Classification of presence of missing teeth in each quadrant using deep learning artificial intelligence on panoramic radiographs of pediatric patients.

Early tooth loss in pediatric patients can lead to various complications, making quick and accurate diagnosis essential. This study aimed to develop a novel deep learning model for classification of missing teeth on panoramic radiographs in pediatric patients and to assess the accuracy. The study included patients aged 8-16 years who visited the Pusan National University Dental Hospital and underwent panoramic radiography. A total of 806 panoramic radiographs were retrospectively analyzed to determine the presence or absence of missing teeth for each tooth number. Moreover, each panoramic radiograph was divided into four quadrants, each of a smaller size, containing both primary and permanent teeth, generating 3224 data. Quadrants with missing teeth (n = 1457) were set as the experimental group, and quadrants without missing teeth (n = 1767) were set as the control group. The data were split into training and validation sets in a 4:1 ratio, and a 5-fold cross-validation was conducted. A gradient-weighted class activation map was used to visualize the deep learning model. The average values of sensitivity, specificity, accuracy, precision, recall and F1-score of this deep learning model were 0.635, 0.814, 0.738, 0.730, 0.732 and 0.731, respectively. In the experimental group, the accuracy was the highest for missing canines and premolars, and the lowest for molars. The deep learning model exhibited a moderate to good distinguishing power with a classification performance of 0.730. This deep learning model and the newly defined small sized region of interest proved adequate for classifying the presence of missing teeth.

Morphometric Comparison and Prognostic Analysis of Permanent Maxillary Central Incisors with Eruption Disturbances-A Cross-Sectional Study.

AIMS: The aim of this study was to retrospectively compare the morphometrics of permanent maxillary central incisors with and without eruption disturbances, while simultaneously evaluating prognosis based on different factors. MATERIALS AND METHODS: Seventy patients with unilateral permanent maxillary central incisor eruption disturbances were included. Within a group of 70 subjects, measurements were taken for both normally erupted central incisors and central incisors with eruption disturbances to determine the length of the roots and the volume of the teeth. Various factors, such as angulation of impaction, and vertical height of impaction, were assessed to investigate their correlation with surgical intervention. RESULTS: Both the root length and tooth volume were significantly smaller in the eruption disturbance incisors than in the normally erupted incisors (p ≤ 0.001). Moreover, there was a statistically significant increase in surgical intervention among cases with no clear physical barrier (primary retention) (p < 0.05) or when adjacent normally erupted central incisors exhibited more than 2/3 of root development (p < 0.05). CONCLUSIONS: The results of this study numerically demonstrated the delayed tooth development of the permanent maxillary central incisors with unilateral eruption disturbances compared to appropriately erupted incisors by measuring root length and tooth volume. The absence of obstacles and the degree of root development in adjacent erupted incisors might serve as factors for clinicians to determine the necessity and timing of surgical intervention.

Strength and Surface Characteristics of 3D-Printed Resin Crowns for the Primary Molars.

Some resin polymers available for three-dimensional (3D) printing are slightly elastic, which may be advantageous when used for full crown coverage of the primary teeth. This study was performed to evaluate the mechanical properties of two types of 3D-printed resin crowns in terms of strength and surface characteristics. Polymer resins used for temporary crowns (TCs) and temporary flexible dentures (TFDs) were tested. Digitally designed crowns with different thicknesses (0.4 and 0.6 mm) were 3D-printed. Milled zirconia crowns were used as the control. The static and dynamic fracture loads of the crowns were measured. The crown surface was evaluated using scanning electron microscopy. The average strength did not differ between the types of crowns. The differences between the dynamic and static fracture loads were insignificant. In the TC group, thicker crowns showed lower strength both under static and dynamic loads. After thermomechanical loading, microcracks and dropouts of macrofillers were detected on the surface of all types of resin crowns. The deposition of abraded debris occurred more in the TFD group. The 3D-printed resin crowns were thought to endure biting forces in children. However, some limitations of the material itself should be improved for consideration as a new treatment option in pediatric dentistry.

Sensor development for multiple simultaneous classifications using genetically engineered M13 bacteriophages.

Sensors for detecting infinitesimal amounts of chemicals in air have been widely developed because they can identify the origin of chemicals. These sensing technologies are also used to determine the variety and freshness of fresh food and detect explosives, hazardous chemicals, environmental hormones, and diseases using exhaled gases. However, there is still a need to rapidly develop portable and highly sensitive sensors that respond to complex environments. Here, we show an efficient method for optimising an M13 bacteriophage-based multi-array colourimetric sensor for multiple simultaneous classifications. Apples, which are difficult to classify due to many varieties in distribution, were selected for classifying targets. M13 was adopted to fabricate a multi-array colourimetric sensor using the self-templating process since a chemical property of major coat protein p8 consisting of the M13 body can be manipulated by genetic engineering to respond to various target substances. The twenty sensor units, which consisted of different types of manipulated M13, exhibited colour changes because of the change of photonic crystal-like nanostructure when they were exposed to target substances associated with apples. The classification success rate of the optimal sensor combinations was achieved with high accuracy for the apple variety (100%), four standard fragrances (100%), and aging (84.5%) simultaneously. We expect that this optimisation technique can be used for rapid sensor development capable of multiple simultaneous classifications in various fields, such as medical diagnosis, hazardous environment monitoring, and the food industry, where sensors need to be developed in response to complex environments consisting of various targets.

Recent Trends in Lateral Flow Immunoassays with Optical Nanoparticles.

Rapid, accurate, and convenient diagnosis is essential for effective disease management. Various detection methods, such as enzyme-linked immunosorbent assay, have been extensively used, with lateral flow immunoassay (LFIA) recently emerging as a major diagnostic tool. Nanoparticles (NPs) with characteristic optical properties are used as probes for LFIA, and researchers have presented various types of optical NPs with modified optical properties. Herein, we review the literature on LFIA with optical NPs for the detection of specific targets in the context of diagnostics.

Guided Autotransplantation of Impacted Canines Using a CAD/CAM Surgical Template.

Autotransplantation is a potential treatment alternative when orthodontic traction of an impacted tooth is difficult. In this article, we describe two cases of guided autotransplantation of an impacted canine using a computer-aided designed and manufactured surgical template. The impacted canine was segmented on preoperative cone-beam computed tomography images to ensure a sufficient periodontal ligament space and placement of the donor tooth with the least pressure on it. The canine was virtually transposed using a simulation program considering the adjacent teeth. The surgical template, which was connected to the occlusal stop on adjacent teeth, was designed and 3D-printed with polymer resin. The recipient site was prepared using the surgical template, followed by immediate transplantation of the surgically extracted canine into the socket. The transplanted donor tooth was positioned in planned infra-occlusion to prevent occlusal interference. It was then splinted with the adjacent teeth for initial stabilization. During follow-up, one transplanted tooth showed pulp canal obliteration and the other had suspected pulp necrosis; endodontic treatment was performed. One year after the procedure, the periradicular condition of both teeth was favorable.

Deep focus approach for accurate bone age estimation from lateral cephalogram.

Background/purpose: Bone age is a useful indicator of children's growth and development. Recently, the rapid development of deep-learning technique has shown promising results in estimating bone age. This study aimed to devise a deep-learning approach for accurate bone-age estimation by focusing on the cervical vertebrae on lateral cephalograms of growing children using image segmentation. Materials and methods: We included 900 participants, aged 4-18 years, who underwent lateral cephalogram and hand-wrist radiograph on the same day. First, cervical vertebrae segmentation was performed from the lateral cephalogram using DeepLabv3+ architecture. Second, after extracting the region of interest from the segmented image for preprocessing, bone age was estimated through transfer learning using a regression model based on Inception-ResNet-v2 architecture. The dataset was divided into train:test sets in a ratio of 4:1; five-fold cross-validation was performed at each step. Results: The segmentation model possessed average accuracy, intersection over union, and mean boundary F1 scores of 0.956, 0.913, and 0.895, respectively, for the segmentation of cervical vertebrae from lateral cephalogram. The regression model for estimating bone age from segmented cervical vertebrae images yielded average mean absolute error and root mean squared error values of 0.300 and 0.390 years, respectively. The coefficient of determination of the proposed method for the actual and estimated bone age was 0.983. Our method visualized important regions on cervical vertebral images to make a prediction using the gradient-weighted regression activation map technique. Conclusion: Results showed that our proposed method can estimate bone age by lateral cephalogram with sufficiently high accuracy.

Deep learning-based identification of mesiodens using automatic maxillary anterior region estimation in panoramic radiography of children.

OBJECTIVES: The purpose of this study is to develop and evaluate the performance of a model that automatically sets a region of interest (ROI) and diagnoses mesiodens in panoramic radiographs of growing children using deep learning technology. METHODS: Out of 988 panoramic radiographs, 489 patients with mesiodens were classified as an experimental group, and 499 patients without mesiodens were classified as a control group. This study consists of two networks. The first network (DeeplabV3plus) is a segmentation model that uses the posterior molar space to set the ROI in the maxillary anterior region with the mesiodens in the panoramic radiograph. The second network (Inception-resnet-v2) is a classification model that uses cropped maxillary anterior teeth to determine the presence of mesiodens. The data were divided into five groups and cross-validated. Deep learning model were created and trained using Inception-ResNet-v2. The performance of the segmentation network was evaluated using accuracy, Intersection over Union (IoU), and MeanBFscore. The overall network performance was evaluated using accuracy, precision, recall, and F1-score. RESULTS: Segmentation performance using posterior molar space in panoramic radiographs was 0.839, IoU 0.762, and MeanBFscore 0.907. The mean values of accuracy, precision, recall, F1-score, and area under the curve for the diagnosis of mesiodens using automatic segmentation were 0.971, 0.971, 0.971, 0.971, and 0.971, respectively. CONCLUSIONS: The diagnostic performance of the deep learning system using posterior molar space on the panoramic radiograph was sufficiently useful. The results of the deep learning system confirmed the possibility of complete automation of the classification of mesiodens.

The perspective of undergraduate dental students on web-based learning in pediatric dentistry during the COVID-19 pandemic: a Korean multicenter cross-sectional survey.

BACKGROUND: The COVID-19 pandemic changed the world and created a shift in the dental education program. This sudden change in the dental education program may have affected the academic standards of dental students. This study aimed to evaluate the overall satisfaction and effectiveness of online learning in pediatric dentistry of undergraduate dental students' during the COVID-19 pandemic in South Korea. METHODS: An anonymous online survey was sent to three dental schools, and responses were collected from dental school students. Questions included the demographics, perspectives of online classes, comparison of online and offline pediatric dentistry classes and opinions on how dental schools are handling the pandemic. Students' perspectives on online classes were evaluated based on satisfaction with online education. Data were analyzed using the Kruskal-Wallis test and the Mann-Whitney U test. RESULTS: Most students took online classes from home (80.9%) using Zoom (50.4%). The majority reported overall program satisfaction (74.1%) and agreed that universities implemented online classes well (55%). Students who were in favor of online classes responded more positively to questions on the effectiveness and safety of online learning (p < 0.05). Regardless of satisfaction with online education, the students agreed that the online education shift was the right decision in pandemic outbreak. CONCLUSIONS: Dental students in South Korea preferred and adapted well to the web-based learning program in pediatric dentistry during COVID-19 pandemic.

Microbiome of Saliva and Plaque in Children According to Age and Dental Caries Experience.

Dental caries are one of the chronic diseases caused by organic acids made from oral microbes. However, there was a lack of knowledge about the oral microbiome of Korean children. The aim of this study was to analyze the metagenome data of the oral microbiome obtained from Korean children and to discover bacteria highly related to dental caries with machine learning models. Saliva and plaque samples from 120 Korean children aged below 12 years were collected. Bacterial composition was identified using Illumina HiSeq sequencing based on the V3-V4 hypervariable region of the 16S rRNA gene. Ten major genera accounted for approximately 70% of the samples on average, including Streptococcus, Neisseria, Corynebacterium, and Fusobacterium. Differential abundant analyses revealed that Scardovia wiggsiae and Leptotrichia wadei were enriched in the caries samples, while Neisseria oralis was abundant in the non-caries samples of children aged below 6 years. The caries and non-caries samples of children aged 6-12 years were enriched in Streptococcus mutans and Corynebacterium durum, respectively. The machine learning models based on these differentially enriched taxa showed accuracies of up to 83%. These results confirmed significant alterations in the oral microbiome according to dental caries and age, and these differences can be used as diagnostic biomarkers.

Automated Mesiodens Classification System Using Deep Learning on Panoramic Radiographs of Children.

In this study, we aimed to develop and evaluate the performance of deep-learning models that automatically classify mesiodens in primary or mixed dentition panoramic radiographs. Panoramic radiographs of 550 patients with mesiodens and 550 patients without mesiodens were used. Primary or mixed dentition patients were included. SqueezeNet, ResNet-18, ResNet-101, and Inception-ResNet-V2 were each used to create deep-learning models. The accuracy, precision, recall, and F1 score of ResNet-101 and Inception-ResNet-V2 were higher than 90%. SqueezeNet exhibited relatively inferior results. In addition, we attempted to visualize the models using a class activation map. In images with mesiodens, the deep-learning models focused on the actual locations of the mesiodens in many cases. Deep-learning technologies may help clinicians with insufficient clinical experience in more accurate and faster diagnosis.

Comparison of Deep Learning Models for Cervical Vertebral Maturation Stage Classification on Lateral Cephalometric Radiographs.

The purpose of this study is to evaluate and compare the performance of six state-of-the-art convolutional neural network (CNN)-based deep learning models for cervical vertebral maturation (CVM) on lateral cephalometric radiographs, and implement visualization of CVM classification for each model using gradient-weighted class activation map (Grad-CAM) technology. A total of 600 lateral cephalometric radiographs obtained from patients aged 6-19 years between 2013 and 2020 in Pusan National University Dental Hospital were used in this study. ResNet-18, MobileNet-v2, ResNet-50, ResNet-101, Inception-v3, and Inception-ResNet-v2 were tested to determine the optimal pre-trained network architecture. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve (AUC) values from the receiver operating characteristic (ROC) curve were used to evaluate the performance of the models. All deep learning models demonstrated more than 90% accuracy, with Inception-ResNet-v2 performing the best, relatively. In addition, visualizing each deep learning model using Grad-CAM led to a primary focus on the cervical vertebrae and surrounding structures. The use of these deep learning models in clinical practice will facilitate dental practitioners in making accurate diagnoses and treatment plans.

Development of cellulose nanocrystal-stabilized Pickering emulsions of massoia and nutmeg essential oils for the control of Aedes albopictus.

We investigated the larvicidal potential of 10 plant essential oils (EOs) against the Asian tiger mosquito Aedes albopictus. Among the EOs, larvicidal activity against Ae. albopictus was strongest in those derived from massoia (Massoia aromatica) and nutmeg (Myristica fragrans). Larvicidal activities of massoia and nutmeg EOs against Ae. albopictus were 95.0% and 85.0% at 50 µg/mL, respectively. A total of 4 and 14 compounds were identified from massoia and nutmeg, respectively, and two massoia lactones, C10 and C12, were isolated from massoia EO. Among the identified compounds, benzyl salicylate, terpinolene, C12 massoia lactone, sabinene, benzyl benzoate, methyl eugenol, and C10 massoia lactone exhibited the strong larvicidal activity. Cellulose nanocrystal (CNC)-stabilized Pickering emulsions of massoia and nutmeg EOs were developed to overcome the insolubility of EOs in water. CNC/massoia and CNC/nutmeg emulsions were stable for at least 10 days, and larvicidal activities of CNC/massoia PE and CNC/nutmeg were higher than those of crude massoia and nutmeg EOs. This study presents a CNC-stabilized PE, a suitable formulation for EOs, as a potential larvicide against Ae. albopictus.

Larvicidal composite alginate hydrogel combined with a Pickering emulsion of essential oil.

Sulfonated cellulose nanocrystals (S-CNCs) can be used to encapsulate thyme white essential oil (EO) that is volatile and immiscible with water. S-CNCs form a Pickering emulsion (PE) with EOs and the micron-scale PEs are embedded in sodium alginate (SA) to form macroscale hydrogel beads. The incorporation of PEs with SA is confirmed with FTIR, XRD, SEM and confocal microscopic characterizations and the release behavior is monitored to understand the time-dependent biological activity of the EOs. The larvicidal performance of the SA-PE composite hydrogel beads is investigated with Aedes albopictus (Skuse) larvae. The larvicidal activity is higher for SA/PE hydrogel beads prepared at 0.5 % CaCl2 than 0.75 or 1.0 % CaCl2 due to their higher release rate.

Positional Differences of the Mandibular Canal in Relation to Permanent Mandibular First Molars with Eruption Disturbances in Children.

Eruption disturbances in permanent mandibular first molars (PM1s) are uncommon. This retrospective study aimed to investigate differences in the position of the mandibular canal in relation to PM1s, with or without, eruption disturbances. Panoramic and cross-sectional views were reconstructed from cone-beam computed tomography imaging of children with PM1 eruption disturbances. Distances from the most inferior margin of the mandible to the center of the mandibular canal (M-C) and from the outer margin of the lingual cortex to the center of the mandibular canal (L-C) were measured for normally erupted PM1s (normal group) and for PM1s with eruption disturbances (ED group) and compared using independent t-tests. The mean M-C was significantly shorter in the ED group (4.86 ± 1.07 mm) than in the normal group (6.56 ± 1.06 mm) (p < 0.05). The mean L-C was also significantly shorter in the ED group (2.74 ± 0.74 mm) than in the normal group (3.09 ± 0.71 mm) (p < 0.05). This study demonstrated that the mandibular canal tended to be positioned more inferiorly in relation to PM1s with eruption disturbances than normally erupted PM1s in children. Clinicians should be aware of this positional deviation when managing children with PM1 eruption disturbances.

Oncostatin M enhances osteogenic differentiation of dental pulp stem cells derived from supernumerary teeth.

Supernumerary tooth (ST) may arise from uncertain developmental abnormalities or underlying genetic causes, and the extraction at the early age is recommended. Dental pulp stem cells (DPSCs) are the valuable resource for the regeneration of tooth and related craniofacial structures. DPSCs isolated from ST (sDPSCs) have not been fully characterized despite the potential in the applications. The objectives of this study are the efficient isolation of sDPSCs and the analysis of the properties as stem cells. sDPSCs were established by hammer-cracking and separation of the intact pulp from ST. sDPSCs in the culture were examined by light microscope and flow cytometer for the morphology and the surface marker expression. sDPSCs exhibited the cellular morphology of typical mesenchymal stem cells and expressed CD44, CD73, CD90, CD105 and CD166, but not CD14, CD34 or CD45. sDPSCs showed the differentiation potential toward osteogenic, chondrogenic and adipogenic lineages. During osteogenic differentiation, the stimulation by Oncostatin M enhanced the differentiation and significantly increased the expression of genes involved in the hard tissue repair, such as BMP2, BMP4, BMP6 and RUNX2. sDPSCs can be effectively derived from ST and displays the characteristics of mesenchymal stem cells in the maintenance and the differentiation. sDPSCs satisfies the quality as DPSCs thus provide the valuable resource to the regenerative therapy.

Factors Associated with Molar-Incisor Hypomineralization: A Population-Based Case-Control Study.

Purpose: The purpose of this case-control study was to investigate the relationship between molar-incisor hypomineralization (MIH) and pre-, peri-, and postnatal conditions of children and mothers in South Korea. Methods: The Korean Academy of Pediatric Dentistry con- ducted this study to examine factors associated with MIH among six- to 13-year-olds. The European Academy of Pediatric Dentistry criteria and self-administered questionnaires associated with MIH were used. Results: In multivariable logistic regression analysis, the odds ratio (OR) of MIH for children whose mothers used health supplements during pregnancy was 0.65 (P=0.009). Also, children with more than three hours of out- door activities per day tended to have a lower MIH (P=0.03) than did those with zero hours of outdoor activity. Additionally, the OR of MIH for children whose mothers smoked during pregnancy was 2.37 (P=0.019) and the MIH found to be 1.33 times more frequent in children with respiratory infections during the first three years of life (P=0.048). Conclusions: Maternal smoking during pregnancy and child's pediatric respiratory infection suffered within three years after birth are factors associated with the MIH among Korean children. Further study is needed because the prevalence of MIH in children whose mothers taking health supplements (vitamins or folic acid or iron) during pregnancy is low.

Ameloblastic Fibro-Odontoma Misidentified as an Enamel Pearl.

Ameloblastic fibro-odontoma (AFO) is a rare, benign, and mixed odontogenic tumor that consists of both ectodermal and mesenchymal elements. AFO is more prevalent in young children and adolescents than in adults and is usually found in the molar area associated with a failure of tooth eruption. The purpose of this report is to discuss the differential diagnosis and treatment of a three-year-old girl diagnosed with an AFO around a primary canine. The manifestations of the lesion resembled localized periodontal disease caused by an enamel pearl. Excision and curettage were done and the separated dental hard tissue was confirmed from the enamel structure of the primary canine. In addition to the hard tissue, pulpy and soft tissues were removed together and were histologically examined, confirming the diagnosis of AFO.

Biological Activity of Thyme White Essential Oil Stabilized by Cellulose Nanocrystals.

Cellulose nanocrystals (CNCs) are produced by sulfonic acid hydrolysis and used for the formation of Pickering emulsion (PE) with thyme white essential oil (EO). Highly volatile and hydrophobic thyme white is encapsulated in PE by the amphiphilicity of CNCs. Encapsulation of EO in a CNC shell is determined by confocal microscopy with distinct fluorescent labelling. The amount of CNC affects the size distribution of PE, and the emulsion stability is confirmed by rheological property. The antimicrobial activity of the emulsion is evaluated against Escherichia coli and Staphylococcus aureus by minimal inhibitory concentration and minimum bactericidal concentration. The larvicidal activity is also investigated against Aedes albopictus by dispersing the emulsion in water.

Effects of mesiodens on adjacent permanent teeth: a retrospective study in Korean children based on cone-beam computed tomography.

BACKGROUND: Mesiodens can be associated with several complications. The optimal age for treatment, however, remains controversial. AIM: To investigate the three-dimensional (3D) positions of mesiodens using cone-beam computed tomography (CBCT) and determine the association of eruption-related complications of mesiodens with these 3D positions and delayed development of the central incisors. DESIGN: In total, 293 Korean children (383 supernumerary teeth) aged 4-10 years with no history of orthodontic treatment were included. CBCT and panoramic radiography data for all patients were retrospectively investigated with regard to the 3D positions of mesiodens, apical maturity of the permanent first molars, delayed development of the central incisors relative to the apical maturity of the permanent first molars (Nolla's stage), and eruption-related complications of mesiodens. RESULTS: Eruption-related complications were not correlated with any 3D characteristic other than the 'within the arch' position of mesiodens, while they showed a significant correlation with delayed development of the central incisors (P < 0.05). CONCLUSIONS: Mesiodens caused eruption-related complications in 33.7% patients. Moreover, the risk of these complications was higher when mesiodens caused delayed development of the central incisors. These findings can aid clinicians in planning appropriate and timely treatment for mesiodens, with focus on minimising patient discomfort.