Search

Skin disease cases are rising in prevalence, and the diagnosis of skin diseases is always a challenging task in the clinic. Utilizing deep learning to diagnose skin diseases could help to meet these challenges. In this study, a novel neural network is proposed for the classification of skin diseases. Since the datasets for the research consist of skin disease images and clinical metadata, we propose a novel multimodal Transformer, which consists of two encoders for both images and metadata and one decoder to fuse the multimodal information. In the proposed network, a suitable Vision Transformer (ViT) model is utilized as the backbone to extract image deep features. As for metadata, they are regarded as labels and a new Soft Label Encoder (SLE) is designed to embed them. Furthermore, in the decoder part, a novel Mutual Attention (MA) block is proposed to better fuse image features and metadata features. To evaluate the model's effectiveness, extensive experiments have been conducted on the private skin disease dataset and the benchmark dataset ISIC 2018. Compared with state-of-the-art methods, the proposed model shows better performance and represents an advancement in skin disease diagnosis.

The continuous development and wide application of CT in medical practice have raised public concern over the associated radiation dose to the patient. However, reducing the radiation dose may result in increasing the noise and artifacts, which may adversely interfere with the judgment and belief of radiologists. Therefore, we propose a low-dose CT denoising model based on multiscale parallel convolution neural network to improve the visual effect. Residual learning is utilized to reduce the difficulty of network learning, and batch normalization is adopted to solve the problem of performance degradation due to the increase in neural network layers. Specifically, we introduce the dilated convolution to expand the receptive field by inserting weights of zero in the standard convolution kernel, while not increasing the extra parameters. Furthermore, the multiscale parallel method is utilized to extract multiscale detail features from lung images. Compared to the traditional methods such as Wiener filter, NLM, and models based on CNN, e.g., SCNN, DnCNN, our extensive experimental results demonstrate that our proposed model (CT-ReCNN) can not only reduce the LDCT lung images noise level, but also retain more exact information as well.

Extremophiles exist among all three domains of life; however, physiological mechanisms for surviving harsh environmental conditions differ among Bacteria, Archaea and Eukarya. Consequently, we expect that domain-specific variation of diversity and community assembly patterns exist along environmental gradients in extreme environments. We investigated inter-domain community compositional differences along a high-elevation salinity gradient in the McMurdo Dry Valleys, Antarctica. Conductivity for 24 soil samples collected along the gradient ranged widely from 50 to 8355 µS cm

Due to the problems of occlusion, pose change, illumination change, and image blur in the wild facial expression dataset, it is a challenging computer vision problem to recognize facial expressions in a complex environment. To solve this problem, this paper proposes a deep neural network called facial expression recognition based on graph convolution network (FERGCN), which can effectively extract expression information from the face in a complex environment. The proposed FERGCN includes three essential parts. First, a feature extraction module is designed to obtain the global feature vectors from convolutional neural networks branch with triplet attention and the local feature vectors from key point-guided attention branch. Then, the proposed graph convolutional network uses the correlation between global features and local features to enhance the expression information of the non-occluded part, based on the topology graph of key points. Furthermore, the graph-matching module uses the similarity between images to enhance the network's ability to distinguish different expressions. Results on public datasets show that our FERGCN can effectively recognize facial expressions in real environment, with RAF-DB of 88.23%, SFEW of 56.15% and AffectNet of 62.03%.

Chest X-ray (CXR) is a medical imaging technology that is common and economical to use in clinical. Recently, coronavirus (COVID-19) has spread worldwide, and the second wave is rebounding strongly now with the coming winter that has a detrimental effect on the global economy and health. To make pre-diagnosis of COVID-19 as soon as possible, and reduce the work pressure of medical staff, making use of deep learning networks to detect positive CXR images of infected patients is a critical step. However, there are complex edge structures and rich texture details in the CXR images susceptible to noise that can interfere with the diagnosis of the machines and the doctors. Therefore, in this paper, we proposed a novel multi-resolution parallel residual CNN (named MPR-CNN) for CXR images denoising and special application for COVID-19 which can improve the image quality. The core of MPR-CNN consists of several essential modules. (a) Multi-resolution parallel convolution streams are utilized for extracting more reliable spatial and semantic information in multi-scale features. (b) Efficient channel and spatial attention can let the network focus more on texture details in CXR images with fewer parameters. (c) The adaptive multi-resolution feature fusion method based on attention is utilized to improve the expression of the network. On the whole, MPR-CNN can simultaneously retain spatial information in the shallow layers with high resolution and semantic information in the deep layers with low resolution. Comprehensive experiments demonstrate that our MPR-CNN can better retain the texture structure details in CXR images. Additionally, extensive experiments show that our MPR-CNN has a positive impact on CXR images classification and detection of COVID-19 cases from denoised CXR images.

The isolated tributary hypothesis (ITH) states that headwater tributaries are insular habitats, and therefore, populations in tributaries will have low genetic connectivity. We compared gen...

The publication of this article unfortunately contained mistakes. The photos of Xiaoben Jiang and Yu Yao were exchanged. The corrected assignment is given below.

In the nonlocal total variation (NLTV) model the constant regularization parameter λ cannot adaptively control the balance between the regularization term and the fidelity term, which may results in over-smoothing and the more losing image details in non-flat areas when λ is small, or insufficient noise removal in flat areas when λ is large. It is better that λ has different values according to the characteristics of image areas. In this paper, we introduce an adaptive regularization parameter λ(x) which can recognize flat areas and non-flat areas of an image and propose an improved NLTV model by replacing regularization parameter λ in NLTV model with the function λ(x). In addition, we calculate the similarity weight function of our model from the pre-filtered image to reduce the influence of noise on it. Experimental results demonstrate our approach outperforms some existing methods in terms of objective criteria and subjective visual perception.

The pH of the majority of thermal springs in Yellowstone National Park (YNP) is from 1 to 3 and 6 to 10; relatively few springs (~5%) have a pH range of 4–5. We used 16S rRNA gene pyrosequencing to investigate microbial communities sampled from four pH 4 thermal springs collected from four regions of YNP that differed in their fluid temperature and geochemistry. Our results revealed that the composition of bacterial communities varied among the sites, despite sharing similar pH values. The taxonomic composition and metabolic functional potential of the site with the lowest temperature (55 °C), a thermal spring from the Seven Mile Hole (SMH) area, were further investigated using shotgun metagenome sequencing. The taxonomic classification, based on 372 Mbp of unassembled metagenomic reads, indicated that this community included a high proportion of Chloroflexi, Bacteroidetes, Proteobacteria, and Firmicutes. Functional comparison with other YNP thermal spring metagenomes indicated that the SMH metagenome was enriched in genes related to energy production and conversion, transcription, and carbohydrate transport. Analysis of genes involved in nitrogen metabolism revealed assimilatory and dissimilatory nitrate reduction pathways, whereas the majority of genes involved in sulfur metabolism were related to the reduction of sulfate to adenylylsulfate, sulfite, and H2S. Given that pH 4 thermal springs are relatively less common in YNP and thermal areas worldwide, they may harbor novel microbiota and the communities that inhabit them deserve further investigation.

Microbial consortia dominate glacial meltwater streams from polar regions, including the McMurdo Dry Valleys (MDV), where they thrive under physiologically stressful conditions. In this study, we examined microbial mat types and sediments found in 12 hydrologically diverse streams to describe the community diversity and composition within and across sites. Sequencing of the 16S rRNA gene from 129 samples revealed ∼24 000 operational taxonomic units (

BACKGROUND: Recombinant DNA technologies have played a pivotal role in the elucidation of structure-function relationships in hemoglobin (Hb) and other globin proteins. Here we describe the development of a plasmid expression system to synthesize recombinant Hbs in Escherichia coli, and we describe a protocol for expressing Hbs with low intrinsic solubilities. Since the alpha- and beta-chain Hbs of different species span a broad range of solubilities, experimental protocols that have been optimized for expressing recombinant human HbA may often prove unsuitable for the recombinant expression of wildtype and mutant Hbs of other species. METHODOLOGY/PRINCIPAL FINDINGS: As a test case for our expression system, we produced recombinant Hbs of the deer mouse (Peromyscus maniculatus), a species that has been the subject of research on mechanisms of Hb adaptation to hypoxia. By experimentally assessing the combined effects of induction temperature, induction time and E. coli expression strain on the solubility of recombinant deer mouse Hbs, we identified combinations of expression conditions that greatly enhanced the yield of recombinant protein and which also increased the efficiency of post-translational modifications. CONCLUSION/SIGNIFICANCE: Our protocol should prove useful for the experimental study of recombinant Hbs in many non-human animals. One of the chief advantages of our protocol is that we can express soluble recombinant Hb without co-expressing molecular chaperones, and without the need for additional reconstitution or heme-incorporation steps. Moreover, our plasmid construct contains a combination of unique restriction sites that allows us to produce recombinant Hbs with different alpha- and beta-chain subunit combinations by means of cassette mutagenesis.