ERGPNet: lesion segmentation network for COVID-19 chest X-ray images based on embedded residual convolution and global perception.

The Segmentation of infected areas from COVID-19 chest X-ray (CXR) images is of great significance for the diagnosis and treatment of patients. However, accurately and effectively segmenting infected areas of CXR images is still challenging due to the inherent ambiguity of CXR images and the cross-scale variations in infected regions. To address these issues, this article proposes a ERGPNet based on embedded residuals and global perception, to segment lesion regions in COVID-19 CXR images. First, aiming at the inherent fuzziness of CXR images, an embedded residual convolution structure is proposed to enhance the ability of internal feature extraction. Second, a global information perception module is constructed to guide the network in generating long-distance information flow, alleviating the interferences of cross-scale variations on the algorithm's discrimination ability. Finally, the network's sensitivity to target regions is improved, and the interference of noise information is suppressed through the utilization of parallel spatial and serial channel attention modules. The interactions between each module fully establish the mapping relationship between feature representation and information decision-making and improve the accuracy of lesion segmentation. Extensive experiments on three datasets of COVID-19 CXR images, and the results demonstrate that the proposed method outperforms other state-of-the-art segmentation methods of CXR images.

Ultrasmall calcium-enriched Prussian blue nanozymes promote chronic wound healing by remodeling the wound microenvironment.

Chronic wound healing remains challenging due to the oxidative microenvironment. Prussian blue (PB) nanoparticles exhibiting multiple antioxidant enzyme-like activities have attracted widespread attention, while their antioxidant efficacy remains unsatisfied. Herein, ultrasmall calcium-enriched Prussian blue nanoparticles (CaPB NPs) are simply constructed with high yields for the wound repair application. Owing to the ultrasmall size and synergistic effect of the generated dual active sites, the CaPB NPs exhibit prominent antioxidase-like activities, protecting cells from oxidative stress-induced damage. In addition to the effect of Ca on regulating keratinocyte and fibroblast growth, it has been demonstrated that the administration of CaPB NPs obviously promoted wound closure as well as collagen deposition and neovascularization in the full-thickness wound defect model in mice. Importantly, the CaPB NP treatment can effectively up-regulate the expression levels of anti-inflammatory cytokines and vascular endothelial growth factors to remodel the wound microenvironment, thereby accelerating the wound healing process. Overall, this work reveals that metal atom substitution is an effective strategy to construct ultrasmall and high-catalytic-performance PB-based nanozymes and further potentiate their effectiveness for chronic wound management.

MHAU-Net: Skin Lesion Segmentation Based on Multi-Scale Hybrid Residual Attention Network.

Melanoma is a main factor that leads to skin cancer, and early diagnosis and treatment can significantly reduce the mortality of patients. Skin lesion boundary segmentation is a key to accurately localizing a lesion in dermoscopic images. However, the irregular shape and size of the lesions and the blurred boundary of the lesions pose significant challenges for researchers. In recent years, pixel-level semantic segmentation strategies based on convolutional neural networks have been widely used, but many methods still suffer from the inaccurate segmentation of fuzzy boundaries. In this paper, we proposed a multi-scale hybrid attentional convolutional neural network (MHAU-Net) for the precise localization and segmentation of skin lesions. MHAU-Net has four main components: multi-scale resolution input, hybrid residual attention (HRA), dilated convolution, and atrous spatial pyramid pooling. Multi-scale resolution inputs provide richer visual information, and HRA solves the problem of blurred boundaries and enhances the segmentation results. The Dice, mIoU, average specificity, and sensitivity on the ISIC2018 task 1 validation set were 93.69%, 90.02%, 92.7% and 93.9%, respectively. The segmentation metrics are significantly better than the latest DCSAU-Net, UNeXt, and U-Net, and excellent segmentation results are achieved on different datasets. We performed model robustness validations on the Kvasir-SEG dataset with an overall sensitivity and average specificity of 95.91% and 96.28%, respectively.

EIEN: Endoscopic Image Enhancement Network Based on Retinex Theory.

In recent years, deep convolutional neural network (CNN)-based image enhancement has shown outstanding performance. However, due to the problems of uneven illumination and low contrast existing in endoscopic images, the implementation of medical endoscopic image enhancement using CNN is still an exploratory and challenging task. An endoscopic image enhancement network (EIEN) based on the Retinex theory is proposed in this paper to solve these problems. The structure consists of three parts: decomposition network, illumination correction network, and reflection component enhancement algorithm. First, the decomposition network model of pre-trained Retinex-Net is retrained on the endoscopic image dataset, and then the images are decomposed into illumination and reflection components by this decomposition network. Second, the illumination components are corrected by the proposed self-attention guided multi-scale pyramid structure. The pyramid structure is used to capture the multi-scale information of the image. The self-attention mechanism is based on the imaging nature of the endoscopic image, and the inverse image of the illumination component is fused with the features of the green and blue channels of the image to be enhanced to generate a weight map that reassigns weights to the spatial dimension of the feature map, to avoid the loss of details in the process of multi-scale feature fusion and image reconstruction by the network. The reflection component enhancement is achieved by sub-channel stretching and weighted fusion, which is used to enhance the vascular information and image contrast. Finally, the enhanced illumination and reflection components are multiplied to obtain the reconstructed image. We compare the results of the proposed method with six other methods on a test set. The experimental results show that EIEN enhances the brightness and contrast of endoscopic images and highlights vascular and tissue information. At the same time, the method in this paper obtained the best results in terms of visual perception and objective evaluation.

PRAPNet: A Parallel Residual Atrous Pyramid Network for Polyp Segmentation.

In a colonoscopy, accurate computer-aided polyp detection and segmentation can help endoscopists to remove abnormal tissue. This reduces the chance of polyps developing into cancer, which is of great importance. In this paper, we propose a neural network (parallel residual atrous pyramid network or PRAPNet) based on a parallel residual atrous pyramid module for the segmentation of intestinal polyp detection. We made full use of the global contextual information of the different regions by the proposed parallel residual atrous pyramid module. The experimental results showed that our proposed global prior module could effectively achieve better segmentation results in the intestinal polyp segmentation task compared with the previously published results. The mean intersection over union and dice coefficient of the model in the Kvasir-SEG dataset were 90.4% and 94.2%, respectively. The experimental results outperformed the scores achieved by the seven classical segmentation network models (U-Net, U-Net++, ResUNet++, praNet, CaraNet, SFFormer-L, TransFuse-L).

Evaluation and optimization of analytical procedure and sample preparation for polar Streptomyces albus J1074 metabolome profiling.

Metabolomics is an essential discipline in omics technology that promotes research on the biology of microbial systems. Streptomyces albus J1074 is a model organism used in fundamental research and industrial microbiology. Nevertheless, a comprehensive and standardized method for analyzing the metabolome of S. albus J1074 is yet to be developed. Thus, we comprehensively evaluated and optimized the analytical procedure and sample preparation for profiling polar metabolites using hydrophilic interaction liquid chromatography (HILIC) coupled with high-resolution mass spectrometry (HRMS). We systematically examined the HILIC columns, quenching solutions, sample-to-quenching ratios, and extraction methods. Then, the optimal protocol was used to investigate the dynamic intracellular polar metabolite profile of the engineered S. albus J1074 strains during spinosad (spinosyn A and spinosyn D) fermentation. A total of 3648 compounds were detected, and 83 metabolites were matched to the standards. The intracellular metabolomic profiles of engineered S. albus J1074 strains (ADE-AP and OE3) were detected; furthermore, their metabolomes in different stages were analyzed to reveal the reasons for their differences in their spinosad production, as well as the current metabolic limitation of heterologous spinosad production in S. albus J1074. The HILIC-HRMS method is a valuable tool for investigating polar metabolomes, and provides a reference methodology to study other Streptomyces metabolomes.

Increasing the heterologous production of spinosad in Streptomyces albus J1074 by regulating biosynthesis of its polyketide skeleton.

Spinosyns are natural broad-spectrum biological insecticides with a double glycosylated polyketide structure that are produced by aerobic fermentation of the actinomycete, Saccharopolyspora spinosa. However, their large-scale overproduction is hindered by poorly understood bottlenecks in optimizing the original strain, and poor adaptability of the heterologous strain to the production of spinosyn. In this study, we genetically engineered heterologous spinosyn-producer Streptomyces albus J1074 and optimized the fermentation to improve the production of spinosad (spinosyn A and spinosyn D) based on our previous work. We systematically investigated the result of overexpressing polyketide synthase genes (spnA, B, C, D, E) using a constitutive promoter on the spinosad titer in S. albus J1074. The supply of polyketide synthase precursors was then increased to further improve spinosad production. Finally, increasing or replacing the carbon source of the culture medium resulted in a final spinosad titer of ∼70 mg/L, which is the highest titer of spinosad achieved in heterologous Streptomyces species. This research provides useful strategies for efficient heterologous production of natural products.

Genomics-driven discovery of the biosynthetic gene cluster of maduramicin and its overproduction in Actinomadura sp. J1-007.

Maduramicin is the most efficient and possesses the largest market share of all anti-coccidiosis polyether antibiotics (ionophore); however, its biosynthetic gene cluster (BGC) has yet to been identified, and the associated strains have not been genetically engineered. Herein, we performed whole-genome sequencing of a maduramicin-producing industrial strain of Actinomadura sp. J1-007 and identified its BGC. Additionally, we analyzed the identified BGCs in silico to predict the biosynthetic pathway of maduramicin. We then developed a conjugation method for the non-spore-forming Actinomadura sp. J1-007, consisting of a site-specific integration method for gene overexpression. The maduramicin titer increased by 30% to 7.16 g/L in shake-flask fermentation following overexpression of type II thioesterase MadTE that is the highest titer at present. Our findings provide insights into the biosynthetic mechanism of polyethers and provide a platform for the metabolic engineering of maduramicin-producing microorganisms for overproduction and development of maduramicin analogs in the future.