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.

Purpose The aim of this study was to assess the performance of a deep learning system for permanent tooth germ detection on pediatric panoramic radiographs. Materials and Methods In total, 4518 anonymized panoramic radiographs of children between 5 and 13 years of age were collected. YOLOv4, a convolutional neural network (CNN)-based object detection model, was used to automatically detect permanent tooth germs. Panoramic images of children processed in LabelImg were trained and tested in the YOLOv4 algorithm. True-positive, false-positive, and false-negative rates were calculated. A confusion matrix was used to evaluate the performance of the model. Results The YOLOv4 model, which detected permanent tooth germs on pediatric panoramic radiographs, provided an average precision value of 94.16% and an F1 value of 0.90, indicating a high level of significance. The average YOLOv4 inference time was 90 ms. Conclusion The detection of permanent tooth germs on pediatric panoramic X-rays using a deep learning-based approach may facilitate the early diagnosis of tooth deficiency or supernumerary teeth and help dental practitioners find more accurate treatment options while saving time and effort.

Objectives: This study was designed to investigate Artificial Intelligence in Dental Radiology (AIDR) videos on YouTube in terms of popularity, content, reliability, and educational quality. Methods: Two researchers systematically searched about AIDR on YouTube on January 27, 2020, by using the terms "artificial intelligence in dental radiology," "machine learning in dental radiology," and "deep learning in dental radiology." The search was performed in English, and 60 videos for each keyword were assessed. Video source, content type, time since upload, duration, and number of views, likes, and dislikes were recorded. Video popularity was reported using Video Power Index (VPI). The accuracy and reliability of the source of information were measured using the adapted DISCERN score. The quality of the videos was measured using JAMAS and modified Global Quality Score (mGQS) and content via Total Concent Evaluation (TCE). Results: There was high interobserver agreement for DISCERN (intraclass cor

Background The aim of this study was to compare the efficacy of K-type stainless steel hand instruments (Mani Inc. ), Fanta AF™ Ledge Correction (LC) (Fanta Dental), and Hyflex EDM (Coltene-Whaledent) for ledge correction, canal transport, centric ability, and shaping (preparation) time after an artificial ledge has been bypassed manually in highly curved canals using acrylic blocks. Methods Forty-two resin blocks, each with a radius of 5 mm (Endo Trainer Block, VDW) and an apical inclination of 55°, were used. Under stereomicroscope magnification, standard artificial ledges were created on acrylic blocks, and attempts were then made to eliminate them using hand instruments, FantaAF™ LC, and Hyflex EDM. Before and after images were obtained using a stereomicroscope and compared using Photoshop. Results Fanta AF™ LC and Hyflex EDM were found to be more effective for correcting ledges than hand instruments. The use of hand instruments resulted in the greatest transportation away from the canal curvature in the apical area. The canal shaping was completed in the shortest amount of time using Fanta AF™ LC, followed by HyFlex EDM and then the hand instruments. Conclusion In terms of centric ability, the order from best to worst is as follows: Fanta AF™ LC, Hyflex EDM, and hand instruments. After the ledge was manually bypassed with hand instruments in the root canals, Hyflex EDM and Fanta AF™ LC were found to be more effective than hand instruments in reshaping the previously unreachable region between the ledge and the foramen apical.

Aim: The aim of this study was to compare the cyclic fatigue resistance of different heat-treated nickel-titanium rotary systems at intracanal temperature.  Methodology: A total of 90 OneCurve (Micro-Mega, Besançon, France), VDW.ROTATE (VDW Dental, Munich, Germany), Typhoon (Clinician’s Choice, New Milford, CT, USA), HyFlex EDM (Coltene/Whaledent AG, Altstatten, Switzerland), and EndoArt Gold and Blue (Inci Dental, Istanbul, Turkey) (n = 15) rotary files (#25/0.06) were tested at intracanal temperature (35.5 ℃) using a dynamic model in a stainless-steel artificial canal with an inner diameter of 1.5 mm, 60° angle of curvature, and 2 mm radius of curvature. Testing was conducted until fracturing, at which time the device stopped automatically, and the number of rotations was calculated as seconds. Lengths of fractured parts were measured using a digital caliper. One-way ANOVA test followed by Tukey’s test was used to compare the groups. Scanning electron microscopic evaluation was performed to confirm the types of fracture. Results: EndoArt Blue group had a significantly higher mean time to fracture in all groups, followed by the HyFlex EDM, VDW.ROTATE, OneCurve, EndoArt Gold, and Typhoon. In addition, the HyFlex EDM and VDW.ROTATE groups had no significant differences between each other and were significantly better than the others. No significant differences were found between the OneCurve, EndoArt Gold, and Typhoon groups (p>0.05). Conclusion: This is the first study in the literature for EndoArt NiTi files and the second study for VDW.ROTATE that evaluated cyclic fatigue resistance. Novel EndoArt Blue files exhibited significantly greater cyclic fatigue resistance than the other NiTi files.   How to cite this article: Güneç HG, Keskin NB, Haznedaroğlu F. Comparison of cyclic fatigue resistance of different and novel heat-treated nickel-titanium rotary file systems at intracanal temperature. Int Dent Res 2021;11(3):158-64. https://doi.org/10.5577/intdentres.2021.vol11.no3.4   Linguistic Revision: The English in this manuscript has been checked by at least two professional editors, both native speakers of English.

Objectives The aim of this study is to evaluate the success rate of radiological diagnoses regarding caries and periapical infection, comparing an artificial intelligence application against junior dentists, based on the valid determinations by specialist dentists.Methods In the initial stage of the study, 2 specialist dentists evaluated the presence of caries and periapical lesions on 500 digital panoramic radiographs, and the detection time was recorded in seconds. In the second stage, 3 junior dentists and an artificial intelligence application performed diagnoses on the same panoramic radiographs, and the diagnostic results and durations were recorded in seconds.Results The artificial intelligence and the three junior dentists, respectively, detected dental caries at an SEN of 0.907,0.889,0.491,0.907; a SPEC of 0.760,0.740,0.454,0.769660; a PPV of 0.693,0.470,0.155,0.666; an NPV of 0.505,0.415,0.275,0.367 and an F1-score of 0.786,0.615,0.236,0.768. The artificial intelligence and the three junior dentists respectively detected periapical lesions at an SEN of 0.973,0.962,0.758,0.958; a SPEC of 0.629,0.421,0.404,0.621; a PPV of 0.861,0.651,0.312,0.648; an NPV of 0.689,0.673,0.278,0.546 and an F1-score of 0.914,0.777,0.442,0.773.Conclusion The artificial intelligence application gave more accurate results, especially in detecting periapical lesions. On the other hand, in caries detection, the underdiagnosis rate was high for both artificial intelligence and junior dentists. Regarding the evaluation time needed, artificial intelligence performed faster, on average.

<p><strong>Objective: </strong>The aim of this in vitro study was to compare the effectiveness of different final irrigant agitation techniques in the removal of <em>Enterococcus faecalis</em> biofilms from root canals. <strong>Material and Methods:</strong> In total, the root canals of 85 extracted single-rooted human maxillary incisors teeth were prepared using the Revo-S system to a 40/06 size. The apical foramen of each tooth was sealed by light-cured resin composite material to obstruct bacterial leakage. The specimens were sterilized in an autoclave at 121°C for 15 min and stored until further use. All teeth except five (negative control group) were inoculated with <em>Enterococcus faecalis</em> and incubated in a CO₂ chamber at 37°C for 7 days; the trypticase soy broth was changed every 2 days. For the determination of possible biofilm formation, five of the 80 teeth were randomly selected as a positive control group; one tooth of positive control group was analysed for biofilm development by scanning electron microscope (SEM) and these teeth received no final irrigant agitation procedure. Then, the remaining 75 teeth were randomly divided into five test groups (n=15 each) and were sequentially irrigated with 5% sodium hypochlorite (NaOCl), 17% ethylenediaminetetraacetic acid and 5% NaOCl. Following each irrigant application, different final irrigant agitation techniques were introduced for 60 s (3×20-s sessions). Group 1 received manual–dynamic agitation, group 2 received passive ultrasonic agitation (PUI), group 3 received EndoActivator agitation, group 4 received photon-initiated photoacoustic streaming (PIPS) with the Er:YAG laser and group 5 received conventional syringe irrigation. Colony-forming units (CFUs) were counted in samples from the positive control and test groups. Data were analysed using Kruskal–Wallis and post-hoc Mann–Whitney U multiple comparison tests. <strong>Results:</strong> <em>E. faecalis </em>elimination was significantly better in the experimental groups than in the positive control groups (p &lt; 0.001). Manual–dynamic agitation and conventional syringe irrigation, with no significant differences between the two groups. <strong>Conclusion:</strong> Essentially, CFU reduction was significantly greater in the PUI, EndoActivator and PIPS groups than in the manual–dynamic agitation and conventional syringe irrigation groups (p &lt;0.001), with no significant differences among the former three groups.</p><p><strong>Keywords</strong></p><p>Enterococcus faecalis; Irrigant agitation; Irrigant solutions; Photon-initiated photoacoustic streaming; Passive ultrasonic irrigation.</p>

Aim. This study applied a CNN (convolutional neural network) algorithm to detect prosthetic restorations on panoramic radiographs and to automatically detect these restorations using deep learning systems. Materials and Methods. This study collected a total of 5126 panoramic radiographs of adult patients. During model training, .bmp, .jpeg, and .png files for images and .txt files containing five different types of information are required for the labels. Herein, 10% of panoramic radiographs were used as a test dataset. Owing to labeling, 2988 crowns and 2969 bridges were formed in the dataset. Results. The mAP and mAR values were obtained when the confidence threshold was set at 0.1. TP, FP, FN, precision, recall, and F1 score values were obtained when the confidence threshold was 0.25. The YOLOv4 model demonstrated that accurate results could be obtained quickly. Bridge results were found to be more successful than crown results. Conclusion. The detection of prosthetic restorations with artificial intelligence on panoramic radiography, which is widely preferred in clinical applications, provides convenience to physicians in terms of diagnosis and time management.