Fully automated identification of cephalometric landmarks for upper airway assessment using cascaded convolutional neural networks.

OBJECTIVES: The aim of the study was to evaluate the accuracy of a cascaded two-stage convolutional neural network (CNN) model in detecting upper airway (UA) soft tissue landmarks in comparison with the skeletal landmarks on the lateral cephalometric images. MATERIALS AND METHODS: The dataset contained 600 lateral cephalograms of adult orthodontic patients, and the ground-truth positions of 16 landmarks (7 skeletal and 9 UA landmarks) were obtained from 500 learning dataset. We trained a UNet with EfficientNetB0 model through the region of interest-centred circular segmentation labelling process. Mean distance errors (MDEs, mm) of the CNN algorithm was compared with those from human examiners. Successful detection rates (SDRs, per cent) assessed within 1-4 mm precision ranges were compared between skeletal and UA landmarks. RESULTS: The proposed model achieved MDEs of 0.80 ± 0.55 mm for skeletal landmarks and 1.78 ± 1.21 mm for UA landmarks. The mean SDRs for UA landmarks were 72.22 per cent for 2 mm range, and 92.78 per cent for 4 mm range, contrasted with those for skeletal landmarks amounting to 93.43 and 98.71 per cent, respectively. As compared with mean interexaminer difference, however, this model showed higher detection accuracies for geometrically constructed UA landmarks on the nasopharynx (AD2 and Ss), while lower accuracies for anatomically located UA landmarks on the tongue (Td) and soft palate (Sb and St). CONCLUSION: The proposed CNN model suggests the availability of an automated cephalometric UA assessment to be integrated with dentoskeletal and facial analysis.

Effect of piezopuncture on tooth movement and bone remodeling in dogs.

INTRODUCTION: The aim of the study was to elucidate whether a newly developed, minimally invasive procedure, piezopuncture, would be a logical modification for accelerating tooth movement in the maxilla and the mandible. METHODS: Ten beagle dogs were divided into 2 groups. Traditional orthodontic tooth movement was performed in the control group. In the experimental group, a piezotome was used to make cortical punctures penetrating the gingiva around the moving tooth. Measurements were made in weeks 1 through 6. Tooth movement and bone apposition rates from the histomorphometric analyses were evaluated by independent t tests. RESULTS: The cumulative tooth movement distance was greater in the piezopuncture group than in the control group: 3.26-fold in the maxilla and 2.45-fold in the mandible. Piezopuncture significantly accelerated the tooth movements at all observation times, and the acceleration was greatest during the first 2 weeks for the maxilla and the second week for the mandible. Anabolic activity was also increased by piezopuncture: 2.55-fold in the maxilla and 2.35-fold in the mandible. CONCLUSIONS: Based on the different effects of piezopuncture on the maxilla and the mandible, the results of a clinical trial of piezopuncture with optimized protocols might give orthodontists a therapeutic benefit for reducing treatment duration.

Modeling to predict growth/no growth boundaries and kinetic behavior of Salmonella on cutting board surfaces.

This study developed models to predict the growth probabilities and kinetic behavior of Salmonella enterica strains on cutting boards. Polyethylene coupons (3 by 5 cm) were rubbed with pork belly, and pork purge was then sprayed on the coupon surface, followed by inoculation of a five-strain Salmonella mixture onto the surface of the coupons. These coupons were stored at 13 to 35°C for 12 h, and total bacterial and Salmonella cell counts were enumerated on tryptic soy agar and xylose lysine deoxycholate (XLD) agar, respectively, every 2 h, which produced 56 combinations. The combinations that had growth of ≥0.5 log CFU/cm(2) of Salmonella bacteria recovered on XLD agar were given the value 1 (growth), and the combinations that had growth of <0.5 log CFU/cm(2) were assigned the value 0 (no growth). These growth response data from XLD agar were analyzed by logistic regression for producing growth/no growth interfaces of Salmonella bacteria. In addition, a linear model was fitted to the Salmonella cell counts to calculate the growth rate (log CFU per square centimeter per hour) and initial cell count (log CFU per square centimeter), following secondary modeling with the square root model. All of the models developed were validated with observed data, which were not used for model development. Growth of total bacteria and Salmonella cells was observed at 28, 30, 33, and 35°C, but there was no growth detected below 20°C within the time frame investigated. Moreover, various indices indicated that the performance of the developed models was acceptable. The results suggest that the models developed in this study may be useful in predicting the growth/no growth interface and kinetic behavior of Salmonella bacteria on polyethylene cutting boards.