Effect of Push-Pull HEPA Filters on Air Age in a Dental Treatment Room.

Air quality was evaluated by visualizing with CFD (Computational Fluid Dynamics) where air tends to stagnate in the dental practice space when natural ventilation and HEPA filters are used together. The results showed that natural ventilation by opening and closing windows and doors alone was not sufficient.

Panoramic Radiograph Generation and Image Reconstruction from Latent Vectors Using a Generative Adversarial Network.

In this study, StyleGAN2 was trained with panoramic radiographs, and original images were projected into the latent space of StyleGAN2. The resulting latent vectors were input into StyleGAN2, and corresponding images were generated to reconstruct the original images. The original and reconstructed images were evaluated by pediatric dentists and found to be similar. Our results suggest that StyleGAN2 could be applied to the anonymization and data compression of medical images.

Automatic dental age calculation from panoramic radiographs using deep learning: a two-stage approach with object detection and image classification.

BACKGROUND: Dental age is crucial for treatment planning in pediatric and orthodontic dentistry. Dental age calculation methods can be categorized into morphological, biochemical, and radiological methods. Radiological methods are commonly used because they are non-invasive and reproducible. When radiographs are available, dental age can be calculated by evaluating the developmental stage of permanent teeth and converting it into an estimated age using a table, or by measuring the length between some landmarks such as the tooth, root, or pulp, and substituting them into regression formulas. However, these methods heavily depend on manual time-consuming processes. In this study, we proposed a novel and completely automatic dental age calculation method using panoramic radiographs and deep learning techniques. METHODS: Overall, 8,023 panoramic radiographs were used as training data for Scaled-YOLOv4 to detect dental germs and mean average precision were evaluated. In total, 18,485 single-root and 16,313 multi-root dental germ images were used as training data for EfficientNetV2 M to classify the developmental stages of detected dental germs and Top-3 accuracy was evaluated since the adjacent stages of the dental germ looks similar and the many variations of the morphological structure can be observed between developmental stages. Scaled-YOLOv4 and EfficientNetV2 M were trained using cross-validation. We evaluated a single selection, a weighted average, and an expected value to convert the probability of developmental stage classification to dental age. One hundred and fifty-seven panoramic radiographs were used to compare automatic and manual human experts' dental age calculations. RESULTS: Dental germ detection was achieved with a mean average precision of 98.26% and dental germ classifiers for single and multi-root were achieved with a Top-3 accuracy of 98.46% and 98.36%, respectively. The mean absolute errors between the automatic and manual dental age calculations using single selection, weighted average, and expected value were 0.274, 0.261, and 0.396, respectively. The weighted average was better than the other methods and was accurate by less than one developmental stage error. CONCLUSION: Our study demonstrates the feasibility of automatic dental age calculation using panoramic radiographs and a two-stage deep learning approach with a clinically acceptable level of accuracy.

Oral squamous cell carcinoma diagnosis in digitized histological images using convolutional neural network.

Background/purpose: Diagnostic methods of oral squamous cell carcinoma (SCC) using artificial intelligence (AI) and digital-histopathologic images have been developed. However, previous AI training methods have focused on the cellular atypia given by the training of high-magnification images, and little attention has been paid to structural atypia provided by low-power wide fields. Since oral SCC has histopathologic types with bland cytology, both cellular atypia and structural atypia must be considered as histopathologic features. This study aimed to investigate AI ability to judge oral SCC in a novel training method considering cellular and structural atypia and their suitability. Materials and methods: We examined digitized histological whole-slide images from 90 randomly selected patients with tongue SCC who attended a dental hospital. Image patches of 1000 × 1000 pixels were cut from whole-slide images at 0.3125-, 1.25-, 5-, and 20-fold magnification, and 90,059 image patches were used for training and evaluation. These image patches were resized into 224 × 224, 384 × 384, 512 × 512, and 768 × 768 pixels, and the differences in input size were analyzed. EfficientNet B0 was utilized as the convolutional neural network model. Gradient-weighted class activation mapping (Grad-CAM) was used to elucidate its validity. Results: The proposed method achieved a peak accuracy of 99.65% with an input size of 512 × 512 pixels. Grad-CAM suggested that AI focused on both cellular and structural atypia of SCC, and tended to focus on the region surrounding the basal layer. Conclusion: Training AI regarding both cellular and structural atypia using various magnification images simultaneously may be suitable for the diagnosis of oral SCC.

Estimation of dental age based on the developmental stages of permanent teeth in Japanese children and adolescents.

Assessment of children's growth and development based on general and oral developmental status and dental age is important in pediatric dentistry for appropriate diagnosis and treatment. Teeth are a useful maturation index because they are unlikely to be affected by exogenous factors such as disease. We examined the correlation between chronological and dental age of permanent teeth in Japanese children and adolescents using orthopantomography. The sample comprised 1024 orthopantomographs from individuals aged 3-18 years, which were stored in an electronic media database for 10 years (2009-2019). We classified the developmental stages of each permanent tooth were classified into 11 stages, clarified the dental age for each developmental stage, and prepared a conversion table. Using the results, we compared the sequence and rate of development of each permanent tooth. We clarified the dental age of each permanent tooth from childhood to mid-adolescence and established a method for calculating the dental age of the whole jaw that is appropriate for modern Japanese individuals. We found that girls tended to form teeth at a faster rate than boys until puberty, but boys caught up with girls after puberty, suggesting that secondary sexual characteristics are involved in the rate of tooth formation.

Intraoral image generation by progressive growing of generative adversarial network and evaluation of generated image quality by dentists.

Dentists need experience with clinical cases to practice specialized skills. However, the need to protect patient's private information limits their ability to utilize intraoral images obtained from clinical cases. In this study, since generating realistic images could make it possible to utilize intraoral images, progressive growing of generative adversarial networks are used to generate intraoral images. A total of 35,254 intraoral images were used as training data with resolutions of 128 × 128, 256 × 256, 512 × 512, and 1024 × 1024. The results of the training datasets with and without data augmentation were compared. The Sliced Wasserstein Distance was calculated to evaluate the generated images. Next, 50 real images and 50 generated images for each resolution were randomly selected and shuffled. 12 pediatric dentists were asked to observe these images and assess whether they were real or generated. The d prime of the 1024 × 1024 images was significantly higher than that of the other resolutions. In conclusion, generated intraoral images with resolutions of 512 × 512 or lower were so realistic that the dentists could not distinguish whether they were real or generated. This implies that the generated images can be used in dental education or data augmentation for deep learning, without privacy restrictions.

Dental effects of enzyme replacement therapy in case of childhood-type hypophosphatasia.

BACKGROUND: Hypophosphatasia (HPP), a skeletal disease characterized by hypomineralization of bone and teeth, is caused by an ALPL gene mutation that leads to low activity of the tissue non-specific alkaline phosphatase enzyme. Although enzyme replacement therapy (ERT) was recently introduced for affected patients, no known studies have been reported regarding its dental effects related to permanent teeth and jaw bones. In the present study, we examined the dental effects of ERT in a case of childhood-type hypophosphatasia, including panoramic radiography findings used to estimate the dental age of permanent teeth and mandibular bone density. Furthermore, the effects of that therapy on the periodontal condition of the patient were evaluated by comparing periodontal pocket depth before and after initiation. CASE PRESENTATION: An 11-year-1-month-old boy was referred to our clinic for consultation regarding oral management. Two primary incisors had spontaneously exfoliated at 1 year 8 months old and he had been diagnosed with childhood-type HPP at the age of 2 years 2 months. Obvious symptoms were localized in the dental region at the time of diagnosis, though later extended to other parts of the body such as bone pain. ERT was started at 11 years 7 months of age, after which bone pain disappeared, and motor functions and activities of daily living improved. We estimated dental age based on tooth development stage. The age gap between chronological and dental ages was expanded before treatment, and then showed a constant decrease after ERT initiation and finally disappeared. The index for mandibular bone density (mandibular cortical width / length from mesial buccal cusp to apex of first molar) was increased after ERT initiation. Furthermore, the periodontal condition for all teeth except those exfoliated was stable after starting therapy. CONCLUSIONS: ERT resulted in improved tooth and mandibular bone mineralization, with notably good effects on teeth under formation. Acceleration of mineralization of roots associated with erupting teeth leads to stabilization of the periodontal condition. We concluded that ERT contributed to the improved dental condition seen in this patient.

Japanese nationwide survey of hypophosphatasia reveals prominent differences in genetic and dental findings between odonto and non-odonto types.

Hypophosphatasia (HPP) is a rare and intractable metabolic bone disease caused by mutations in the ALPL gene. Here, we undertook a nationwide survey of HPP in Japan, specifically regarding the prominent genetic and dental manifestations of odonto (n = 16 cases) and other (termed "non-odonto") (n = 36 cases) types. Mean serum alkaline phosphatase (ALP) values in odonto-type patients were significantly greater than those of non-odonto-type patients (P<0.05). Autosomal dominant and autosomal recessive inheritance patterns were detected, respectively, in 89% of odonto-type and 96% of non-odonto-type patients. The ALPL "c.1559delT" mutation, associated with extremely low ALP activity, was found in approximately 70% of cases. Regarding dental manifestations, all patients classified as odonto-type showed early exfoliation of the primary teeth significantly more frequently than patients classified as non-odonto-type (100% vs. 56%; P<0.05). Tooth hypomineralisation was detected in 42% of non-odonto-type patients, but not in any odonto-type patients (0%; P<0.05). Collectively, these results suggest that genetic and dental manifestations of patients with odonto-type and non-odonto-type HPP are significantly different, and these differences should be considered during clinical treatment of patients with HPP.

Current knowledge among Japanese experienced general dentists regarding prevention of infective endocarditis.

Infective endocarditis (IE), a life-threatening condition predominantly occurring in patients with underlying heart disease, is mainly caused by bacteremia induced by invasive dental treatment. However, the amount of related information shared between cardiologists and dentists appears to be inadequate. In the present study, a survey regarding prevention of IE, composed of 13 major questions, 2 of which also allowed free comments, was sent to approximately 3000 dentists belonging to a prefectural dental association in Japan. Of the 13.6% who returned the forms, more than 80% were general dentists with more than 20 years of experience. Approximately, 55% of the responders reported that they had opportunities to prescribe antibiotics prior to performing treatments with risk of IE, though noted difficulties with designation of which patients with heart disease were at risk. Most of the dentists considered that oral surgery procedures have a high risk for IE, whereas less invasive procedures were considered to be not associated with the disease. Approximately, 35% selected oral amoxicillin, with a dose of 2.0 g (20%) or 500 mg (27%) prescribed for adults, and 50 mg (10%) or 30 mg (12%) per kg of body weight for children. However, the timing of the antibiotics administration varied. The present results reveal current knowledge regarding prevention of IE among general dentists in Japan, and should be valuable for construction of a protocol to establish consensus between dentists and cardiologists.