ISSN : 0376-4672
Aim: To evaluate the accuracy of indirect bonding using a jig fabricated from the digital setup model. Materials and Methods: Total 120 bracket jigs for the maxillary teeth were fabricated using computer-aided design and manufacturing (CAD/CAM) from 10 maxillary digital setup models. Brackets were bonded using the jigs on five models (Group 1), and using the jigs and additional vacuum tray on five models (Group 2). The models were scanned again and superimposed with each initial digital models for evaluation of bonding accuracy. Results: Indirect bonding using CAD/CAM jigs showed the average bonding error of ± 0.1 mm at linear measurement and ± 2.0°at angular measurement except labio-lingual inclination (3.36°) at the premolar of Group 1. The bonding accuracy were not statistically different between both groups. Conclusions: CAD/CAM jigs can transfer the bracket to the desired position regardless of whether additional vacuum tray is used or not, and this indirect bonding system provides clinically acceptable accuracy.
Purpose: The purpose of this study is to analyze the prevalence and infection status of COVID-19 confirmed patients among dental healthcare workers, and to suggest guidelines for dental infection control, management and prevention based on the latest literature. Method: Information registered in the Basic Epidemiological Survey of COVID-19 confirmed cases of dental healthcare workers(dentists, dental hygienists, dental technicians) from the Korea Disease Control and Prevention Agency for 23 months from February 2020 to December 2021 was analyzed. Results: In the case of dentists, the number of confirmed cases increased about 9 times from an average of 1.1 monthly in 2020 to an average of 9.8 monthly in 2021. The number of confirmed cases among dentists, dental hygienists, and dental technicians has increased, with a total cumulative number of 395 confirmed cases until 2021. The highest number of month - ly confirmed cases was reported 111 cases in December 2021. There were 19.2 times more confirmed cases (269 cases) caused by community groups or close contact than the number of confirmed cases (14 cases) in dental hospital settings. Conclusions: Dental healthcare workers should follow basic infection control for COVID-19 prevention in the dental environment. Moreover, dental healthcare workers should check the latest COVID-19 guidelines, COVID-19 guidelines and follow them strictly in dental clinics as well as in their local communities.
Artificial intelligence (AI) technology is widely used in our life. Likewise, AI in the field of oral and maxillo facial radiology is being studied in various fields such as detection, classification, segmentation, measurement, and image translation. This study aimed to investigate the 1) research papers and 2) developed software based on AI in the oral and maxillofacial radiology to help dentists actively utilize the upcoming AI application. Papers were searched through 5 major data bases until June 2021, and a total of 101 papers corresponding to dental imaging-based AI research in the oral and maxillofacial area were collected. A number of AI papers showed a sharp increase from 2017, and the most research conducted on panoramas. The AI based dental imaging software search for the purpose of commercialization was first collected based on the list announced on October 21, 2020 by the Ministry of Food and Drug Safety of Korea and the web da tabase search was on October 22-23, 2021. Total 23 software were searched, and the function of automatically detecting lesions in panoramic or apical images and the orthodontic diagnosis analysis function by automati cally recognizing important anatomical landmarks in cephalogram were the most popular in the world. If a clear profitability model is presented in the future and evidence for clinical effectiveness and ethical re sponsibility are prepared, the clinical use of AI-based application using dental images will increase. Therefore, it is thought that dentists need to take an interest in AI technology research trends and product development and actively participate.
Recently, AI has made rapid developments in various fields. Therefore, it is meaningful to look into the future of AI in the dental field and what needs to be supplemented to minimize its side effects. In this article, the future of AI technology in the dental field in the near future and the coping direction were summarized based on the insights of the papers on the future of AI in this field. In the future, AI will be able to provide more useful diagnosis and treatment planning assistance by comprehen sively analyzing various information such as EMR data, article, genome, and wearable data as well as X-ray image. In addition, the efficiency of dental work will be improved by automating the design of the laboratory work and device. This efficiency can be extended from dental inventory to patient appointment management, and instant feedback in the clinic, and eventually develop into an comprehensive dental care system. With the advent of more advanced natural language processing systems, smart AI assistants who can have conversations about treatment and dental operations will appear. In addition, face-to-face contact with patients will increase along with AI-based charting automation, and AI will improve the patient experience, allowing more patients to receive appropriate oral health care. As AI is expected to be broadly applied to dentistry, a basic understanding of how big data is collected and how AI algorithms are programmed is now essential for dentists as well.
Deep learning is a subset of machine learning, and machine learning is also a subset of artificial intelligence (AI). The biggest difference between machine learning and deep learning is that in the learning of artificial intelligence models, machine learning basically requires a human feature extraction process before learning, but deep learning does not require this process and the original data is directly used as input. The development of deep learning coincides with the development of artificial neural networks (ANNs), and many people have contributed to the development of artificial neural networks for decades. The following five models are the representative architectures most widely used in deep learning. That is, Deep Feedforward Neural Network (D FFNN), Convolutional Neural Network (CNN), Deep Belief Network (DBN), Autoencoders (AE), and Long Short-Term Memory (LSTM) Network. A convolutional neural network (CNN) is a feedforward NN composed of a convolutional layer, a ReLU activation function, and a pooling layer. CNNs provide properties of weight sharing and local connectivity to process high-dimensional data. In dental and medical fields, an AI model that can be interpretable or explainable (XAI) is needed to increase patient persuasiveness. In the future, explainable AI (XAI) will become an indispensable and practical component in order to obtain an improved, transparent, secure, fair and unbiased AI learning model.
