Objectives: The objective of this study is to develop a deep learning (DL) model for fast and accurate mandibular canal (MC) segmentation on cone beam computed tomography (CBCT). Methods: A total of 220 CBCT scans from dentate subjects needing oral surgery were used in this study. The segmentation ground truth is annotated and reviewed by two senior dentists. All patients were randomly splitted into a training dataset (n = 132), a validation dataset (n = 44) and a test dataset (n = 44). We proposed a two-stage 3D-UNet based segmentation framework for automated MC segmentation on CBCT. The Dice Similarity Coefficient (DSC) and 95% Hausdorff Distance (95% HD) were used as the evaluation metrics for the segmentation model. Results: The two-stage 3D-UNet model successfully segmented the MC on CBCT images. In the test dataset, the mean DSC was 0.875 ± 0.045 and the mean 95% HD was 0.442 ± 0.379. Conclusions: This automatic DL method might aid in the detection of MC and assist dental practitioners to set up treatment plans for oral surgery evolved MC.

This study aims to investigate the relationship between vitamin intake and the occurrence of dental caries. This study was a retrospective study that collected data from the National Health And Nutrition Examination Survey database from 2011 to 2018. The number of dental caries teeth was determined using the Radike AW. Criteria for diagnosis of caries (1968), and vitamin consumption data were obtained through face-to-face interviews. Logistic regression analysis was used to explore the association between dental caries and vitamins, and variables with P < .1 in the univariate analysis were selected for multivariate logistic regression analysis. Clinical prediction models were constructed for variables with P < .05 and were internally and externally validated to assess the predictive ability of the models. This study included 4221 subjects (2215 training, 2006 validation), with vitamin C (47.6%), vitamin K (19.4%), vitamin B12 (14.2%), and vitamin D (11.3%) demonstrating the highest intake proportions. Logistic regression identified age, education, vitamin D, and vitamin K as predictors of dental caries, while the clinical model exhibited consistent moderate predictive performance across both datasets. Results remained stable after variable incorporation, confirming model reliability. Our findings suggest an association between vitamin D intake and vitamin K deficiency with dental caries; however, further prospective studies are warranted to confirm causal mechanisms.