The available evidence suggests a significantly positive association between periodontal disease and obesity in children. Paediatric dentists should be aware of periodontal alterations as a potential hazard associated with obesity.
The applicability of the Willems et al. model was verified on a collected sample of Malay (Malaysian nationality) children. This sample was split in a reference sample to develop a Malay-specific prediction model based on the Willems et al. method and in a test sample to validate this new developed model. Next, the incorporation of third molars into this model was analyzed. Panoramic radiographs (n = 1,403) of Malay children aged between 4 and 14.99 years (n = 702) and subadults aged between 15 and 23.99 years (n = 701) were collected. The left mandibular seven permanent teeth of the children were scored based on the staging technique described by Demirjian and converted to age using the Willems et al. method. Third molar development of all individuals was staged based on the technique described by Gleiser and Hunt modified by Kohler. Differences between dental age and chronological age were calculated and expressed in mean error (ME), mean absolute error (MAE), and root mean square error (RMSE). The Willems et al. model verified on the collected Malay children overestimated chronological age with a ME around 0.45 year. Small differences in ME, MAE, and RMSE between the verified Malay-specific prediction model and the Willems et al. model were observed. An overall neglected decrease in RMSE was detected adding third molar stages to the developed permanent teeth model.
Background
This study aims to propose the combinations of image processing and machine learning model to segment the maturity development of the mandibular premolars using a Keras-based deep learning convolutional neural networks (DCNN) model.
Methods
A dataset consisting of 240 images (20 images per stage per sex) of retrospect digital dental panoramic imaging of patients between 5 and 14 years of age was retrieved. In image preprocessing, abounding box with a dimension of 250 × 250 pixels was assigned to the left mandibular first (P1) and second (P2) permanent premolars. The implementation of dynamic programming of active contour (DP-AC) and convolutions neural network on images that require the procedure of image filtration using Python TensorFlow and Keras libraries were performed in image segmentation and classification, respectively.
Results
Image segmentation using the DP-AC algorithm enhanced the visibility of the image features in the region of interest while suppressing the image's background noise. The proposed model has an accuracy of 97.74%, 96.63% and 78.13% on the training, validation, and testing set, respectively. In addition, moderate agreement (Kappa value = 0.58) between human observer and computer were identified. Nonetheless, a robust DCNN model was achieved as there is no sign of the model's over-or under-fitting upon the learning process.
Conclusions
The application of digital imaging and deep learning techniques used by the DP-AC and convolutions neural network algorithms to segment and identify premolars provides promising results for semi-automated forensic dental staging in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.