YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.

OBJECTIVES: In the interpretation of panoramic radiographs (PRs), the identification and numbering of teeth is an important part of the correct diagnosis. This study evaluates the effectiveness of YOLO-v5 in the automatic detection, segmentation, and numbering of deciduous and permanent teeth in mixed dentition pediatric patients based on PRs. METHODS: A total of 3854 mixed pediatric patients PRs were labelled for deciduous and permanent teeth using the CranioCatch labeling program. The dataset was divided into three subsets: training (n = 3093, 80% of the total), validation (n = 387, 10% of the total) and test (n = 385, 10% of the total). An artificial intelligence (AI) algorithm using YOLO-v5 models were developed. RESULTS: The sensitivity, precision, F-1 score, and mean average precision-0.5 (mAP-0.5) values were 0.99, 0.99, 0.99, and 0.98 respectively, to teeth detection. The sensitivity, precision, F-1 score, and mAP-0.5 values were 0.98, 0.98, 0.98, and 0.98, respectively, to teeth segmentation. CONCLUSIONS: YOLO-v5 based models can have the potential to detect and enable the accurate segmentation of deciduous and permanent teeth using PRs of pediatric patients with mixed dentition.

Determination of growth and developmental stages in hand-wrist radiographs : Can fractal analysis in combination with artificial intelligence be used?

PURPOSE: The goal of this work was to assess the classification of maturation stage using artificial intelligence (AI) classifiers. METHODS: Hand-wrist radiographs (HWRs) from 1067 individuals aged between 7 and 18 years were included. Fifteen regions of interest were selected for fractal dimension (FD) analysis. Five predictive models with different inputs were created (model 1: only FD; model 2: FD and Chapman sesamoid stage; model 3: FD, age, and sex; model 4: FD, Chapman sesamoid stage, age, and sex; model 5: Chapman sesamoid stage, age, and sex). The target diagnoses were accelerating growth velocity, very high growth velocity, and decreasing growth velocity. Four AI algorithms were applied: multilayer perceptron (MLP), support vector machine (SVM), gradient boosting machine (GBM) and C 5.0 decision tree classifier. RESULTS: All AI algorithms except for C 5.0 yielded similar overall predictive accuracies for the five models. In order from lowest to highest, the predictive accuracies of the models were as follows: model 1 < model 3 < model 2 < model 5 < model 4. The highest overall F1 score, which was used instead of accuracy especially for models with unbalanced data, was obtained for models 1, 2, and 3 based on SVM, for model 4 based on MLP, and for model 5 based on C 5.0. Adding Chapman sesamoid stage, chronologic age, and sex as additional inputs to the FD values significantly increased the F1 score. CONCLUSION: Applying FD analysis to HWRs is not sufficient to predict maturation stage in growing patients but can be considered a growth rate prediction method if combined with the Chapman sesamoid stage, age, and sex.

Evaluation of trabecular bone and mandibular cortical thickness in adults with different vertical facial types.

OBJECTIVES: This study investigated differences in trabecular structure and mandibular cortical thickness in adults related to vertical facial type (VFT), sex, and their interactions. STUDY DESIGN: Lateral cephalometric radiographs (LCRs) and panoramic radiographs (PRs) of 256 patients were reviewed. The VFT classification into low-angle, normal, and high-angle groups was determined using angular and linear measurements on LCRs. Fractal dimension (FD) values and mandibular radiomorphometric indices (RMIs) were calculated on PRs. RESULTS: Two-way analysis of variance revealed significant differences in FD overall among VFT groups in all sites (P < .001), with pairwise comparisons indicating the greatest values in the high-angle group in the condyle (P < .05) but in the low-angle group elsewhere (P < .001). RMIs were significantly different overall regarding VFT only in the posterior mandible (P = .004), with pairwise comparisons revealing low-angle and normal group values greater than high-angle group values (P < .05). Patient sex and the interaction of facial type and sex had no significant effect on any bone measurements. CONCLUSIONS: VFT had significant effects on trabecular structure at all measured sites, but cortical thickness was affected only in 1 location.