Background: Classification of optical coherence tomography (OCT) images can be achieved with high accuracy using classical convolution neural networks (CNN), a commonly used deep learning network for computer-aided diagnosis. Classical CNN has often been criticized for suppressing positional relations in a pooling layer. Therefore, because capsule networks can learn positional information from images, we attempted application of a capsule network to OCT images to overcome that shortcoming. This study is our attempt to improve classification accuracy by replacing CNN with a capsule network. Methods: From an OCT dataset, we produced a training dataset of 83,484 images and a test dataset of 1000 images. For training, the dataset comprises 37,205 images with choroidal neovascularization (CNV), 11,348 with diabetic macular edema (DME), 8616 with drusen, and 26,315 normal images. The test dataset has 250 images from each category. The proposed model was constructed based on a capsule network for improving classification accuracy. It was trained using the training dataset. Subsequently, the test dataset was used to evaluate the trained model.Results: Classification of OCT images using our method achieved accuracy of 99.6%, which is 3.2 percentage points higher than that of other methods described in the literature. Conclusion: The proposed method achieved classification accuracy results equivalent to those reported for other methods for CNV, DME, drusen, and normal images.

The purpose of this cross-sectional pilot study was to find salivary microRNAs (miRNAs) reflecting periodontal condition in chronic periodontitis. One hundred and twenty chronic periodontitis patients (mean age, 68.4 years) participated in the study, from whom unstimulated whole saliva was collected. A multiphase study was conducted to explore salivary miRNAs as biomarkers of periodontitis. At first, a polymerase chain reaction (PCR) array was performed to compare salivary miRNAs profiles in no and mild (no/mild) and severe periodontitis patients. Next, the relative expression of salivary miRNAs on individual samples was assessed by real-time reverse transcription-PCR. The numbers (%) of patients were 26 (21.6%, no/mild), 58 (48.3%, moderate) and 36 (30.0%, severe), respectively. Among 84 miRNAs, only the relative expression of hsa-miR-381-3p in the severe periodontitis group was significantly higher than that of the no/mild periodontitis group (p < 0.05). Among the 120 patients, there was also a significant correlation between the relative expression of hsa-miR-381-3p and the mean probing pocket depth (PPD) (r = 0.181, p < 0.05). Salivary hsa-miR-381-3p was correlated with periodontitis condition in chronic periodontitis patients.

No abstract

No abstract

Bruxism is a parafunctional activity that can seriously affect quality of life. Although bruxism induces many problems in the oral and maxillofacial area, whether it contributes to the onset of malocclusion remains unclear. The purpose of this prospective cohort study was to investigate the association between the onset of malocclusion and awareness of clenching during the daytime in young adults. Among 1,092 Okayama University students who underwent normal occlusion at baseline, we analysed 238 who had undergone a dental examination and had complete data after 3 years (2013–2016). We also performed subgroup analysis to focus on the association between awake bruxism and the onset of crowding (n = 216). Odds ratios (ORs) were calculated using multivariate logistic regression analyses. The incidences of malocclusion and crowding were 53.8% and 44.5%, respectively. In multivariate logistic regression, awareness of clenching was a risk factor for crowding (OR: 3.63; 95% confidence interval [CI]: 1.08–12.17). Moreover, underweight (body mass index < 18.5 kg/m2) was related to the onset of malocclusion (OR: 2.34; 95%CI: 1.11–4.92) and crowding (OR: 2.52, 95%CI: 1.25–5.76). These results suggest that awareness of clenching during the daytime and underweight are risk factors for the onset of crowding in young adults.