Tongue Image Texture Classification Based on Image Inpainting and Convolutional Neural Network.

Tongue texture analysis is of importance to inspection diagnosis in traditional Chinese medicine (TCM), which has great application and irreplaceable value. The tough and tender classification for tongue image relies mainly on image texture of tongue body. However, texture discontinuity adversely affects the classification of the tough and tender tongue classification. In order to promote the accuracy and robustness of tongue texture analysis, a novel tongue image texture classification method based on image inpainting and convolutional neural network is proposed. Firstly, Gaussian mixture model is applied to separate the tongue coating and body. In order to exclude the interference of tongue coating on tough and tender tongue classification, a tongue body image inpainting model is built based on generative image inpainting with contextual attention to realize the inpainting of the tongue body image to ensure the continuity of texture and color change of tongue body image. Finally, the classification model of the tough and tender tongue inpainting image based on ResNet101 residual network is used to train and test. The experimental results show that the proposed method achieves better classification results compared with the existing methods of texture classification of tongue image and provides a new idea for tough and tender tongue classification.

Development of Molecularly Imprinted Polymers for Fenthion Detection in Food and Soil Samples.

Modern agricultural production is greatly dependent on pesticide usage, which results in severe environmental pollution, health risks and degraded food quality and safety. Molecularly imprinted polymers are one of the most prominent approaches for the detection of pesticide residues in food and environmental samples. In this research, we prepared molecularly imprinted polymers for fenthion detection by using beta-cyclodextrin as a functional monomer and a room-temperature ionic liquid as a cosolvent. The characterization of the developed polymers was carried out. The polymers synthesized by using the room-temperature ionic liquid as the cosolvent had a good adsorption efficiency of 26.85 mg g-1, with a short adsorption equilibrium time of 20 min, and the results fitted well with the Langmuir isotherm model and pseudo-second-order kinetic model. The polymer showed cross-selectivity for methyl-parathion, but it had a higher selectivity as compared to acetamiprid and abamectin. A recovery of 87.44-101.25% with a limit of detection of 0.04 mg L-1 and a relative standard deviation of below 3% was achieved from soil, lettuce and grape samples, within the linear range of 0.02-3.0 mg L-1, using high-performance liquid chromatography with an ultraviolet detector. Based on the results, we propose a new, convenient and practical analytical method for fenthion detection in real samples using improved imprinted polymers with room-temperature ionic liquid.

Room-Temperature, Ionic-Liquid-Enhanced, Beta-Cyclodextrin-Based, Molecularly Imprinted Polymers for the Selective Extraction of Abamectin.

To ensure environmental protection and food quality and safety, the trace level detection of pesticide residues with molecularly imprinted polymers using a more economic, reliable, and greener approach is always demanded. Herein, novel, enhanced, imprinted polymers based on beta-cyclodextrin, using room-temperature, ionic liquid as a solvent for abamectin were developed with a simple polymerization process. The successful synthesis of the polymers was verified, with morphological and structural characterization performed via scanning electron microscope analysis, nitrogen adsorption experiments, and thermogravimetric analysis. The imprinted polymers showed good adsorption ability, which was confirmed with a pseudo-second-order kinetic model and a Langmuir isotherm model, as they exhibit a theoretical adsorption of 15.08 mg g-1 for abamectin. The polymers showed high selectivity for abamectin and significant reusability without significant performance loss. The MIPs were used to analyze abamectin in spiked apple, banana, orange, and grape samples, and as a result, a good recovery of 81.67-101.47%, with 1.26-4.36% relative standard deviation, and limits of detection and quantitation of 0.02 µg g-1 and 0.05 µg g-1, respectively, was achieved within a linear range of 0.03-1.50 µg g-1. Thus, room-temperature, ionic-liquid-enhanced, beta-cyclodextrin-based, molecularly imprinted polymers for the selective detection of abamectin proved to be a convenient and practical platform.

Convergence, Consilience, and the Evolution of Temperate Deciduous Forests.

The deciduous habit of northern temperate trees and shrubs provides one of the most obvious examples of convergent evolution, but how did it evolve? Hypotheses based on the fossil record posit that deciduousness evolved first in response to drought or darkness and preadapted certain lineages as cold climates spread. An alternative is that evergreens first established in freezing environments and later evolved the deciduous habit. We monitored phenological patterns of 20 species of Viburnum spanning tropical, lucidophyllous (subtropical montane and warm temperate), and cool temperate Asian forests. In lucidophyllous forests, all viburnums were evergreen plants that exhibited coordinated leaf flushes with the onset of the rainy season but varied greatly in the timing of leaf senescence. In contrast, deciduous species exhibited tight coordination of both flushing and senescence, and we found a perfect correlation between the deciduous habit and prolonged annual freezing. In contrast to previous stepwise hypotheses, a consilience of independent lines of evidence supports a lockstep model in which deciduousness evolved in situ, in parallel, and concurrent with a gradual cooling climate. A pervasive selective force combined with the elevated evolutionary accessibility of a particular response may explain the massive convergence of adaptive strategies that characterizes the world's biomes.

Pre-bent elastic stable intramedullary nail fixation for distal radial shaft fractures in children.

OBJECTIVE: To investigate the functional and radiographic outcomes of pre-bent elastic stable intramedullary nail in treatment of distal radial shaft fractures in children. METHODS: From January 2006 to December 2008, 18 children with distal radial shaft fracture were treated by close reduction and internal fixation with a pre-bent elastic stable intramedullary nail. The age range was from 5 years to 15 years, with an average of 9 years and 8 months. The minimum follow-up was 12 months. RESULTS: All fractures maintained good alignment postoperatively, and 94.4% (17/18) of the patients regained a full range of rotation of the forearm. One patient has limitation of rotation to less than 10°, this had improved by final follow-up. Complications included soft tissue irritation at the site of nail insertion in one patient and transient scar hypersensitivity in another. CONCLUSION: Fixation with a pre-bent elastic stable intramedullary nail is an effective, safe and convenient method for treating distal radial shaft fractures in children.