MATERIALS AND METHODS: A DCN model was developed using pill images captured with mobile phones under unconstraint environments. The performance of the DCN model was compared to two baseline methods of hand-crafted features.
RESULTS: The DCN model outperforms the baseline methods. The mean accuracy rate of DCN at Top-1 return was 95.35%, whereas the mean accuracy rates of the two baseline methods were 89.00% and 70.65%, respectively. The mean accuracy rates of DCN for Top-5 and Top-10 returns, i.e., 98.75% and 99.55%, were also consistently higher than those of the baseline methods.
DISCUSSION: The images used in this study were captured at various angles and under different level of illumination. DCN model achieved high accuracy despite the suboptimal image quality.
CONCLUSION: The superior performance of DCN underscores the potential of Deep Learning model in the application of pill identification and verification.
METHODS: Three databases were searched to identify randomized clinical trials (RCTs) published up until September 2017. Retrieved RCTs were evaluated using the revised Cochrane Risk of Bias Tool. The primary efficacy outcome of interest was the success rate of IANB anesthesia. Meta-analytic estimates (risk ratio [RR] with 95% confidence intervals [CIs]) performed using a random effects model and publication bias determined using funnel plot analysis were assessed. Random errors were evaluated with trial sequential analyses, and the quality of evidence was appraised using a Grading of Recommendations, Assessment, Development and Evaluation approach.
RESULTS: Thirteen RCTs (N = 1034) were included. Eight studies had low risk of bias. Statistical analysis of good-quality RCTs showed a significant beneficial effect of any NSAID in increasing the anesthetic success of IANBs compared with placebo (RR = 1.92; 95% CI, 1.55-2.38). Subgroup analyses showed a similar beneficial effect for ibuprofen, diclofenac, and ketorolac (RR = 1.83 [95% CI, 1.43-2.35], RR = 2.56 [95% CI, 1.46-4.50], and RR = 2.07 [95% CI, 1.47-2.90], respectively). Dose-dependent ibuprofen >400 mg/d (RR = 1.85; 95% CI, 1.39-2.45) was shown to be effective; however, ibuprofen ≤400 mg/d showed no association (RR = 1.78; 95% CI, 0.90-3.55). TSA confirmed conclusive evidence for a beneficial effect of NSAIDs for IANB premedication. The Grading of Recommendations, Assessment, Development and Evaluation approach did not reveal any concerns regarding the quality of the results.
CONCLUSIONS: Oral premedication with NSAIDs and ibuprofen (>400 mg/d) increased the anesthetic success of IANBs in patients with irreversible pulpitis.
AIMS OF THE STUDY: The present study aims to establish safety profile for the consumption of cultivated fruiting body of O. sinensis (FBOS) by 28-days sub-acute toxicity study in Sprague Dawley rats.
MATERIALS AND METHODS: Rats were orally administered with cultivated FBOS at three graded doses (250, 500 and 1000mg/kg), once daily for 28 consecutive days. Control group received distilled water. General observations (gross behavioral changes and toxic symptoms) and body weight of each animal were monitored daily. Haematological, serum biochemical and histopathological analysis were carried out at the end of the experiment (Day 29).
RESULTS: No behavioral changes, toxic symptoms or death was observed in rats throughout the dosing period. Cultivated FBOS treatment up to 1000mg/kg did not cause any adverse effect on the growth of the animals. Results from haematology and serum biochemistry revealed no toxic effect following cultivated FBOS treatment at three graded doses for 28 days. In addition, no treatment related histopathological changes were noted in heart, spleen, kidney, lung and liver of the animals.
CONCLUSION: The present study revealed that oral administration of cultivated FBOS for 28 days, at dosage up to 1000mg/kg did not pose toxicological concern in rats. Therefore, the no-observed-adverse-effect level (NOAEL) dose of cultivated FBOS in 28-days subacute toxicity study is higher than 1000mg/kg.