RESUMO
Background/Purpose: The preciseness of detecting periodontal bone loss is examiners dependent, and this leads to low reliability. The need for automated assistance systems on dental radiographic images has been increased. To the best of our knowledge, no studies have quantitatively and automatically staged periodontitis using dental periapical radiographs. The purpose of this study was to evaluate periodontal bone loss and periodontitis stage on dental periapical radiographs using deep convolutional neural networks (CNNs). Materials and methods: 336 periapical radiographic images (teeth: 390) between January 2017 and December 2019 were collected and de-identified. All periapical radiographic image datasets were divided into training dataset (n = 82, teeth: 123) and test dataset (n = 336, teeth: 390). For creating an optimal deep CNN algorithm model, the training datasets were directly used for the segmentation and individual tooth detection. To evaluate the diagnostic power, we calculated the degree of alveolar bone loss deviation between our proposed method and ground truth, the Pearson correlation coefficients (PCC), and the diagnostic accuracy of the proposed method in the test datasets. Results: The periodontal bone loss degree deviation between our proposed method and the ground truth drawn by the three periodontists was 6.5 %. In addition, the overall PCC value of our proposed system and the periodontists' diagnoses was 0.828 (P < 0.01). The total diagnostic accuracy of our proposed method was 72.8 %. The diagnostic accuracy was highest for stage III (97.0 %). Conclusion: This tool helps with diagnosis and prevents omission, and this may be especially helpful for inexperienced younger doctors and doctors in underdeveloped countries. It could also dramatically reduce the workload of clinicians and timely access to periodontist care for people requiring advanced periodontal treatment.
RESUMO
Background/purpose: Asymptomatic COVID-19 patients visit the dental clinic for routine treatment, during which, high-speed handpieces, and third-use sprayers can produce aerosols. We focused on the effect and possible inadequacy of personal protective equipment (PPE) while cleaning teeth and assessed whether doctors' proficiency was related to the range of spraying droplets. Materials and methods: Doctors were divided into three different groups: attending physicians, residents, and intern respectively. Each doctor treated 15 patients; each group comprised 30 patients. The dentists wore leg covers, shoe covers, medical masks, haircaps, full masks, waterproof barrier gowns, and gloves. Each patient was covered with a waterproof hole towel, and the upper edge was fixed to the patient's nose with a medical tape. After cleaning the teeth with water contained red pigment, the spattering distance and range of droplets were calculated. Concurrently, we examined whether there was any droplet contamination on the PPE. Results: With the exception of shoe covers, haircaps, and medical surgical masks, pigment splash marks were found on both the dentist and assistant's PPE. The interns performed cleaning for a significantly longer time than the residents and attending physicians, with a significant statistical difference (P < 0.05). The spatter distance for the interns was significantly larger than the residents (P < 0.05). Conclusion: It is recommended that the hole towel be centered on the patient's nose tip, at least larger than a radius of 54.9-64.5 cm. The dentist's proficiency did cause differences in the duration of teeth cleaning, which further affects the spatter distance.
