Objectives: Deep learning methods have achieved impressive diagnostic performance in the field of radiology. The current study aimed to use deep learning methods to detect caries lesions, classify different radiographic extensions on panoramic films, and compare the classification results with those of expert dentists. Methods: A total of 1160 dental panoramic films were evaluated by three expert dentists. All caries lesions in the films were marked with circles, whose combination was defined as the reference dataset. A training and validation dataset (1071) and a test dataset (89) were then established from the reference dataset. A convolutional neural network, called nnU-Net, was applied to detect caries lesions, and DenseNet121 was applied to classify the lesions according to their depths (dentin lesions in the outer, middle, or inner third D1/2/3 of dentin). The performance of the test dataset in the trained nnU-Net and DenseNet121 models was compared with the results of six expert dentists in terms of the intersection over union (IoU), Dice coefficient, accuracy, precision, recall, negative predictive value (NPV), and F1-score metrics. Results: nnU-Net yielded caries lesion segmentation IoU and Dice coefficient values of 0.785 and 0.663, respectively, and the accuracy and recall rate of nnU-Net were 0.986 and 0.821, respectively. The results of the expert dentists and the neural network were shown to be no different in terms of accuracy, precision, recall, NPV, and F1-score. For caries depth classification, DenseNet121 showed an overall accuracy of 0.957 for D1 lesions, 0.832 for D2 lesions, and 0.863 for D3 lesions. The recall results of the D1/D2/D3 lesions were 0.765, 0.652, and 0.918, respectively. All metric values, including accuracy, precision, recall, NPV, and F1-score values, were proven to be no different from those of the experienced dentists. Conclusion: In detecting and classifying caries lesions on dental panoramic radiographs, the performance of deep learning methods was similar to that of expert dentists. The impact of applying these well-trained neural networks for disease diagnosis and treatment decision making should be explored.

Background: Radiographic periodontal bone loss is one of the most important basis for periodontitis staging, with problems such as limited accuracy, inconsistency, and low efficiency in imaging diagnosis. Deep learning network may be a solution to improve the accuracy and efficiency of periodontitis imaging staging diagnosis. This study aims to establish a comprehensive and accurate radiological staging model of periodontal alveolar bone loss based on panoramic images. Methods: A total of 640 panoramic images were included, and 3 experienced periodontal physicians marked the key points needed to calculate the degree of periodontal alveolar bone loss and the specific location and shape of the alveolar bone loss. A two-stage deep learning architecture based on UNet and YOLO-v4 was proposed to localize the tooth and key points, so that the percentage of periodontal alveolar bone loss was accurately calculated and periodontitis was staged. The ability of the model to recognize these features was evaluated and compared with that of general dental practitioners. Results: The overall classification accuracy of the model was 0.77, and the performance of the model varied for different tooth positions and categories; model classification was generally more accurate than that of general practitioners. Conclusions: It is feasible to establish deep learning model for assessment and staging radiographic periodontal alveolar bone loss using two-stage architecture based on UNet and YOLO-v4.

This study aimed to develop a novel detection model for automatically assessing the real contact relationship between mandibular third molars (MM3s) and the inferior alveolar nerve (IAN) based on panoramic radiographs processed with deep learning networks, minimizing pseudo-contact interference and reducing the frequency of cone beam computed tomography (CBCT) use. A deep-learning network approach based on YOLOv4, named as MM3-IANnet, was applied to oral panoramic radiographs for the first time. The relationship between MM3s and the IAN in CBCT was considered the real contact relationship. Accuracy metrics were calculated to evaluate and compare the performance of the MM3–IANnet, dentists and a cooperative approach with dentists and the MM3–IANnet. Our results showed that in comparison with detection by dentists (AP = 76.45%) or the MM3–IANnet (AP = 83.02%), the cooperative dentist–MM3–IANnet approach yielded the highest average precision (AP = 88.06%). In conclusion, the MM3-IANnet detection model is an encouraging artificial intelligence approach that might assist dentists in detecting the real contact relationship between MM3s and IANs based on panoramic radiographs.

Dental caries is one of the most common infectious diseases affecting 6–8-year-old children, especially their first permanent molars (FPMs). This study explored the prevalence of dental caries on FPMs by analyzing the oral health status of 1,423,720 children aged 6–8 years in Zhejiang Province, China. The data were extracted from the dental electronic records of the schoolchildren attending the Oral Health Promotion Project (OHPP), conducted during 2013–2017 in Zhejiang Province. Multiple logistic regression models were used to determine the factors affecting dental caries. Boys and girls accounted for 53.2% and 46.8% of the subjects, respectively. From 2013 to 2017, the prevalence of dental caries on FPMs increased: 2013: 20.4%; 2014: 25.3%; 2015: 24.5%; 2016: 27.0%; and 2017: 29.0%, despite the OHPP conducted. Based on multiple logistic regression model, girls had a significantly higher risk of FPM caries compared to boys (OR = 1.38, 95% CI: 1.37–1.39, p < 0.0001); compared with the caries rates in urban areas, the caries risk was significantly higher in rural areas (OR = 1.15, 95% CI: 1.14–1.16, p < 0.0001). In terms of geographic location in Zhejiang Province, the odds ratios of the caries risk of the east, south, west, and north were 1.35 (1.33–1.36), 1.3 (1.28–1.31), 0.81 (0.8–0.83), and 0.82 (0.81–0.84), respectively (p < 0.0001), by considering the central region as a reference. The caries prevalence of FPMs was high, with an increasing tendency and gender, social, cultural, and environmental factors affecting the caries prevalence.

Dental caries in preschool children is prevalent worldwide, but data regarding its magnitude and associated factors were not available for preschool children in Zhejiang Province, China. This study examines the dental caries situation and its associated factors in Zhejiang Province. A total of 1591 children aged 3–5 years and their parents or caregivers were enrolled in this study. The condition of their teeth was assessed by three dental technicians qualified to WHO 2013 criteria. A structured questionnaire was completed by the children’s parents or caregivers. A logistic regression analysis was used to analyze the risk factors that may be associated with dental caries occurring among preschool children. Caries prevalence (dmft> 0) of 3–5 year old children in Zhejiang Province was 70.4%. The mean decayed, missing and filled teeth (dmft) scores of the 3, 4 or 5 year old children surveyed were 2.96 ± 4.07, 4.42 ± 4.66, and 5.75 ± 5.19 respectively. The negative binomial regression model found that higher dental caries prevalence was found in children as age increased, with lower body mass index (BMI), with longer breastfeeding duration and with fewer hours of sleep. The dental caries prevalence and dmft score of 3–5-year-old children in Zhejiang Province was high, and it was associated with age, BMI, breastfeeding duration and hours slept.