAs including random forest (RF), support vector machine (SVM), naive Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN) were added to the PER-CNN model for control, stage I, stage II and stage III/IV periodontitis. Heat map was produced using a gradient-weighted class activation mapping method to visualize the regions of interest of the PER-Alexnet model. Clustering analysis was performed based on the ten PER-CNN scores and the clinical characteristics. RESULTS: The accuracy of the PER-Alexnet and PER-VGG16 models with the higher performance was 0.872 and 0.853, respectively. The accuracy of the PER-Alexnet + RF model with the highest performance for control, stage I, stage II and stage III/IV was 0.968, 0.960, 0.835 and 0.842, respectively. Heat map showed that the regions of interest predicted by the model were periodontitis bone lesions. We found that age and smoking were significantly related to periodontitis based on the PER-Alexnet scores. CONCLUSION: The PER-Alexnet + RF model has reached high performance for whole-case periodontal diagnosis. The CNN models combined with CA can assist dentists in quickly and accurately diagnosing the stage of periodontitis.

An injectable MB/BG@LG sustained release lipid gel with antibacterial and osteogenic properties for efficient treatment of chronic periodontitis in rats.

Periodontitis is a chronic inflammatory disease characterized by the colonization of pathogenic microorganisms and the loss of periodontal supporting tissue. However, the existing local drug delivery system for periodontitis has some problems including subpar antibacterial impact, easy loss, and unsatisfactory periodontal regeneration. In this study, a multi-functional and sustained release drug delivery system (MB/BG@LG) was developed by encapsulating methylene blue (MB) and bioactive glass (BG) into the lipid gel (LG) precursor by Macrosol technology. The properties of MB/BG@LG were characterized using a scanning electron microscope, a dynamic shear rotation rheometer, and a release curve. The results showed that MB/BG@LG could not only sustained release for 16 days, but also quickly fill the irregular bone defect caused by periodontitis through in situ hydration. Under 660 â€‹nm light irradiation, methylene blue-produced reactive oxygen species (ROS) can reduce local inflammatory response by inhibiting bacterial growth. In addition, in vitro and vivo experiments have shown that MB/BG@LG can effectively promote periodontal tissue regeneration by reducing inflammatory response, promoting cell proliferation and osteogenic differentiation. In summary, MB/BG@LG exhibited excellent adhesion properties, self-assembly properties, and superior drug release control capabilities, which improved the clinical feasibility of its application in complex oral environments.