Deep learning for determining the difficulty of endodontic treatment: a pilot study.

BACKGROUND: To develop and validate a deep learning model for automated assessment of endodontic case difficulty from periapical radiographs. METHODS: A dataset of 1,386 periapical radiographs was compiled from two clinical sites. Two dentists and two endodontists annotated the radiographs for difficulty using the "simple assessment" criteria from the American Association of Endodontists' case difficulty assessment form in the Endocase application. A classification task labeled cases as "easy" or "hard", while regression predicted overall difficulty scores. Convolutional neural networks (i.e. VGG16, ResNet18, ResNet50, ResNext50, and Inception v2) were used, with a baseline model trained via transfer learning from ImageNet weights. Other models was pre-trained using self-supervised contrastive learning (i.e. BYOL, SimCLR, MoCo, and DINO) on 20,295 unlabeled dental radiographs to learn representation without manual labels. Both models were evaluated using 10-fold cross-validation, with performance compared to seven human examiners (three general dentists and four endodontists) on a hold-out test set. RESULTS: The baseline VGG16 model attained 87.62% accuracy in classifying difficulty. Self-supervised pretraining did not improve performance. Regression predicted scores with ± 3.21 score error. All models outperformed human raters, with poor inter-examiner reliability. CONCLUSION: This pilot study demonstrated the feasibility of automated endodontic difficulty assessment via deep learning models.

Evaluation of Decayed, Missing due to Caries, and Filled Teeth Index in Children with Phenylketonuria in Comparison to Normal Population.

OBJECTIVE: Management of patients with phenylketonuria mainly includes limiting the content of phenylalanine in the diet. Therefore, the purpose of this study was to investigate oral problems in children with phenylketonuria compared to the healthy population as a case-control study. MATERIALS AND METHODS: The subjects of the case and control groups were selected according to the inclusion criteria. First, the oral cavity and tooth were examined by a specialist dentist to indicate the decayed, missing due to caries, and filled teeth index in both groups. To inves- tigate the level of phenylalanine and evaluate other laboratory examinations, 2 mL of blood and saliva samples was taken from the subjects. Blood and saliva phenylalanine levels were measured by high-performance liquid chromatography. Phosphorus, calcium, and pH levels were investigated through calorimetric measurement. The data were analyzed using Statistical Package for Social Sciences software. RESULTS: There was no significant difference between the case and control groups in terms of age and sex. The average level of calcium and phosphorus in the case group was higher than in the control group. Also, the average decayed, missing due to caries, and filled teeth index in the case group was not significantly different compared to the control group. None of the above-investigated indicators had a significant relationship with each other. On the other hand, it was found that there was a positive and significant relationship between phenylalanine in blood, saliva, and pH as well as between saliva phenylalanine with decayed, missing due to caries, and filled teeth. CONCLUSION: The results of this study indicate a significant effect of phenylketonuria disease on calcium, phosphorus, and oral pH levels in children.