No abstract

PurposeThe aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT).MethodsCombining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python.ResultsThe periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%–91.2%) for premolars and 73.4% (95% CI, 59.9%–84.0%) for molars.ConclusionsWe demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

Background : Enamel matrix derivative (EMD) has been considered to exert positive effects on wound healing, postoperative discomfort, and bone regeneration. This study investigated the efficacy of adjunctive EMD use in alveolar ridge preservation (ARP).Aim/Hypothesis : The aim of this randomized, controlled, parallel-arm study was to evaluate the (1) radiographic bone dimensional changes,(2) postoperative discomfort, and (3) early wound healing outcomes, following extraction of maxillary anterior teeth and treatment with and without the adjunctive use of EMD.Material and Methods : Thirty extraction sockets (with < 50% bone loss in the buccal bone plate) were randomly assigned to two groups-deproteinized bovine bone mineral with 10% collagen covered with two layers of a native bilayer collagen membrane with the adjunctive use of EMD (test group) and without EMD (control group). Bone dimensional changes were measured using cone beam computed tomography at 3 and 5 months after ARP. The severity and duration of pain and swelling were evaluated using self-reported questionnaires and soft tissue wound healing outcomes were assessed clinically. Chi-square tests, t -tests, and Mann-Whitney U tests were conducted to compare differences between the two groups.Results : Radiographic and clinical analyses showed no significant differences in horizontal and vertical bone dimensional changes and soft tissue wound healing outcomes (including spontaneous bleeding, persistent swelling, and ulceration) between the two groups. There were no significant differences in the severity of pain and swelling between the two groups, but the durations of pain (difference [Df] = 1.20, 95% CI = 0.33-2.06; P = 0.008) and swelling (Df = 1.06, 95% CI = 0.11-2.01; P = 0.029) were significantly reduced in the test group. Conclusion and Clinical Implications: ARP with the adjunctive use of EMD reduced the durations of postoperative pain and swelling following maxillary anterior teeth extraction.

ObjectivesThe aim of the current study was to evaluate the detection and diagnosis of three types of odontogenic cystic lesions (OCLs)—odontogenic keratocysts, dentigerous cysts, and periapical cysts—using dental panoramic radiography and cone beam computed tomographic (CBCT) images based on a deep convolutional neural network (CNN).MethodsThe GoogLeNet Inception‐v3 architecture was used to enhance the overall performance of the detection and diagnosis of OCLs based on transfer learning. Diagnostic indices (area under the ROC curve [AUC], sensitivity, specificity, and confusion matrix with and without normalization) were calculated and compared between pretrained models using panoramic and CBCT images.ResultsThe pretrained model using CBCT images showed good diagnostic performance (AUC = 0.914, sensitivity = 96.1%, specificity = 77.1%), which was significantly greater than that achieved by other models using panoramic images (AUC = 0.847, sensitivity = 88.2%, specificity = 77.0%) (p = .014).ConclusionsThis study demonstrated that panoramic and CBCT image datasets, comprising three types of odontogenic OCLs, are effectively detected and diagnosed based on the deep CNN architecture. In particular, we found that the deep CNN architecture trained with CBCT images achieved higher diagnostic performance than that trained with panoramic images.

Purpose The purpose of this study was to evaluate severe periodontitis with tooth loss as a modifiable risk factor for Alzheimer dementia (AD), vascular dementia (VaD), and mixed dementia (MD) using the National Health Insurance Service-National Health Screening Retrospective Cohort database with long-term follow-up over 14 years. Methods Multivariate Cox hazards regression analysis was applied to a longitudinal retrospective database, which was updated in 2018, to evaluate the association between severe periodontitis with few remaining teeth and dementia after adjusting for potential risk factors, including sociodemographic factors and comorbid diseases. Results Among 514,866 individuals in South Korea, 237,940 (46.2%) participants satisfying the inclusion criteria were selected. A total of 10,115 age- and sex-matched participants with severe periodontitis and 10,115 periodontally healthy participants were randomly selected and evenly assigned. The results showed that the risks of AD (hazard ratio [HR], 1.08), VaD (HR, 1.24), and MD (HR, 1.16) were significantly higher in patients with severe periodontitis with 1–9 remaining teeth after adjustment for sociodemographic factors, anthropomorphic measurements, lifestyle factors, and comorbidities. Conclusions Severe periodontitis with few remaining teeth (1–9) may be considered a modifiable risk factor for the development of AD, VaD, and MD in Korean adults.