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.
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.
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.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.