Evaluation of Toothbrush Quality Using AI-based Virtual Tooth Plaque Assessment

As oral health issues are becoming increasingly important, how to measure tooth stain and evaluate the toothbrush cleaning effect has become an important research topic. In this paper, AI-based virtual tartar assessment method is proposed. YOLOv10 target detection integrated with Otsu threshold segmentation is proposed for automatic measurement of tooth stain. First, the YOLOv10 target detection algorithm is used to automatically locate and extract tooth regions from the input image to ensure accurate focusing on the relevant regions. Then Otsu threshold segmentation method are used to segment the tooth surface and extract stains. Finally, the tooth cleaning effect is estimated by calculating the area variation of the stained regions before and after cleaning. Experiments conducted on the collected real cases show that the method has high accuracy and robustness in tooth stain detection and toothbrush cleaning ability evaluation. This study can provide technical support for evaluating the effectiveness of dental cleaning products and personalised oral care programmes.