Multi-Class Wound Classification via High and Low-Frequency Guidance Network.

Wound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfortunately, it is still challenging to classify multiple wound types due to the complexity and variety of wound images. Existing CNNs usually extract high- and low-frequency features at the same convolutional layer, which inevitably causes information loss and further affects the accuracy of classification. To this end, we propose a novel High and Low-frequency Guidance Network (HLG-Net) for multi-class wound classification. To be specific, HLG-Net contains two branches: High-Frequency Network (HF-Net) and Low-Frequency Network (LF-Net). We employ pre-trained models ResNet and Res2Net as the feature backbone of the HF-Net, which makes the network capture the high-frequency details and texture information of wound images. To extract much low-frequency information, we utilize a Multi-Stream Dilation Convolution Residual Block (MSDCRB) as the backbone of the LF-Net. Moreover, a fusion module is proposed to fully explore informative features at the end of these two separate feature extraction branches, and obtain the final classification result. Extensive experiments demonstrate that HLG-Net can achieve maximum accuracy of 98.00%, 92.11%, and 82.61% in two-class, three-class, and four-class wound image classifications, respectively, which outperforms the previous state-of-the-art methods.

Toward Earth system modeling with resolved clouds and ocean submesoscales on heterogeneous many-core HPCs.

With the aid of the newly developed 'Sunway' heterogeneous-architecture supercomputer, which has world-leading HPC (high-performance computer) capability, a series of high-resolution coupled Earth system models (SW-HRESMs) with up to 5 km of atmosphere and 3 km of ocean have been developed. These models can meet the needs of multiscale interaction studies with different computational costs. Here we describe the progress of SW-HRESMs development, with an overview of the major advancements made by the international Earth science community in HR-ESMs. We also show the preliminary results of SW-HRESMs with regard to capturing major weather-climate extremes in the atmosphere and ocean, stressing the importance of permitted clouds and ocean submesoscale eddies in modeling tropical cyclones and eddy-mean flow interactions, and paving the way for further model development to resolve finer scales with even higher resolution and more realistic physics. Finally, in addition to increasing model resolution, the development procedure for a non-hydrostatic cloud and ocean submesoscale resolved ESM is discussed, laying out the major scientific directions of such a huge modeling advancement.

Substantial short- and long-term health effect due to PM2.5 and the constituents even under future emission reductions in China.

Heavy pollution events of fine particulate matter (PM2.5) frequently occur in China, seriously affecting the human health. However, how meteorological factors and anthropogenic emissions affect PM2.5 and the major constituents, as well as the subsequent health effect, remains unclear. Here, based on regional climate and air quality models Weather Research and Forecasting (WRF) and Community Multiscale Air Quality (CMAQ), the PM2.5 and major constituents in China at present and mid-century under the carbon neutral scenario Shared Socioeconomic Pathways (SSP)1-2.6 are simulated. Due to anthropogenic emission reduction, concentrations of PM2.5 and the constituents decrease substantially in SSP1-2.6. The long-term exposure premature deaths at present are 2.23 million per year in mainland China, which is projected to increase by 76 % under SSP1-2.6 despite emission reduction, primarily attributable to aging which strikingly offsets the effect of air quality improvement. The number of annual premature deaths resulting from short-term exposure is 228,104 in mainland China at present, which is projected to decrease in the future. Using North China Plain as an example, we identify that among the major constituents of PM2.5, organic carbon leads to the most short-term exposure deaths considering the largest exposure-response coefficient. Regarding the abnormally meteorological conditions, we find, relative to low relative humidity (RH) and non-stagnation, the compound events, defined as concurrence of high RH and atmospheric stagnation, exhibit an amplified role inducing larger premature deaths compared to the additive effect of the individual event of high RH and atmospheric stagnation. This nonlinear effect occurs at both present and future, but diminished in future due to emission reductions. Our study highlights the importance of considering both the long- and short-term premature deaths associated with PM2.5 and the constituents, as well as the critical effect of extreme weather events.

Exploring the role and mechanism of gut microbiota in methamphetamine addiction using antibiotic treatment followed by fecal microbiota transplantation.

Recently, the role of the gut microbiota in the context of drug addiction has attracted the attention of researchers; however, the specific effects and underlying mechanisms require further exploration. To accomplish this, C57BL/6 mice were firstly treated with methamphetamine (MA). Conditioned place preference (CPP) behavior changes, gut permeability and function, microglial activation, and inflammatory cytokine expression were systematically analyzed in antibiotics-treated mice with microbiota depletion and in fecal microbiota transplantation mice with microbiota reconstitution. MA treatment altered microbiota composition and caused gut dysbiosis. Depletion of gut microbiota with antibiotics inhibited MA-induced CPP formation, and fecal microbiota transplantation reversed this inhibition. Mechanistic analyses indicated that antibiotic treatment decreased gut permeability and neuroinflammation, while fecal microbiota transplantation offset the impact of antibiotic treatment. Additionally, MA-induced microglial activation was suppressed by antibiotics but restored by microbiota transplantation, and this correlated well with the CPP score. Compared to antibiotic treatment, microbiota transplantation significantly increased 5-HT4 receptor expression in both the nucleus accumbens and the hippocampus. Furthermore, when fecal microbiota from healthy mice was transplanted into MA-treated mice, the CPP scores decreased. Our results provide a novel avenue for understanding MA addiction and suggest a potential future intervention strategy.

Threat by marine heatwaves to adaptive large marine ecosystems in an eddy-resolving model.

Marine heatwaves (MHWs), episodic periods of abnormally high sea surface temperature (SST), severely affect marine ecosystems. Large Marine Ecosystems (LMEs) cover ~22% of the global ocean but account for 95% of global fisheries catches. Yet how climate change affects MHWs over LMEs remains unknown, because such LMEs are confined to the coast where low-resolution climate models are known to have biases. Here, using a high-resolution Earth system model and applying a "future threshold" that considers MHWs as anomalous warming above the long-term mean warming of SSTs, we find that future intensity and annual days of MHWs over majority of the LMEs remain higher than in the present-day climate. Better resolution of ocean mesoscale eddies enables simulation of more realistic MHWs than low-resolution models. These increases in MHWs under global warming poses a serious threat to LMEs, even if resident organisms could adapt fully to the long-term mean warming.

The enhanced role of atmospheric reduced nitrogen deposition in future over East Asia-Northwest Pacific.

The atmospheric nitrogen deposition plays a crucial role in natural ecosystem, and the changes in emissions substantially affect the amount of nitrogen deposition. Along with the decrease in NOx emissions and increase in NH3 emissions, the reduced nitrogen deposition may play a more important role in future. However, to what extent these changes may modify the reduced nitrogen deposition across East Asia, which is fulfilled with a large amount of nitrogen deposition, to the northwestern Pacific has not yet to be clear. Based on the results of multi-model ensemble of Atmospheric Chemistry and Climate Model Intercomparison Project (ACCMIP), the future changes of reduced nitrogen (NHx) deposition is firstly examined. Here we show the changes of NHx deposition flux is substantially modulated by both climate change and emissions, exhibiting an increasing trend over East Asia-Northwest Pacific in future under representative concentration pathways (RCP) 8.5 scenario, largely controlled by increase of NH3 emissions, contrasting to the oxidized nitrogen deposition which is projected to decrease. Specifically, the ratio of NHx to total nitrogen deposition in eastern China increases from 38% at present to 56% by the end of the century under RCP 8.5, indicative of a transition in the form of dominant nitrogen deposition from oxidized to reduced one. The increase is clearly discernable over the marginal seas and northwestern Pacific. Moreover, we identify a meridional shift of high wet NHx deposition from northern China in summer to southern China in the other seasons. Based on simulations from regional models Weather Research and Forecasting (WRF) and Community Multi-scale Air Quality (CMAQ), we find that the synergistically nonlinear modulation of NHx concentration and precipitation triggers the north-south shift of wet NHx deposition. The findings in this study indicate a potentially more important role of reduced nitrogen deposition on the natural ecosystem in future.