The study aims to evaluate the diagnostic performance of an artificial intelligence system based on deep learning for the segmentation of occlusal, proximal and cervical caries lesions on panoramic radiographs. The study included 504 anonymous panoramic radiographs obtained from the radiology archive of Inonu University Faculty of Dentistry’s Department of Oral and Maxillofacial Radiology from January 2018 to January 2020. This study proposes Dental Caries Detection Network (DCDNet) architecture for dental caries segmentation. The main difference between DCDNet and other segmentation architecture is that the last part of DCDNet contains a Multi-Predicted Output (MPO) structure. In MPO, the final feature map split into three different paths for detecting occlusal, proximal and cervical caries. Extensive experimental analyses were executed to analyze the DCDNet network architecture performance. In these comparison results, while the proposed model achieved an average F1-score of 62.79%, the highest average F1-score of 15.69% was achieved with the state-of-the-art segmentation models. These results show that the proposed artificial intelligence-based model can be one of the indispensable auxiliary tools of dentists in the diagnosis and treatment planning of carious lesions by enabling their detection in different locations with high success.

No abstract

Objectives:The aim of this study was to evaluate the sealing abilities of three different gutta-percha techniques in experimentally defective roots (EDR) and non-defective roots (NR).Materials and Methods:Sixty canine teeth were divided into six groups of ten; Group 1, NR + cold lateral condensation (CLC); Group 2, EDR + LC; Group 3, NR + BeeFill; Group 4, EDR + BeeFill; Group 5, NR + Thermafil; and Group 6, EDR + Thermafil. Apical leakage was measured using a computerized fluid filtration meter with a laser system.Results:Statistical analysis revealed that the CLC demonstrated more microleakage in the EDR than in the NR (P < 0.01). Thermafil demonstrated more microleakage in the NR than in the EDR (P < 0.01). No statistically significant differences were found between the BeeFill groups (P > 0.05).Conclusions:The results of this study indicate that internal resorptive cavities can affect the apical sealing properties of different root canal filling techniques, with Thermafil ensuring the lowest apical microleakage.

PurposeThis study aimed to compare the effects of the collagen-BioAggregate mixture (CBA-M) and collagen-BioAggregate composite (CBA-C) sponge as a scaffolding material on the reparative dentin formation. Materials and MethodsCBA-C sponge (10:1 w/w) was obtained and characterized by Scanning Electron Microscopy (SEM) and Mercury Porosimetry. Cytotoxicity of the CBA-C sponge was tested by using the L929 mouse fibroblast cell line. Dental pulp stem cells (DPSCs) were isolated from the pulp tissue of sheep teeth and characterized by flow cytometry for the presence of mesenchymal stem cell marker, CD44. The osteogenic differentiation capability of isolated DPSCs was studied by Alizarin Red staining. The cells were then used to study for the compatibility of CBA-C sponge with cell proliferation and calcium phosphate deposition. The effect of CBA-C sponge and CBA-M on the induction of dentin regeneration was studied in the perforated teeth of sheep for the eight-week period. All the analyses were performed with appropriate statistical hypothesis tests. ResultsCBA-C sponge was found to be biocompatible for DPSCs. The DPSCs seeded on the CBA-C sponge were able to differentiate into the osteoblastic lineage and deposit calcium phosphate crystals in vitro. Reparative dentin formation was observed after the second week in the CBA-C sponge applied group. At the end of eight weeks, a complete reparative dentin structure was formed in the CBA-C sponge applied group, whereas necrotic tissue residues were observed in groups treated with the CBA-M. ConclusionCBA-C sponge represents a better microenvironment for reparative dentin formation probably due to maintaining DPSCs and allowing their osteogenic differentiation and thus calcium phosphate deposition.

It is important to cover the pulp surface with a biocompatible material that is physically, mechanically, and chemically adequate. Graphene has the potential to form hard tissue, but at high doses, it shows toxic effects. It can be added to biocompatible materials at low doses to enhance their hard tissue forming potential. The aim of this study was to compare the physical, chemical, and mechanical properties of graphene nanoplatelet (GNP) added Angelus mineral trioxide aggregate (A‐MTA) to pure A‐MTA and calcium hydroxide. Homogeneous mixtures (created by adding +0.1 weight[wt]% and 0.3 wt% GNP to A‐MTA), pure A‐MTA, and Dycal were used. Three disc‐shaped samples of each material were prepared using Teflon mold. Scanning electron microscope–energy dispersive X‐ray (SEM–EDX), particle size, microhardness, and Fourier transform infrared spectroscopy (FTIR) analysis of the materials were performed in vitro. Data were analyzed using Kruskal–Wallis test followed by Conover test (p < .001). A‐MTA and GNP added samples showed similar peaks in FTIR analysis. In the EDX analysis, the amount of carbon was observed with a higher increase at A‐MTA + 0.3 wt% GNP than A‐MTA + 0.1 wt% GNP. In the SEM image, hollow structure and particle size decreased as the amount of GNP increased; particle size was smaller at A‐MTA + 0.3 wt% GNP than A‐MTA + 0.1 wt% GNP (p < .001). A‐MTA + 0.3 wt% GNP showed the highest microhardness while Dycal showed the lowest microhardness. The addition of GNP, a material with high potential for forming hard tissue, to the structure of capping materials can also positively contribute to the microhardness of the capping materials.