Alveolar Bone Segmentation in Intraoral Ultrasonographs with Machine Learning.

The use of intraoral ultrasound imaging has received great attention recently due to the benefits of being a portable and low-cost imaging solution for initial and continuing care that is noninvasive and free of ionizing radiation. Alveolar bone is an important structure in the periodontal apparatus to support the tooth. Accurate assessment of alveolar bone level is essential for periodontal diagnosis. However, interpretation of alveolar bone structure in ultrasound images is a challenge for clinicians. This work is aimed at automatically segmenting alveolar bone and locating the alveolar crest via a machine learning (ML) approach for intraoral ultrasound images. Three convolutional neural network-based ML methods were trained, validated, and tested with 700, 200, and 200 images, respectively. To improve the robustness of the ML algorithms, a data augmentation approach was introduced, where 2100 additional images were synthesized through vertical and horizontal shifting as well as horizontal flipping during the training process. Quantitative evaluations of 200 images, as compared with an expert clinician, showed that the best ML approach yielded an average Dice score of 85.3%, sensitivity of 88.5%, and specificity of 99.8%, and identified the alveolar crest with a mean difference of 0.20 mm and excellent reliability (intraclass correlation coefficient ≥0.98) in less than a second. This work demonstrated the potential use of ML to assist general dentists and specialists in the visualization of alveolar bone in ultrasound images.

Improving ground beef safety and stabilizing color during irradiation using antioxidants, reductants or TSP.

The objective of this research was to extend ground beef retail display life using antioxidants, reductants, and/or TSP treatments combined with electron beam irradiation. Ground beef was produced with added butylated hydroxyanisole (BHA) plus butylated hydroxytoluene (BHT) with the following combinations; (1) ascorbate; (2) trisodium phosphate(buffer); (3) erythorbate; (1) and (2); (1) and (3); (1), (2), and (3); and an untreated control, C. Half of the treated samples were irradiated (I) at 2.0kGy-absorbed dose under a nitrogen atmosphere, half remained non-irradiated (N). Samples were displayed under atmospheric oxygen and evaluated for total aerobic plate count (TPC), thiobarbituric acid reactive substances (TBARS) and instrumental color during 9d of simulated retail display (SRD). Controls had the highest (P<0.05) TBARS value and the lowest (P<0.05) redness (CIE a∗), proportion of oxymyoglobin and vividness. Treated irradiated samples were just as red and vivid on SRD day 9 as the non-irradiated untreated control at day 0. Treatments stabilized color and lipids of ground beef after irradiation and during SRD.

The pre- and post-grinding application of rosemary and its effects on lipid oxidation and color during storage of ground beef.

The timing of the application of rosemary extract was evaluated as one-way of minimizing myoglobin and lipid oxidation in ground beef. In experiment 1, rosemary extract was added to beef at four different stages namely trim, cube, coarse, and fine ground beef. The beef was evaluated for color and TBARS values during 144h of storage (4°C). Results showed that when rosemary was added to the pre-grinding treatments of trim and cube, ground beef had the highest a(∗) values (redness), oxymyoglobin content, and lowest TBARS values at 144h. In experiment 2, the effect of rosemary extract was evaluated on the color quality of case ready ground beef inoculated with 10(7)CFU/g Escherichia coli. Microbial counts, color, and TBARS values were measured during 144h of simulated storage. The results showed that both the rosemary treated samples that were inoculated and uninoculated remained redder longer and had lower TBARS values than the untreated inoculated and uninoculated controls. There was no significant inhibition of E. coli by the rosemary extract.