RAAWC-UNet: an apple leaf and disease segmentation method based on residual attention and atrous spatial pyramid pooling improved UNet with weight compression loss.

Introduction: Early detection of leaf diseases is necessary to control the spread of plant diseases, and one of the important steps is the segmentation of leaf and disease images. The uneven light and leaf overlap in complex situations make segmentation of leaves and diseases quite difficult. Moreover, the significant differences in ratios of leaf and disease pixels results in a challenge in identifying diseases. Methods: To solve the above issues, the residual attention mechanism combined with atrous spatial pyramid pooling and weight compression loss of UNet is proposed, which is named RAAWC-UNet. Firstly, weights compression loss is a method that introduces a modulation factor in front of the cross-entropy loss, aiming at solving the problem of the imbalance between foreground and background pixels. Secondly, the residual network and the convolutional block attention module are combined to form Res_CBAM. It can accurately localize pixels at the edge of the disease and alleviate the vanishing of gradient and semantic information from downsampling. Finally, in the last layer of downsampling, the atrous spatial pyramid pooling is used instead of two convolutions to solve the problem of insufficient spatial context information. Results: The experimental results show that the proposed RAAWC-UNet increases the intersection over union in leaf and disease segmentation by 1.91% and 5.61%, and the pixel accuracy of disease by 4.65% compared with UNet. Discussion: The effectiveness of the proposed method was further verified by the better results in comparison with deep learning methods with similar network architectures.

Coarse-to-Fine Contrastive Self-Supervised Feature Learning for Land-Cover Classification in SAR Images With Limited Labeled Data.

Contrastive self-supervised learning (CSSL) has achieved promising results in extracting visual features from unlabeled data. Most of the current CSSL methods are used to learn global image features with low-resolution that are not suitable or efficient for pixel-level tasks. In this paper, we propose a coarse-to-fine CSSL framework based on a novel contrasting strategy to address this problem. It consists of two stages, one for encoder pre-training to learn global features and the other for decoder pre-training to derive local features. Firstly, the novel contrasting strategy takes advantage of the spatial structure and semantic meaning of different regions and provides more cues to learn than that relying only on data augmentation. Specifically, a positive pair is built from two nearby patches sampled along the direction of the texture if they fall into the same cluster. A negative pair is generated from different clusters. When the novel contrasting strategy is applied to the coarse-to-fine CSSL framework, global and local features are learned successively by forcing the positive pair close to each other and the negative pair apart in an embedding space. Secondly, a discriminant constraint is incorporated into the per-pixel classification model to maximize the inter-class distance. It makes the classification model more competent at distinguishing between different categories that have similar appearance. Finally, the proposed method is validated on four SAR images for land-cover classification with limited labeled data and substantially improves the experimental results. The effectiveness of the proposed method is demonstrated in pixel-level tasks after comparison with the state-of-the-art methods.

Immunotherapy of Tumor RNA-Loaded Lipid Nanoparticles Against Hepatocellular Carcinoma.

PURPOSE: Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related deaths worldwide. Most current therapeutic strategies primarily include localized treatment, lacking effective systemic strategies. Meanwhile, recent studies have suggested that RNA vaccines can effectively activate antigen-presenting cells (APCs) and lymphocytes to produce a strong systemic immune response and inhibit tumor growth. However, tumor vaccines loaded with a single tumor antigen may induce immunosuppression and immune evasion, while identifying tumor-specific antigens can require expensive and laborious procedures. Therefore, the use of whole tumor cell antigens are currently considered to be promising, potentially effective, methods. Previously, we developed a targeted liposome-polycation-DNA (LPD) complex nanoparticle that possess a small size, high RNA encapsulation efficiency, and superior serum stability. These particles were found to successfully deliver RNA to tumor sites. In the current study, we encapsulated total tumor-derived RNA in lipid nanoparticles (LNPs) to target dendritic cells (DCs) to incite expeditious and robust anti-tumor immunity. METHODS: Total tumor-derived RNA was extracted from liver cancer cells (Hepa1-6 cells). LNPs loaded with tumor RNA were then prepared thin-film hydration method. The ability of RNA LNPs to induce DC maturation, cytotoxicity, and anti-tumor activity, was investigated in vitro and in vivo. RESULTS: The average particle size of LNPs and RNA LNPs was 102.22 ± 4.05 nm and 209.68 ± 6.14 nm, respectively, while the zeta potential was 29.97 ± 0.61 mV and 42.03 ± 0.42 mV, respectively. Both LNPs and RNA LNP vaccines exhibited good distribution and stability. In vitro, RNA LNP vaccines were capable of promoting DC maturation and inducing T lymphocytes to kill Hepa1-6 cells. In vivo, RNA LNP vaccines effectively prevent and inhibit HCC growth. CONCLUSION: RNA LNPs may serve as an effective antigen specific vaccine to induce anti-tumor immunity for HCC.

Analysis of Apoptosis-Related Genes Reveals that Apoptosis Functions in Conidiation and Pathogenesis of Fusarium pseudograminearum.

Apoptosis, a type of programmed cell death, plays crucial roles in various physiological processes, from development to adaptive responses. Key features of apoptosis have been verified in various fungal microbes but not yet in Fusarium species. Here, we identified 19 apoptosis-related genes in Fusarium pseudograminearum using a genome-wide survey. Expression profile analysis revealed that several apoptosis-related genes were significantly increased during conidiation and infection stages. Among these is FpBIR1, with two BIR (baculovirus inhibitor-of-apoptosis protein repeat) domains at the N-terminal end of the protein, a homolog of Saccharomyces cerevisiae BIR1, which is a unique apoptosis inhibitor. FpNUC1 is the ortholog of S. cerevisiae NUC1, which triggers AIF1- or YCA1-independent apoptosis. The functions of these two proteins were assessed by creating Δfpbir1 and Δfpnuc1 mutants via targeted gene deletion. The Δfpbir1 mutant had more cells with nuclear fragmentation and exhibited reduced conidiation, conidial formation, and infectivity. Correspondingly, the Δfpnuc1 mutant contained multiple nuclei, produced thicker and more branched hyphae, was reduced in conidiation, and exhibited faster conidial formation and higher infection rates. Taken together, our results indicate that the apoptosis-related genes FpBIR1 and FpNUC1 function in conidiation, conidial germination, and infection by F. pseudograminearumIMPORTANCE The plant-pathogenic fungus F. pseudograminearum is the causal agent of Fusarium crown rot (FCR) in wheat and barley, resulting in substantial yield losses worldwide. Particularly, in the Huanghuai wheat-growing region of China, F. pseudograminearum was reported as the dominant Fusarium species in FCR infections. Apoptosis is an evolutionarily conserved mechanism in eukaryotes, playing crucial roles in development and cell responses to biotic and abiotic stresses. However, few reports on apoptosis in plant fungal pathogens have been published. In this study, we identified 19 conserved apoptosis-related genes in F. pseudograminearum, several of which were significantly increased during conidiation and infection stages. Potential apoptosis functions were assessed by deletion of the putative apoptosis inhibitor gene FpBIR1 and apoptosis trigger gene FpNUC1 in F. pseudograminearum The FpBIR1 deletion mutant exhibited defects in conidial germination and pathogenicity, whereas the FpNUC1 deletion mutant experienced faster conidial formation and higher infection rates. Apoptosis appears to negatively regulate the conidial germination and pathogenicity of F. pseudograminearum To our knowledge, this study is the first report of apoptosis contributing to infection-related morphogenesis and pathogenesis in F. pseudograminearum.

A High Barrier and Sustained Release Oxygen-Absorbing Ionic Polymer for Food Packaging Applications.

Development and utilization of oxygen absorbing materials for food and beverage packaging are important to protect the oxygen-sensitive foods. In this study, we developed a kind of ionic polymer with excellent oxygen absorbing ability based on reacting ethylene-acrylic acid copolymer (EAA) and sodium sulfite (Na2 SO3 ). By virtue of the hydrophilicity of the ionic polymer, the sulfite in Na2 SO3 is easily hydrolyzed and ionized. The oxygen inhalation reaction was gradually initiated and started, whereas achieved a slow and controllable oxygen absorption process. The oxygen absorbing agent can be directly added in the form of an auxiliary agent, which greatly simplifies the preparation process of the oxygen absorbing material. Furthermore, the ionic structure of the EAA/Na2 SO3 composites were destroyed and mechanical properties of the material did not decrease after oxygen absorption. More importantly, it can effectively prevent the entry of external oxygen because the ionic polymer itself has better barrier properties. PRACTICAL APPLICATION: Typical oxygen-sensitive objects include: beer, coffee, canned food, meat products, dairy products, and so on. The presence of oxygen in the package can cause microbial growth, odor generation, color change and nutrient loss, resulting in a significant reduction in food shelf life. Therefore, controlling the oxygen content of the food package is important to limit the rate of these spoilage and spoilage reactions in the food. Materials with active oxygen scavenging and good barrier properties and packaging performance are highly economically viable in terms of improving product quality and reducing packaging costs.

A Stable Plasmonic Cu@Cu2 O/ZnO Heterojunction for Enhanced Photocatalytic Hydrogen Generation.

The localized surface plasmon resonance (LSPR) effect has been widely utilized in photocatalysis, but most reported LSPR materials are based on noble metals of gold or silver with high chemical stability. Plasmonic copper nanoparticles that exhibit an LSPR absorbance at 600 nm are promising for many applications, such as photocatalysis. Unfortunately, plasmonic copper nanoparticles are affected by serious surface oxidation in air. Herein, a novel lollipop-shaped Cu@Cu2 O/ZnO heterojunction nanostructure was designed, for the first time, to stabilize the plasmonic Cu core by decorating Cu@Cu2 O core-shell structures with ZnO nanorods. This Cu@Cu2 O/ZnO nanostructure exhibited significantly enhanced stability than that of regular Cu@Cu2 O, which accounted for the remarkably enhanced photocatalytic H2 evolution rate through water splitting, relative to pristine ZnO nanorods, over an extended wavelength range due to the plasmonic Cu core.

Strong temperature-dependent crystallization, phase transition, optical and electrical characteristics of p-type CuAlO2 thin films.

We report here a reliable and reproducible single-step (without post-annealing) fabrication of phase-pure p-type rhombohedral CuAlO2 (r-CuAlO2) thin films by reactive magnetron sputtering. The dependence of crystallinity and phase compositions of the films on the growth temperature was investigated, revealing that highly-crystallized r-CuAlO2 thin films could be in situ grown in a narrow temperature window of ∼940 °C. Optical and electrical property studies demonstrate that (i) the films are transparent in the visible light region, and the bandgaps of the films increased to ∼3.86 eV with the improvement of crystallinity; (ii) the conductance increased by four orders of magnitude as the film was evolved from the amorphous-like to crystalline structure. The predominant role of crystallinity in determining CuAlO2 film properties was demonstrated to be due to the heavy anisotropic characteristics of the O 2p-Cu 3d hybridized valence orbitals.