Aim: The goal was to use a deep convolutional neural network to measure the radiographic alveolar bone level to aid periodontal diagnosis. Materials and Methods: A deep learning (DL) model was developed by integrating three segmentation networks (bone area, tooth, cemento-enamel junction) and image analysis to measure the radiographic bone level and assign radiographic bone loss (RBL) stages. The percentage of RBL was calculated to determine the stage of RBL for each tooth. A provisional periodontal diagnosis was assigned using the 2018 periodontitis classification. RBL percentage, staging, and presumptive diagnosis were compared with the measurements and diagnoses made by the independent examiners. Results:The average Dice Similarity Coefficient (DSC) for segmentation was over 0.91. There was no significant difference in the RBL percentage measurements determined by DL and examiners (p ¼ :65). The area under the receiver operating characteristics curve of RBL stage assignment for stages I, II, and III was 0.89, 0.90, and 0.90, respectively. The accuracy of the case diagnosis was 0.85. Conclusions:The proposed DL model provides reliable RBL measurements and image-based periodontal diagnosis using periapical radiographic images. However, this model has to be further optimized and validated by a larger number of images to facilitate its application.

BackgroundThe purpose of this article is to review and update the current developments of biologically active dental implant surfaces and their effect on osseointegration.MethodsPubMed was searched for entries from January 2006 to January 2016. Only in-vivo studies that evaluated the effects of biomolecular coatings on titanium dental implants inserted into the bone of animals or humans were included.ResultsThirty four non-review studies provided data and observations were included in this review. Within the criteria, four categories of biomolecular coatings were evaluated. The potential biomolecules include bone morphogenetic proteins in 8 articles, other growth factors in 8 articles, peptides in 5 articles, and extracellular matrix in 13 articles. Most articles had a healing period of 1 to 3 months and the longest time of study was 6 months. In addition, all studies comprised of implants inserted in animals except for one, which evaluated implants placed in both animals and humans. The results indicate that dental implant surface modification with biological molecules seem to improve performance as demonstrated by histomorphometric analysis (such as percentage of bone-to-implant contact and peri-implant bone density) and biomechanical testing (such as removal torque, push-out/pull-out tests, and resonance frequency analysis).ConclusionsBioactive surface modifications on implant surfaces do not always offer a beneficial effect on osseointegration. Nevertheless, surface modifications of titanium dental implants with biomolecular coatings seem to promote peri-implant bone formation, resulting in enhanced osseointegration during the early stages of healing. However, long-term clinical studies are needed to validate this result. In addition, clinicians must keep in mind that results from animal experiments need not necessarily reflect the human clinical reality.

Smoking has been identified as a major risk factor for periodontal diseases (Genco & Borgnakke, 2013). Previous longitudinal studies have found that smokers have accelerated and more severe periodontal tissue destruction, poor wound healing, and respond less favourably towards periodontal treatments (Feldman et al., 1987;

Periodontitis disproportionately affects different racial and ethnic populations. In this study, we used qPCR to determine and compare oral microbial profiles in dental plaque samples from 191 periodontitis patients of different ethnic/racial backgrounds. We also obtained the periodontal parameters of these patients retrospectively using axiUm and performed statistical analysis using SAS 9.4. We found that in this patient cohort, neighborhood median incomes were significantly higher among Caucasians Americans (CAs) than among African Americans (AAs) and Hispanic Americans (HAs). Levels of total bacteria and Porphyromonas gingivalis, a keystone periodontal pathogen, were not evenly distributed among the three groups. We confirmed our previous findings that Streptococcus cristatus reduces P. gingivalis virulence potential and likely serves as a beneficial bacterium. We also showed the ratio of S. cristatus to P. gingivalis to be significantly higher in CAs than in HAs and AAs. Our results suggest that higher levels of P. gingivalis and lower ratios of S. cristatus to P. gingivalis may contribute to periodontal health disparities.

No abstract