Tongue feature dataset construction and real-time detection.

BACKGROUND: Tongue diagnosis in traditional Chinese medicine (TCM) provides clinically important, objective evidence from direct observation of specific features that assist with diagnosis. However, the current interpretation of tongue features requires a significant amount of manpower and time. TCM physicians may have different interpretations of features displayed by the same tongue. An automated interpretation system that interprets tongue features would expedite the interpretation process and yield more consistent results. MATERIALS AND METHODS: This study applied deep learning visualization to tongue diagnosis. After collecting tongue images and corresponding interpretation reports by TCM physicians in a single teaching hospital, various tongue features such as fissures, tooth marks, and different types of coatings were annotated manually with rectangles. These annotated data and images were used to train a deep learning object detection model. Upon completion of training, the position of each tongue feature was dynamically marked. RESULTS: A large high-quality manually annotated tongue feature dataset was constructed and analyzed. A detection model was trained with average precision (AP) 47.67%, 58.94%, 71.25% and 59.78% for fissures, tooth marks, thick and yellow coatings, respectively. At over 40 frames per second on a NVIDIA GeForce GTX 1060, the model was capable of detecting tongue features from any viewpoint in real time. CONCLUSIONS/SIGNIFICANCE: This study constructed a tongue feature dataset and trained a deep learning object detection model to locate tongue features in real time. The model provided interpretability and intuitiveness that are often lacking in general neural network models and implies good feasibility for clinical application.

Arecoline Induces ROS Accumulation, Transcription of Proinflammatory Factors, and Expression of KRT6 in Oral Epithelial Cells.

Areca nut is a major contributor to the high prevalence of oral cancer in Asia. The precise mechanisms by which areca nut stimulates mucosal cells and contributes to the progression of oral cancer urgently require clarification. The current study aimed to assess the effects of arecoline on the normal human gingival epithelium cell line S-G. Cell viability, levels of reactive oxygen species (ROS), protein expression, cellular morphology, and gene expression were evaluated using the MTT test, flow cytometry, Western blot analysis, optical or confocal microscopy, and RT-qPCR. Keratin (KRT6) analysis involved matched normal and cancer tissues from clinical head and neck specimens. The results demonstrated that 12.5 µg/mL of arecoline induced ROS production, tumor necrosis factor-α (TNF-α), and interleukin-6 (IL-6) mRNA expression in S-G cells. This activation of the MAPK/ERK pathway increased KRT6 expression while limiting cell migration. In head and neck cancer tissues, KRT6B gene expression exceeded that of normal tissues. This study confirms that arecoline induces ROS accumulation in normal cells, leading to the secretion of proinflammatory factors and KRT6 expression. This impedes oral mucosal healing, thereby promoting the progression of oral cancer.

Transdermal delivery of selegiline from alginate-Pluronic composite thermogels.

The present work was carried out to design a practical, controlled-release transdermal system for selegiline using thermosensitive hydrogels. The copolymers of alginate and Pluronic F127 (PF127) were used to design thermogels by either physical blending (A+P) or chemical grafting (AP). The thermogels were characterized in terms of the sol-gel temperature, scanning electron microscopy (SEM), degradation ratio, and skin permeation behavior. The chemical grafting of alginate to PF127 could delay the sol-gel temperature from 24.1 to 30.4°C, which is near the temperature of the skin surface. The gelling temperature of the physical mixture of alginate and PF127 (A+P) did not significantly differ. The porosity of the A+P structure was greater compared to that of the AP structure. AP thermogels were regularly degraded, with 60% of the gel matrix remaining after a 48-h incubation. PF127 and A+P hydrogels showed almost no degradation. The results of skin permeation across porcine skin and nude mouse skin suggested that the thermogels could produce sustained selegiline release, with AP showing the most-sustained permeation. AP hydrogels exhibited linear permeation properties for the transdermal delivery of selegiline. Inter-subject variations in skin permeation were reduced by incorporation of the thermogel. Such a thermosensitive hydrogel can be advantageous as a topical therapeutic formulation for selegiline.

Transdermal permeation of selegiline from hydrogel-membrane drug delivery systems.

In the present work, we attempted to design a transdermal system for delivering selegiline using a hydrogel-based drug reservoir and a rate-controlling membrane (Solupor polyethylene membranes). The appearances of these preparations were evaluated by scanning electron microscopy (SEM), and the in vitro skin permeation of selegiline across porcine skin was examined. Both the R- and S-forms of selegiline were examined in this study to elucidate the stereoselectivity of skin to selegiline. Solupor membranes and hydrogels exhibited a cross-linking structure with micropores. R-Selegiline revealed a flux of 1.13 microg/cm(2)/h across porcine skin. Solupor membranes were rate limiting for skin permeation of selegiline. Around a 2-fold reduction in the drug flux was determined after Solupor membrane incorporation. There were no significant differences in drug flux across the four Solupor membranes tested. The flux of R-selegiline from cellulose hydrogels approximated that from the aqueous solution (control). Both the membrane and hydrogel greatly reduced the inter-subject variations in skin permeation. According to the results of skin permeation and the partition coefficient between the skin and water (logP(skin/water)), the S-enantiomer may be preferable for permeation into the skin. However, the R- and S-forms demonstrated equal absorption of the drug fluxed in the presence of the membrane and/or the hydrogel. The results of this study encouraged us to further investigate hydrogel-membrane delivery systems for transdermal selegiline administration.