Temporomandibular Joint Disorders Multi-Class Classification Using Deep Learning.

Temporomandibular joint (TMJ) disorders have been misinterpreted by various normal TMJ features leading to treatment failure. This study assessed deep learning algorithms, DenseNet-121 and InceptionV3, for multi-class classification of TMJ normal variations and disorders in 1,710 panoramic radiographs. The overall accuracy of DenseNet-121 and InceptionV3 were 0.99 and 0.95, respectively. The AUC from 0.99 to 1.00, indicating high performance for TMJ disorders classification in panoramic radiographs.

Deep Learning for Midfacial Fracture Detection in CT Images.

This study deploys the deep learning-based object detection algorithms to detect midfacial fractures in computed tomography (CT) images. The object detection models were created using faster R-CNN and RetinaNet from 2,000 CT images. The best detection model, faster R-CNN, yielded an average precision of 0.79 and an area under the curve (AUC) of 0.80. In conclusion, faster R-CNN model has good potential for detecting midfacial fractures in CT images.

Application of a Multi-Layer Perceptron in Preoperative Screening for Orthognathic Surgery.

OBJECTIVES: Orthognathic surgery is used to treat moderate to severe occlusal discrepancies. Examinations and measurements for preoperative screening are essential procedures. A careful analysis is needed to decide whether cases require orthognathic surgery. This study developed screening software using a multi-layer perceptron to determine whether orthognathic surgery is required. METHODS: In total, 538 digital lateral cephalometric radiographs were retrospectively collected from a hospital data system. The input data consisted of seven cephalometric variables. All cephalograms were analyzed by the Detectron2 detection and segmentation algorithms. A keypoint region-based convolutional neural network (R-CNN) was used for object detection, and an artificial neural network (ANN) was used for classification. This novel neural network decision support system was created and validated using Keras software. The output data are shown as a number from 0 to 1, with cases requiring orthognathic surgery being indicated by a number approaching 1. RESULTS: The screening software demonstrated a diagnostic agreement of 96.3% with specialists regarding the requirement for orthognathic surgery. A confusion matrix showed that only 2 out of 54 cases were misdiagnosed (accuracy = 0.963, sensitivity = 1, precision = 0.93, F-value = 0.963, area under the curve = 0.96). CONCLUSIONS: Orthognathic surgery screening with a keypoint R-CNN for object detection and an ANN for classification showed 96.3% diagnostic agreement in this study.

Clinical Decision Support System for Geriatric Dental Treatment Using a Bayesian Network and a Convolutional Neural Network.

OBJECTIVES: The aim of this study was to evaluate the performance of a clinical decision support system (CDSS) for therapeutic plans in geriatric dentistry. The information that needs to be considered in a therapeutic plan includes not only the patient's oral health status obtained from an oral examination, but also other related factors such as underlying diseases, socioeconomic characteristics, and functional dependency. METHODS: A Bayesian network (BN) was used as a framework to construct a model of contributing factors and their causal relationships based on clinical knowledge and data. The faster R-CNN (regional convolutional neural network) algorithm was used to detect oral health status, which was part of the BN structure. The study was conducted using retrospective data from 400 patients receiving geriatric dental care at a university hospital between January 2020 and June 2021. RESULTS: The model showed an F1-score of 89.31%, precision of 86.69%, and recall of 82.14% for the detection of periodontally compromised teeth. A receiver operating characteristic curve analysis showed that the BN model was highly accurate for recommending therapeutic plans (area under the curve = 0.902). The model performance was compared to that of experts in geriatric dentistry, and the experts and the system strongly agreed on the recommended therapeutic plans (kappa value = 0.905). CONCLUSIONS: This research was the first phase of the development of a CDSS to recommend geriatric dental treatment. The proposed system, when integrated into the clinical workflow, is expected to provide general practitioners with expert-level decision support in geriatric dental care.

Comparative Dissemination of Aerosol and Splatter Using Suction Device during Ultrasonic Scaling: A Pilot Study.

Objective: This study compared the aerosol and splatter diameter and count numbers produced by a dental mouth prop with a suction holder device and a saliva ejector during ultrasonic scaling in a clinical setting. Methodology: Fluorescein dye was placed in the dental equipment irrigation reservoirs with a mannequin, and an ultrasonic scaler was employed. The procedures were performed three times per device. The upper and bottom board papers were placed on the laboratory platform. All processes used an ultrasonic scaler to generate aerosol and splatter. A dental mouth prop with a suction holder and a saliva ejector were also tested. Photographic analysis was used to examine the fluorescein samples, followed by image processing in Python and assessment of the diameter and count number. For device comparison, statistics were used with an independent t-test. Result: When using the dental mouth prop with a suction holder, the scaler produced aerosol particles that were maintained on the upper board paper (mean ± SD: 1080 ± 662 µm) compared to on the bottom board paper (1230 ± 1020 µm). When the saliva ejector was used, it was found that the diameter of the aerosol on the upper board paper was 900 ± 580 µm, and the diameter on the bottom board paper was 1000 ± 756 µm. Conclusion: There was a significant difference in the aerosol and splatter particle diameter and count number between the dental mouth prop with a suction holder and saliva ejector (p < 0.05). Furthermore, the results revealed that there was a statistically significant difference between the two groups on the upper and bottom board papers.

Effects of Nanocrystal Cellulose from Bamboo on the Flexural Strength of Acrylic Resin: In Vitro.

The purpose of this study is to evaluate the effects of nanocrystal cellulose (NCC) from bamboo on the flexural strength of heat-cured acrylic resin. A total of 35 specimens (3.3 mm × 10 mm × 64 mm) were prepared and the specimens were divided into five groups of seven specimens each. Group 1 used conventional acrylic resin that was prepared based on the instructions of the manufacturer (0%). The filled NCC from bamboo fiber in four concentrations (0.25, 0.5, 1, and 2% w/w) was used in the four-reinforcing resin workpiece groups. The specimens were loaded until failure occurred on a three-point bending test machine. One-way analysis of variance and Dunnett's multiple comparison test at a 95% confidence level were used to determine the statistical differences in the flexural strength among the five groups. The results found that the average flexural strength of five specimen groups (0, 0.25, 0.5, 1, and 2% w/w) were 60.11 ± 2.4, 60.75 ± 2.18, 66.50 ± 5.08, 56.04 ± 0.31, and 48.05 ± 2.61 MPa, respectively. The flexural strength of 0.5 mg% w/w NCC-reinforced acrylic resin was significantly higher than the control group (p < 0.01). The reinforced NCC from bamboo fiber to acrylic resin improved the flexural strength properties.

Automatic detection of periodontal compromised teeth in digital panoramic radiographs using faster regional convolutional neural networks.

PURPOSE: Periodontal disease causes tooth loss and is associated with cardiovascular diseases, diabetes, and rheumatoid arthritis. The present study proposes using a deep learning-based object detection method to identify periodontally compromised teeth on digital panoramic radiographs. A faster regional convolutional neural network (faster R-CNN) which is a state-of-the-art deep detection network, was adapted from the natural image domain using a small annotated clinical data- set. MATERIALS AND METHODS: In total, 100 digital panoramic radiographs of periodontally compromised patients were retrospectively collected from our hospital's information system and augmented. The periodontally compromised teeth found in each image were annotated by experts in periodontology to obtain the ground truth. The Keras library, which is written in Python, was used to train and test the model on a single NVidia 1080Ti GPU. The faster R-CNN model used a pretrained ResNet architecture. RESULTS: The average precision rate of 0.81 demonstrated that there was a significant region of overlap between the predicted regions and the ground truth. The average recall rate of 0.80 showed that the periodontally compromised teeth regions generated by the detection method excluded healthiest teeth areas. In addition, the model achieved a sensitivity of 0.84, a specificity of 0.88 and an F-measure of 0.81. CONCLUSION: The faster R-CNN trained on a limited amount of labeled imaging data performed satisfactorily in detecting periodontally compromised teeth. The application of a faster R-CNN to assist in the detection of periodontally compromised teeth may reduce diagnostic effort by saving assessment time and allowing automated screening documentation.

Vibrotactile -Feedback Device for Postural Balance Among Malocclusion Patients.

Multiple studies have suggested that some associations exist between occlusal factors and postural alterations. OBJECTIVES: This study aimed to evaluate the effectiveness of a vibrotactile posture trainer device, comprised a wearable device containing an accelerometer sensor to measure the angle of the neck flexion (input) and provided real-time vibrotactile biofeedback (output) for postural balance among patients with malocclusion. METHODS: Twenty-four subjects were divided in 3 groups based on occlusion and using Angle's classification. Each group consisted of 8 patients for class I, II and III malocclusion. The Posture Trainer System was used for feedback concerning neck flexion angles when higher than 15 degrees. A 4-week training program to adjust posture balance in 2 axes (flexion-extension, lateral-flexion) was applied in activities for daily living. The assessments in this study were comprised of neck flexion angles from the Posture Trainer System and the center of pressure ([Formula: see text]) using a force plate. The effects of a vibrotactile posture trainer (baseline vs. post-training test) were evaluated using the paired t-test and were assumed to be significant at p < 0.05 (two-side). All analyses were conducted using the Statistical Package for Social Sciences, Version 21.0 (SPSS, Chicago, IL, USA). RESULTS: Neck flexion angles and center of pressure significantly decreased post-training by the Posture Trainer System among patients with class II malocclusion. No changes in the above parameters post-training were found in class I and class III. CONCLUSION: The results demonstrated that patients with class II malocclusion training by the Posture Trainer System lowered neck flexion angles and COP compared with pre-training. Clinical Impact: Feedback by the Posture Trainer System can help improve the postural balance in class II malocclusion.

Improving Postural Balance in Dentoalveolar Malocclusion Patients Using a Vibrotactile Posture Trainer Device.

The biomechanical relationship between the body and teeth suggested that posture imbalance can lead to dentoalveolar malocclusion. A randomized crossover trial was conducted to compare body posture measure using tilt angles of the neck and center of pressure of the malocclusion patients that received vibrotactile biofeedback from the posture trainer device with those who received no feedback. The results showed that the system is associated with quantitative improvements of the body posture in malocclusion patients.

Bayesian-Based Decision Support System for Assessing the Needs for Orthodontic Treatment.

OBJECTIVES: In this study, a clinical decision support system was developed to help general practitioners assess the need for orthodontic treatment in patients with permanent dentition. METHODS: We chose a Bayesian network (BN) as the underlying model for assessing the need for orthodontic treatment. One thousand permanent dentition patient data sets chosen from a hospital record system were prepared in which one data element represented one participant with information for all variables and their stated need for orthodontic treatment. To evaluate the system, we compared the assessment results based on the judgements of two orthodontists to those recommended by the decision support system. RESULTS: In a BN decision support model, each variable is modelled as a node, and the causal relationship between two variables may be represented as a directed arc. For each node, a conditional probability table is supplied that represents the probabilities of each value of this node, given the conditions of its parents. There was a high degree of agreement between the two orthodontists (kappa value = 0.894) in their diagnoses and their judgements regarding the need for orthodontic treatment. Also, there was a high degree of agreement between the decision support system and orthodontists A (kappa value = 1.00) and B (kappa value = 0.894). CONCLUSIONS: The study was the first testing phase in which the results generated by the proposed system were compared with those suggested by expert orthodontists. The system delivered promising results; it showed a high degree of accuracy in classifying patients into groups needing and not needing orthodontic treatment.

Clinical Decision Support Model to Predict Occlusal Force in Bruxism Patients.

OBJECTIVES: The aim of this study was to develop a decision support model for the prediction of occlusal force from the size and color of articulating paper markings in bruxism patients. METHODS: We used the information from the datasets of 30 bruxism patients in which digital measurements of the size and color of articulating paper markings (12-µm Hanel; Coltene/Whaledent GmbH, Langenau, Germany) on canine protected hard stabilization splints were measured in pixels (P) and in red (R), green (G), and blue (B) values using Adobe Photoshop software (Adobe Systems, San Jose, CA, USA). The occlusal force (F) was measured using T-Scan III (Tekscan Inc., South Boston, MA, USA). The multiple regression equation was applied to predict F from the P and RGB. Model evaluation was performed using the datasets from 10 new patients. The patient's occlusal force measured by T-Scan III was used as a 'gold standard' to compare with the occlusal force predicted by the multiple regression model. RESULTS: The results demonstrate that the correlation between the occlusal force and the pixels and RGB of the articulating paper markings was positive (F = 1.62×P + 0.07×R -0.08×G + 0.08×B + 4.74; R2 = 0.34). There was a high degree of agreement between the occlusal force of the patient measured using T-Scan III and the occlusal force predicted by the model (kappa value = 0.82). CONCLUSIONS: The results obtained demonstrate that the multiple regression model can predict the occlusal force using the digital values for the size and color of the articulating paper markings in bruxism patients.

A study on light transmittance through red protective shields modified with different window films.

OBJECTIVES/AIMS: This study aimed to improve effectiveness of red protective shields in filtering unwanted light using window films. MATERIALS AND METHODS: Red protective shields were modified by placing V-Kool (VK), Scotchtint (ST) or Hüper Optik (HP) window films on both sides. Percentage transmittance (%T) of light with a wavelength of 190-990 nm was determined using a double-beam ultraviolet (UV) and visible spectrophotometer. RESULTS: In UV light (190-390 nm) and visible light (430-590 nm) ranges, %T in all modified groups and the control was below 2.5%. An increase in %T was observed at the wavelength of 630 nm, when all the modified shields showed superior effectiveness in light filtration over the control. In the infrared spectrum (700-990 nm), %T in the control was constantly high, ranging from 86 to 91%, compared to %T of 2-38% in all the modified groups, with the application of VK on both sides being the most effective group, followed by a combination of VK and HP. CONCLUSION: This study has introduced an economical and simple, yet highly effective, means of enhancing the efficiency of a red plastic protection shield in filtering unwanted infrared light, thereby additionally providing protection for dental personnel from potential ocular damages.

Decision support system for predicting color change after tooth whitening.

Tooth whitening is becoming increasingly popular among patients and dentists since it is a relatively noninvasive approach. However, the degree of color change after tooth whitening is known to vary substantially between studies. The present study aims to develop a clinical decision support system for predicting color change after in-office tooth whitening. We used the information from patients' data sets, and applied the multiple regression equation of CIELAB color coordinates including L*, a*, and b* of the original tooth color and the color difference (ΔE) that expresses the color change after tooth whitening. To evaluate the system performance, the patient's post-treatment color was used as "gold standard" to compare with the post-treatment color predicted by the system. There was a high degree of agreement between the patient's post-treatment color and the post-treatment color predicted by the system (kappa value=0.894). The results obtained have demonstrated that the decision support system is possible to predict the color change obtained using an in-office whitening system using colorimetric values.

The Improvement of Dental Posture Using Personalized Biofeedback.

BACKGROUND: Dentists are subject to staying in static or awkward postures for long periods due to their highly concentrated work. OBJECTIVES: This study describes a real-time personalized biofeedback system developed for dental posture training with the use of vibrotactile biofeedback. METHODS: The real-time personalized biofeedback system was an integrated solution that comprised of two components: 1) a wearable device that contained an accelerometer sensor for measuring the tilt angle of the body (input) and provided real-time vibrotactile biofeedback (output); and 2) software for data capturing, processing, and personalized biofeedback generation. The implementation of real-time personalized vibrotactile feedback was computed using Hidden Markov Models (HMMs). For the test case, we calculated the probability and log-likelihood of the test movements under the Work related Musculoskeletal Disorders (WMSD) and non-WMSD HMMs. The vibrotactile biofeedback was provided to the user via a wearable device for a WMSD-predicted case. In the system evaluation, a randomized crossover trial was conducted to compare dental posture measure using tilt angles of the upper back and muscle activities of those dental students that received vibrotactile biofeedback from the system with the control group against the dental students who received no feedback. RESULTS: The participants who received feedback from the system had a lower tilt angle at 10th, 50th, and 90th percentiles of Backx and Backy, as well as muscular load, which were statistically different (p<0.05) from those who received no feedback from the system. CONCLUSIONS: The results presented here demonstrate that a personalized biofeedback system for posture training in dental students is feasible and associated with quantitative improvements of the dental posture.

A system for predicting musculoskeletal disorders among dental students.

OBJECTIVE: This study aimed to develop a system for predicting work-related musculoskeletal disorders (WMSD) among dental students. MATERIALS AND METHODS: The system comprised 2 accelerometer sensors to register neck and upper back postures and movements, and software developed to collect and process the data. Hidden Markov models (HMMs) were used to predict the likelihood of WMSD in dental students by comparing their neck and upper back movement patterns with WMSD and non-WMSD HMMs learned from previous data. To evaluate the performance of the system, 16 participants were randomly assigned into a 2 × 2 crossover trial scheduled for each sequence of working: receiving feedback or no-feedback from the system. The primary outcome measure was the extension of the neck and upper back, before (pre-test) and after (posttest) receiving feedback or no-feedback from the system. The secondary outcome measure was the log likelihood of classifying the movements as WMSD. RESULTS AND DISCUSSION: The results showed that in the group that received feedback, the extension of the neck in the y axis and of the upper back in the y axis decreased significantly (t test, p < .05) on the post-test. CONCLUSION: The system for predicting and preventing WMSD aids the correction of the extension of the neck and upper back in the y axis.

A system for predicting and preventing work-related musculoskeletal disorders among dentists.

Work-related musculoskeletal disorders (WMSDs) have become increasingly common among dentists and initiate a series of events that could result in a career ending. This study aims to construct a system for predicting and preventing WMSD among dentists. We used Bayesian network (BN) that describes the mutual relationships among multiple variables contributing to WMSDs. The data-sets were prepared from direct measurements of dentist's movements and a questionnaire survey. We applied BN learning algorithms to the training data-sets to develop WMSD prediction model using 10-fold cross-validation. To evaluate the system performance, 16 dentists were randomly assigned into a 2 × 2 crossover trial scheduled to each of two sequences of dental working: receiving feedback or no feedback including the probability of WMSD and related risk factors from the system. The group that received feedback decreased significantly (t-test, p < 0.05) the extensions of neck and upper back in the y-axis as well as the WMSD probability on the post-test. In conclusion, the system for predicting and preventing WMSD aids the correction of neck and upper back extensions and reduction in WMSD probability, which may potentially contribute to reduce the risk of WMSD among dentists.