The severity of furcation involvement (FI) directly affected tooth prognosis and influenced treatment approaches. However, assessing, diagnosing, and treating molars with FI was complicated by anatomical and morphological variations. Cone-beam computed tomography (CBCT) enhanced diagnostic accuracy for detecting FI and measuring furcation defects. Despite its advantages, the high cost and radiation dose associated with CBCT equipment limited its widespread use. The aim of this study was to evaluate the performance of the Vision Transformer (ViT) in comparison with several commonly used traditional deep learning (DL) models for classifying molars with or without FI on panoramic radiographs. A total of 1,568 tooth images obtained from 506 panoramic radiographs were used to construct the database and evaluate the models. This study developed and assessed a ViT model for classifying FI from panoramic radiographs, and compared its performance with traditional models, including Multi-Layer Perceptron (MLP), Visual Geometry Group (VGG)Net, and GoogLeNet. Among the evaluated models, the ViT model outperformed all others, achieving the highest precision (0.98), recall (0.92), and F1 score (0.95), along with the lowest cross-entropy loss (0.27) and the highest accuracy (92%). ViT also recorded the highest area under the curve (AUC) (98%), outperforming the other models with statistically significant differences (p < 0.05), confirming its enhanced classification capability. The gradient-weighted class activation mapping (Grad-CAM) analysis on the ViT model revealed the key areas of the images that the model focused on during predictions. DL algorithms can automatically classify FI using readily accessible panoramic images. These findings demonstrate that ViT outperforms the tested traditional models, highlighting the potential of transformer-based approaches to significantly advance image classification. This approach is also expected to reduce both the radiation dose and the financial burden on patients while simultaneously improving diagnostic precision.

Periodontitis is a hypoxic infectious disease. When periodontal tissues are affected by disease and the microenvironment becomes inflamed, the release of local inflammatory factors and increased tissue metabolism lead to an imbalance between oxygen supply and demand. This inflammatory environment disrupts blood microcirculation, causing the local periodontal tissue to enter a relatively ischemic and hypoxic state. Deep periodontal pockets and periodontal pathogenic bacteria further reduce the oxygen tension in periodontal tissues, exacerbating the progression of periodontitis. Current treatment strategies for improving the inflammatory microenvironment include mechanical therapy and systemic or localized antibiotic administration. However, these existing methods fail to effectively restore the microbiota balance, ensure sustained drug release, or maintain drug presence at the lesion site. Hydrogels, due to their low cytotoxicity, excellent water retention properties, and ability to control drug release, serve as an effective drug delivery pathway that supplies oxygen to inflammatory sites. This article reviews the mechanisms and recent advancements in using hydrogel-based therapies to improve the hypoxic microenvironment of periodontal tissues, thereby promoting periodontal regeneration, and provides clinical insights for future applications in periodontal regeneration.

Periodontitis is a chronic inflammatory disorder characterized by a sustained inflammatory stimulus that creates an oxidative stress microenvironment within periodontal tissues. Under such conditions, elevated levels of reactive oxygen species (ROS) disrupt the structural and functional integrity of periodontal ligament stem cells (PDLSCs), inhibit osteogenic differentiation, and impair the regeneration of periodontal bone defects. Herein, a ROS-responsive degradable hydrogel loaded with growth differentiation factor 5 (GDF5) was developed to target this pathological microenvironment. By incorporating a thioketal (TK) linker that can be cleaved by ROS, the hydrogel reacts with high concentrations of ROS, improving the oxidative stress environment. As the reaction occurs, the hydrogel is degraded, and during this process, GDF5 is successfully released into the microenvironment, then exerts a sustained osteogenic-promoting effect. This study does not simply expose GDF5 to a harmful environment. Instead, our hydrogel first rapidly scavenges high levels of ROS upon sensing them, creating a redox-balanced microenvironment for the cells; subsequently, it releases GDF5 through an ROS-triggered mechanism. This sequential logic of “clearing the environment first, then treating” is designed to ensure that the released GDF5 can function in an optimized and functional microenvironment, thereby maximizing its protective effects and promoting its osteogenic activity.