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.
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.
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.
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.
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.
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.
Rapid advances of sensing and cloud technologies transform the manufacturing system into a data-rich environment and make production scheduling increasingly complex. Traditional offline scheduling ...methods are limited in the ability to handle low-volume-high-mix workorders with diverse design specifications. Simulation-based methods show the promise for distributed scheduling of manufacturing jobs but are mostly implemented with historical data and empirical rules in a static manner. Recently, artificial intelligence (AI) algorithms fuel increasing interests to solve dynamic scheduling problems in the manufacturing setting. However, it's difficult to utilize high-dimensional data for production scheduling while considering multiple practical objectives for smart manufacturing (e.g., minimize the makespan, reduce production costs, balance workloads). Therefore, this paper presents a new AI scheduler with composite reward functions for data-driven dynamic scheduling of manufacturing jobs under uncertainty in a smart factory. Internet-enabled sensor networks are deployed in the smart factory to track real-time statuses of workorders, machines, and material handling systems. A novel manufacturing value network is developed to take high-dimensional data as the input and then learn the state-action values for real-time decision making. Based on reinforcement learning (RL), composite rewards help the AI scheduler learn efficiently to achieve multiple objectives for production scheduling in real time. The proposed methodology is evaluated and validated with experimental studies in a smart manufacturing setting. Experimental results show that the new AI scheduler not only improves the multi-objective performance metrics in the production scheduling problem but also effectively copes with unexpected events (e.g., urgent workorders, machine failures) in manufacturing systems.
Along with the number and the functional complexity of machines increase in the intelligent manufacturing system, the probability of faults will increase, which may lead to huge economic losses. ...Traditional passive or regular maintenance methods of solving the faults have the problems of low efficiency and huge resource consumption. Besides, traditional maintenance methods mostly contain single model, so all the prognostics and maintenance tasks of the intelligent manufacturing system can hardly be addressed at the same time. Therefore, this paper proposes a novel predictive maintenance (PDM) method based on the improved deep adversarial learning (LSTM-GAN). The long-short-term memory (LSTM) network can solve the disadvantage of vanishing gradients and the mode collapse from the generative adversarial network (GAN). The method can not only avoid the mode collapse of GAN but also realize the self-detection of abnormal data. Meanwhile, the predictive maintenance model includes two prediction models and a maintenance decision model. The prediction models can predict the state of the machine and the fault of the machine in advance. Then the maintenance decision model will arrange maintenance personnel and offer a plan of maintenance. Finally, a case study about predictive maintenance using LSTM-GAN in the intelligent manufacturing system is presented. The fault prediction accuracy of LTSM-GAN is as high as 99.68%. With the comparison between LSTM-GAN and other traditional methods, LSTM-GAN shows priority both in accuracy and efficiency. Moreover, the proposed PDM can reduce maintenance costs and downtime so that the life of machines in the intelligent manufacturing system will extend.
The pore structure and its influence on physical properties and oil saturation of the Triassic Chang 7 sandstones, Ordos Basin were discussed using thin sections, physical properties, oil saturation ...and mercury intrusion data. The results show that the tight sandstone has a binary pore structure: when the pore throat radius is larger than the peak radius, the pore radius is significantly larger than throat size, the pore structure is similar to the bead-string model with no fractal feature, and the pore throat volume is determined by the pore volume. When the pore throat radius is smaller than the peak radius, the pore structure is close to the capillary model and shows fractal features, the pore size is close to the throat size, and the pore throat volume is determined by the throat radius. The development of pore throats larger than the peak radius provides most of the oil storage space and is the major controlling factor for the porosity and permeability variation of tight sandstone. The pore throat smaller than the peak radius (including throats with no mercury invaded) contributes major reservoir space, it shows limited variation and has little effect on the change of physical properties which is lack of correlation with oil saturation. The pore throat larger than the peak radius is mainly composed of secondary and intergranular pores. Therefore genesis and main controlling factors of large pores such as intergranular and dissolved pores should be emphasized when predicting the tight sandstones quality.
Objectives
Periodontitis is a local inflammatory disease of high prevalence worldwide. Increasing evidence has shown its association with cardiovascular diseases. While high-density lipoprotein is an ...important protective factor in preventing cardiovascular diseases, this study aims to examine whether high-density lipoprotein cholesterol (HDL-C) level is associated with different status of periodontitis.
Materials and methods
A total of 874 Chinese retirees (≥ 60 years of age) with different statuses of periodontitis were enrolled. Periodontal clinical data were collected to define periodontal disease severity (no, mild-moderate, severe). Peripheral blood was collected for serum lipid profile analysis. Linear and logistic regression analysis with adjustment for potential confounders (gender, age, BMI, alcohol intake, exercise frequency, smoking habits) were used to determine the association of periodontitis with HDL-C.
Results
After adjustments for confounders, linear regression analyses revealed a significant relationship between the decreased HDL-C and periodontitis severity (
p
< 0.05). Although the multivariable-adjusted ORs of decreased HDL-C were not statistically significant, logistic regression analyses showed Chinese elderly with severe periodontitis had higher odds of exhibiting clinically abnormal HDL-C levels than those without periodontitis.
Conclusions
The elderly population with periodontitis showed HDL-C levels significantly lower than those without periodontitis. The severity of periodontitis was positively correlated with serum HDL-C levels.
Clinical relevance
Periodontitis reduces HDL-C level in the elderly population, indicating that oral health should be paid attention to in the prevention and treatment of dyslipidemia.
The Qaidam Basin is a Cenozoic continental basin formed by the subduction and collision between the Indian plate and the Eurasian plate. It is the only large oil- and gas-bearing basin in China on ...the Qinghai–Tibet Plateau. The Qaidam Basin has recorded the uplift of the plateau with its complete Cenozoic sequences. Therefore, studying the structural characteristics of the Qaidam Basin helps us to understand the uplift of the Qinghai–Tibet Plateau. Studies have shown that the structural activities in the Qaidam Basin were episodic, transformable, and inconsistent, which reflected the characteristics of the uplift of the Qinghai–Tibet Plateau. In general, the structural activities of the Qaidam Basin are divided into three phases, which are characterized by the shifting of structural activities from the south to the north, the west to the east, and from the margin to the hinterland of the basin, respectively. The intensity of the early activity was greater than that of the early basin in both time and space. In conclusion, the uplift of the Qinghai–Tibet Plateau controls the structural and sedimentary characteristics of the basin and ultimately, the hydrocarbon accumulation and distribution of the basin.
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.
Periodontal diseases is considered the most important global oral health burden according to the world health organization (WHO) (Oral health. ...https://www.who.int/news-room/fact-sheets/detail/oral-health#Overviewth (who.int). Accessed 21 Sep 2023). It is a common local inflammatory disease associated with hypertension, this study aims to explore the relationship between periodontitis and uncontrolled hypertension and whether inflammation indication such as white blood cell (WBC) count or neutrophil count is a mediator of this relationship.
One thousand four hundred eighty-eight elders attending annual physical and oral examinations in Zhejiang province were included in this study. The staging of Periodontitis was classified as none, mild-moderate and severe. Participants are categorized into two groups based on blood pressure: hypertensive( positive high blood pressure( HBP) history or underwent HBP medication or blood pressure( BP) ≥ 140/90 mmHg) and uncontrolled hypertensive (systolic blood pressure( SBP) ≥ 140 mmHg or distolic blood pressure( DBP) ≥ 90 mmHg). Peripheral blood samples were collected, information on hypertension history and potential confounders (age, sex, smoking, alcohol consumption, exercise frequency, diabetes) was collected in questionnaires. The correlation between periodontitis and hypertension was investigated using logistics regression analyses, mediation analysis was assessed for the effect of inflammation on hypertension.
The study population includes 1,488 participants aged 55-90 years. Odds of uncontrolled hypertension increased significantly along with periodontitis in the regression models both in unadjusted model (odds ratio( OR): 1.407, 95% confidence intervals( CI): 1.037 ~ 1.910) and fully adjusted model (OR: 1.950, 95% CI: 1.127 ~ 3.373). Mediation analysis confirmed that WBC and neutrophic count function as a full mediator of the association between periodontitis and uncontrolled hypertension either in the unadjusted or the adjusted model.
In a study of urban elderly population in southeast China, periodontitis is found to be significantly associated with uncontrolled hypertension, such relation is mediated by WBC and neutrophil count. Periodontitis can increase the difficulty of controlling hypertension. Promotion of periodontal health strategies in the dental setting could help reduce the burden of hypertension and its complications.