In this paper, we aimed to evaluate the performance of a deep learning system for automated tooth detection and numbering on pediatric panoramic radiographs. Study Design: YOLO V4, a CNN (Convolutional Neural Networks) based object detection model was used for automated tooth detection and numbering. 4545 pediatric panoramic X-ray images, processed in labelImg, were trained and tested in the Yolo algorithm. Results and Conclusions: The model was successful in detecting and numbering both primary and permanent teeth on pediatric panoramic radiographs with the mean average precision (mAP) value of 92.22 %, mean average recall (mAR) value of 94.44% and weighted-F1 score of 0.91. The proposed CNN method yielded high and fast performance for automated tooth detection and numbering on pediatric panoramic radiographs. Automatic tooth detection could help dental practitioners to save time and also use it as a pre-processing tool for detection of dental pathologies.

Evaluation of deformation and fracture rates for nickel-titanium rotary instruments according to the frequency of clinical use Purpose To evaluate the deformation and fracture rates for ProTaper Universal (PTU) nickeltitanium rotary instruments according to the frequency of clinical use. Materials and MethodsA total of 619 PTU instruments (S1, S2, F1, F2, and F3) that have been used in the clinic by a single endodontist were collected over a period of 4 years. These instruments were grouped on the basis of one to three (Group A), four to six (Group B) and seven to nine (Group C) clinical uses (one canal = one use). All instruments were evaluated by a blinded investigator under a stereomicroscope at 15×-45× magnification for the presence of deformation and fracture. ResultsThe overall rates of deformation and fracture were 10% and 1.2%, respectively. The deformation and fracture rates for the S2, F1, and F2 instruments showed no significant differences among groups. However, fracture rate for S1 instruments in Group A was significantly higher than for those in Group B (p=0.025) and Group C (p=0.004). In Group C, the S1 instruments showed a significantly higher deformation rate compared with the S2 (p=0.04), F1 (p=0.008) and F2 (p=0.049) instruments; there were no other significant differences within groups. ConclusionUnder the conditions of the current study, frequency of use seemed to influence the deformation rates of PTU rotary instruments. Except S1, these instruments could be used without any fracture or deformation in up to 9 clinical cases by an experienced endodontist.

No abstract