A Multi-Modal Open Object Detection Model for Tomato Leaf Diseases with Strong Generalization Performance Using PDC-VLD.

Precise disease detection is crucial in modern precision agriculture, especially in ensuring the health of tomato crops and enhancing agricultural productivity and product quality. Although most existing disease detection methods have helped growers identify tomato leaf diseases to some extent, these methods typically target fixed categories. When faced with new diseases, extensive and costly manual annotation is required to retrain the dataset. To overcome these limitations, this study proposes a multimodal model PDC-VLD based on the open-vocabulary object detection (OVD) technology within the VLDet framework, which can accurately identify new tomato leaf diseases without manual annotation by using only image-text pairs. First, we developed a progressive visual transformer-convolutional pyramid module (PVT-C) that effectively extracts tomato leaf disease features and optimizes anchor box positioning using the self-supervised learning algorithm DINO, suppressing interference from irrelevant backgrounds. Then, a context feature guided module (CFG) was adopted to address the low adaptability and recognition accuracy of the model in data-scarce environments. To validate the model's effectiveness, we constructed a tomato leaf disease image dataset containing 4 base classes and 2 new categories. Experimental results show that the PDC-VLD model achieved 61.2% on the main evaluation metric mAP novel 50 , and 56.4% on mAP novel 75 , 87.7% on mAP base 50 , 81.0% on mAP all 50 , and 45.5% on average recall, outperforming existing OVD models. Our research provides an innovative solution for efficiently and accurately detecting new diseases, substantially reducing the need for manual annotation, and offering critical technical support and practical reference for agricultural workers.

A High-Precision Identification Method for Maize Leaf Diseases and Pests Based on LFMNet under Complex Backgrounds.

Maize, as one of the most important crops in the world, faces severe challenges from various diseases and pests. The timely and accurate identification of maize leaf diseases and pests is of great significance for ensuring agricultural production. Currently, the identification of maize leaf diseases and pests faces two key challenges: (1) In the actual process of identifying leaf diseases and pests, complex backgrounds can interfere with the identification effect. (2) The subtle features of diseases and pests are difficult to accurately extract. To address these challenges, this study proposes a maize leaf disease and pest identification model called LFMNet. Firstly, the localized multi-scale inverted residual convolutional block (LMSB) is proposed to perform preliminary down-sampling on the image, preserving important feature information for the subsequent extraction of fine disease and pest features in the model structure. Then, the feature localization bottleneck (FLB) is proposed to improve the model's ability to focus on and locate disease and pest characteristics and to reduce interference from complex backgrounds. Subsequently, the multi-hop local-feature fusion architecture (MLFFA) is proposed, which effectively addresses the problem of extracting subtle features by enhancing the extraction and fusion of global and local disease and pest features in images. After training and testing on a dataset containing 19,451 images of maize leaf diseases and pests, the LFMNet model demonstrated excellent performance, with an average identification accuracy of 95.68%, a precision of 95.91%, a recall of 95.78%, and an F1 score of 95.83%. Compared to existing models, it exhibits significant advantages, offering robust technical support for the precise identification of maize diseases and pests.

A comprehensive exploration of hydrogel applications in multi-stage skin wound healing.

Hydrogels, as an emerging biomaterial, have found extensive use in the healing of wounds due to their distinctive physicochemical structure and functional properties. Moreover, hydrogels can be made to match a range of therapeutic requirements for materials used in wound healing through specific functional modifications. This review provides a step-by-step explanation of the processes involved in cutaneous wound healing, including hemostasis, inflammation, proliferation, and reconstitution, along with an investigation of the factors that impact these processes. Furthermore, a thorough analysis is conducted on the various stages of the wound healing process at which functional hydrogels are implemented, including hemostasis, anti-infection measures, encouraging regeneration, scar reduction, and wound monitoring. Next, the latest progress of multifunctional hydrogels for wound healing and the methods to achieve these functions are discussed in depth and categorized for elucidation. Finally, perspectives and challenges associated with the clinical applications of multifunctional hydrogels are discussed.

CRLNet: A Multimodal Peach Detection Network Based on Cooperative Asymptotic Enhancement and the Fusion of Granularity Refinement.

Accurate peach detection is essential for automated agronomic management, such as mechanical peach harvesting. However, ubiquitous occlusion makes identifying peaches from complex backgrounds extremely challenging. In addition, it is difficult to capture fine-grained peach features from a single RGB image, which can suffer from light and noise in scenarios with dense small target clusters and extreme light. To solve these problems, this study proposes a multimodal detector, called CRLNet, based on RGB and depth images. First, YOLOv9 was extended to design a backbone network that can extract RGB and depth features in parallel from an image. Second, to address the problem of information fusion bias, the Rough-Fine Hybrid Attention Fusion Module (RFAM) was designed to combine the advantageous information of different modes while suppressing the hollow noise at the edge of the peach. Finally, a Transformer-based Local-Global Joint Enhancement Module (LGEM) was developed to jointly enhance the local and global features of peaches using information from different modalities in order to enhance the percentage of information about the target peaches and remove the interference of redundant background information. CRLNet was trained on the Peach dataset and evaluated against other state-of-the-art methods; the model achieved an mAP50 of 97.1%. In addition, CRLNet also achieved an mAP50 of 92.4% in generalized experiments, validating its strong generalization capability. These results provide valuable insights for peach and other outdoor fruit multimodal detection.

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet.

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model's performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops.

Benzorhodol derived far-red/near-infrared fluorescent probes for selective and sensitive detection of butyrylcholinesterase activity in living cells and the non-alcoholic fatty liver of zebrafish.

Liver diseases are a growing public health concern and the development of non-alcoholic fatty liver disease (NAFLD) has a significant impact on human metabolism. Butyrylcholinesterase (BChE) is a vital biomarker for NAFLD, making it crucial to monitor BChE activity with high sensitivity and selectivity. In this study, we designed and synthesized a range of benzorhodol-derived far-red/near-infrared fluorescent probes, FRBN-B, NF-SB, and NF-B, for the quantitative detection and imaging of BChE. These probes differed in the size of their conjugated systems and in the number of incorporated cyclopropanecarboxylates, acting as the recognition site for BChE. Comprehensive characterization showed that FRBN-B and NF-SB fluorescence was triggered by BChE-mediated hydrolysis, while an additional cyclopropanecarboxylate in NF-B impeded the fluorescence release. High selectivity towards BChE was observed for FRBN-B and NF-SB, with a detection limit of 7.2 × 10-3 U mL-1 for FRBN-B and 1.9 × 10-3 U mL-1 for NF-SB. The probes were further employed in the evaluation of BChE inhibitor efficacy and imaging of intracellular BChE activity. Additionally, FRBN-B was utilized for imaging the BChE activity level in liver tissues in zebrafish, demonstrating its potential as a diagnostic tool for NAFLD.

Psoralen and Isopsoralen, Two Estrogen-Like Natural Products from Psoraleae Fructus, Induced Cholestasis via Activation of ERK1/2.

With the increasing use of oral contraceptives and estrogen replacement therapy, the incidence of estrogen-induced cholestasis (EC) has tended to rise. Psoralen (P) and isopsoralen (IP) are the major bioactive components in Psoraleae Fructus, and their estrogen-like activities have already been recognized. Recent studies have also reported that ERK1/2 plays a critical role in EC in mice. This study aimed to investigate whether P and IP induce EC and reveal specific mechanisms. It was found that P and IP increased the expression of esr1, cyp19a1b and the levels of E2 and VTG at 80 µM in zebrafish larvae. Exemestane (Exe), an aromatase antagonist, blocked estrogen-like activities of P and IP. At the same time, P and IP induced cholestatic hepatotoxicity in zebrafish larvae with increasing liver fluorescence areas and bile flow inhibition rates. Further mechanistic analysis revealed that P and IP significantly decreased the expression of bile acids (BAs) synthesis genes cyp7a1 and cyp8b1, BAs transport genes abcb11b and slc10a1, and BAs receptor genes nr1h4 and nr0b2a. In addition, P and IP caused EC by increasing the level of phosphorylation of ERK1/2. The ERK1/2 antagonists GDC0994 and Exe both showed significant rescue effects in terms of cholestatic liver injury. In conclusion, we comprehensively studied the specific mechanisms of P- and IP-induced EC and speculated that ERK1/2 may represent an important therapeutic target for EC induced by phytoestrogens.

Antibacterial and antioxidant bifunctional hydrogel based on hyaluronic acid complex MoS2-dithiothreitol nanozyme for treatment of infected wounds.

Wound repair is a complex physiological process that often leads to bacterial infections, which significantly threaten human health. Therefore, developing wound-healing materials that promote healing and prevent bacterial infections is crucial. In this study, the coordination interaction between sulfhydryl groups on dithiothreitol (DTT) and MoS2 nanosheets is investigated to synthesize a MoS2-DTT nanozyme with photothermal properties and an improved free-radical scavenging ability. Double-bond-modified hyaluronic acid is used as a monomer and is cross-linked with a PF127-DA agent. PHMoD is prepared in coordination with MoS2-DTT as the functional component. This hydrogel exhibits antioxidant and antibacterial properties, attributed to the catalytic activity of catalase-like enzymes and photothermal effects. Under the near-infrared (NIR), it exhibits potent antibacterial effects against gram-positive (Staphylococcus aureus) and gram-negative bacteria (Escherichia coli), achieving bactericidal rates of 99.76% and 99.42%, respectively. Furthermore, the hydrogel exhibits remarkable reactive oxygen species scavenging and antioxidant capabilities, effectively countering oxidative stress in L929 cells. Remarkably, in an animal model, wounds treated with the PHMoD(2.0) and NIR laser heal the fastest, sealing completely within 10 days. These results indicate the unique biocompatibility and bifunctionality of the PHMoD, which make it a promising material for wound-healing applications.

Angiotensin-converting enzyme inhibitors provide a protective effect on hypoxia-induced injury in human coronary artery endothelial cells via Nrf2 signaling and PLVAP.

BACKGROUND: Angiotensin-converting enzyme inhibitors (ACEIs) were reported to protect from hypoxia-induced oxidative stress in coronary endothelial cells (CECs) after acute myocardial infarction (AMI). Nrf2 shows a protective effect in hypoxia-induced CECs after AMI. Plasmalemma vesicle-associated protein (PLVAP) plays a pivotal role in angiogenesis after AMI. AIM: To explore the protective effect of ACEIs and the involved mechanisms under hypoxia challenge. METHODS: Human coronary endothelial cells (HCAECs) were used to establish hypoxia-induced oxidative stress injury in vitro. Flow cytometry was used to evaluate the protective effect of ACEI on hypoxia conditions.ET-1, NO, ROS, and VEGF were detected by ELISA. HO-1, Nrf2, and Keap-1, the pivotal member in the Nrf2 signaling pathway, eNOS and PLVAP were detected in HEAECs treated with ACEI by immunofluorescence, qPCR, and western blotting. RESULTS: The hypoxia ACEI or Nrf2 agonist groups showed higher cell viability compared with the hypoxia control group at 24 (61.75±1.16 or 61.23±0.59 vs. 44.24±0.58, both P < 0.05) and 48 h (41.85±1.19 or 59.64±1.13 vs. 22.98±0.25, both P < 0.05). ACEI decreased the levels of ET-1 and ROS under hypoxia challenge at 24 and 48 h (all P < 0.05); ACEI increased the VEGF and NO levels (all P < 0.05). ACEI promoted the expression level of eNOS, HO-1, Nrf2 and PLVAP but inhibited Keap-1 expression at the mRNA and protein levels (all P < 0.05). Blockade of the Nrf2 signaling pathway significantly decreased the expression level of PLVAP. CONCLUSION: ACEI protects hypoxia-treated HEAECs by activating the Nrf2 signaling pathway and upregulating the expression of PLVAP.

A Dynamics-Learning Multirate Estimation Approach for the Feeding Condition Perception of Complex Industry Processes.

In this study, we propose a dynamics-learning multirate estimation approach to perceive the quality-related indices (QRIs) of the feeding solution of a unit process. A quality-related index for estimation is an intermediate technical indicator between a unit process and a proceeding unit process; hence, the estimation problem is formulated as a two-stage estimation problem utilizing the production data of both unit processes. Dynamics-learning bidirectional long short-term memory (BiLSTM) with different inputs for the forward and backward layers is proposed to manage the input data from the different unit processes. In the dynamics-learning BiLSTM, a cycle control gate is added in the memory cell to learn the dynamics of the QRIs, thereby enabling a high-rate estimation under multirate conditions. A Bayesian estimation model is then combined with the dynamics-learning BiLSTM model to manage the process delay. Ablation and comparative experiments are conducted to evaluate the feasibility and effectiveness of the proposed estimation approach. The experimental results illustrate the performance and high-rate estimation ability of the proposed approach.

Efficacy and Mechanism Study of 6S-5-Methyltetrahydrofolate-Calcium Against Telencephalon Infarction Injury in Zebrafish Model of Ischemic Stroke.

Ischemic stroke is a heterogeneous brain injury with complex pathophysiology and it is also a time sensitive neurological injury disease. At present, the treatment options for ischemic stroke are still limited. 6S-5-methyltetrahydrofolate-calcium (MTHF-Ca) is the calcium salt of the predominant form of dietary folate in circulation. MTHF-Ca has potential neuroprotective effect on neurocytes, but whether it can be used for ischemic stroke treatment remains unknown. We established zebrafish ischemic stroke model through photothrombotic method to evaluate the protective effect of MTHF-Ca on the ischemic brain injury of zebrafish. We demonstrated that MTHF-Ca reduced the brain damage by reducing motor dysfunction and neurobehavioral defects of zebrafish with telencephalon infarction injury. MTHF-Ca counteracted oxidative damages after Tel injury by increasing the activities of GSH-Px and SOD and decreasing the content of MDA. RNA-seq and RT-qPCR results showed that MTHF-Ca played a neuroprotective role by alleviating neuroinflammation, inhibiting blood coagulation, and neuronal apoptosis processes. Overall, we have demonstrated that MTHF-Ca has neuroprotective effect in ischemic stroke and can be used as a potential treatment for ischemic stroke.

Sensitive and Direct Analysis of Pseudomonas aeruginosa through Self-Primer-Assisted Chain Extension and CRISPR-Cas12a-Based Color Reaction.

Pseudomonas aeruginosa (P. aeruginosa) is a common opportunistic Gram-negative pathogen that may cause infections to immunocompromised patients. However, sensitive and reliable analysis of P. aeruginosa remains a huge challenge. In this method, target recognition assists the formation of a self-primer and initiates single-stranded chain production. The produced single-stranded DNA chain is identified by CRISPR-Cas12a, and consequently, the trans-cleavage activity of the Cas12a enzyme is activated to parallelly digest Ag+ aptamer sequences that are chelated with silver ions (Ag+). The released Ag+ reacted with 3,3',5,5'-tetramethylbenzidine (TMB) for coloring. Compared with the traditional color developing strategies, which mainly rely on the DNA hybridization, the color developing strategy in this approach exhibits a higher efficiency due to the robust trans-cleavage activity of the Cas12a enzyme. Consequently, the method shows a low limit of detection of a wide detection of 5 orders of magnitudes and a low limit of detection of 21 cfu/mL, holding a promising prospect in early diagnosis of infections. Herein, we develop a sensitive and reliable method for direct and colorimetric detection of P. aeruginosa by integrating self-primer-assisted chain production and CRISPR-Cas12a-based color reaction and believe that the established approach will facilitate the development of bacteria-analyzing sensors.

ABCF1/CXCL12/CXCR4 Enhances Glioblastoma Cell Proliferation, Migration, and Invasion by Activating the PI3K/AKT Signal Pathway.

Glioblastoma (GBM) is the most prevalent and fatal form of brain tumor, which is associated with a poor prognosis. ATP-binding cassette subfamily F member 1 (ABCF1) is an E2 ubiquitin-conjugating enzyme, which is implicated in regulating immune responses and tumorigenesis. Aberrant E3 ubiquitylation has been evidenced in GBM. However, the role of ABCF1 in GBM needs to be further explored. The expression of ABCF1, CXC chemokine ligand 12 (CXCL12), and CXC chemokine receptor 4 (CXCR4) in GBM tissues was examined by the GEPIA tool, real-time PCR and Western blotting. HMC3, U251MG, and LN-229 cells were cultured and transfected with shRNA targeting ABCF1 and ABCF1 plasmids. The proliferative, migrative, and invasive ability of cells was detected. Western blotting was used to detect the levels of phosphorylated phosphatidylinositol 3-kinase (PI3K) and phosphorylated protein kinase B (AKT). We observed that GBM tissues had higher ABCF1, CXCL12, and CXCR4 expression levels. The expression levels of CXCL12 and CXCR4 were enhanced by ABCF1 overexpression, which were significantly reversed by silence of ABCF1 in GBM cells. Silencing ABCF1 or CXCR4 inhibition weakened the capacity of GBM cell growth, migration, and invasion, while ectopic ABCF1 expression or CXCL12 treatment enhanced the cellular function of GBM cells. Furthermore, p-PI3K and p-AKT protein levels were downregulated by ABCF1 knockdown or CXCR4 blockade, which were prompted by ABCF1 overexpression or CXCL12 supplement. The ABCF1-CXCL12-CXCR4 axis was identified as a key player in GBM cell survival and metastasis by activating the PI3K/AKT signaling pathway in GBM cells.

Anti-inflammatory effects of 6S-5-methyltetrahydrofolate-calcium on RAW264.7 cells and zebrafish.

AIM: 6S-5-methyltetrahydrofolate is the predominant form of dietary folate in circulation and is used as a crystalline form of calcium salt (MTHF-Ca). Reports revealed that MTHF-Ca was more safe than folic acid, a synthetic and highly stable version of folate. Folic acid has been reported to have anti-inflammatory effects. The study's objective was to assess the anti-inflammatory effect of MTHF-Ca in vitro and in vivo. MAIN METHODS: In vitro, the ROS production was assessed by H2DCFDA, and nuclear translocation of NF-κB were evaluated by the NF-κB nuclear translocation assay kit. Interleukin-6 (IL-6), interleukin-1ß (IL-1ß), and tumor necrosis factor-alpha (TNF-α) were assessed using ELISA. In vivo, ROS production was assessed by H2DCFDA, neutrophils and macrophages recruitment were evaluated in tail transection-induced and CuSO4-induced zebrafish inflammation models. Expression of inflammation related genes were also investigated based on CuSO4-induced zebrafish inflammation model. KEY FINDINGS: MTHF-Ca treatment decreased LPS-induced ROS production, inhibited nuclear translocation of NF-κB and decreased the levels of IL-6, IL-1ß and TNF-α in RAW264.7 cells. In addition, MTHF-Ca treatment inhibited ROS production, suppressed the recruitment of neutrophils and macrophages, and reduced the expression of inflammation related genes, including jnk, erk, nf-κb, myd88, p65, tnf-α, and il-1b in zebrafish larvae. SIGNIFICANCE: MTHF-Ca may play an anti-inflammatory role by reducing the recruitment of neutrophils and macrophages and keeping the low levels of proinflammatory mediators and cytokines. MTHF-Ca may have a potential role in the treatment of inflammatory diseases.

Efficacy and mechanism study of cordycepin against brain metastases of small cell lung cancer based on zebrafish.

BACKGROUND: Small cell lung cancer (SCLC) is an aggressive tumor with high brain metastasis (BM) potential. There has been no significant progress in the treatment of SCLC for more than 30 years. Cordycepin has shown the therapeutic potential for cancer by modulating multiple cellular signaling pathways. However, the effect and mechanism of cordycepin on anti-SCLC BM remain unknown. PURPOSE: In this study, we focused on the anti-SCLC BM effect of cordycepin in the zebrafish model and its potential mechanism. STUDY DESIGN AND METHODS: A SCLC xenograft model based on zebrafish embryos and in vitro cell migration assay were established. Cordycepin was administrated by soaking and microinjection in the zebrafish model. RNA-seq assay was performed to analyze transcriptomes of different groups. Geno Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment were performed to reveal the underlying mechanism. Real-time qPCR was used to verify the effects of cordycepin on the key genes. RESULTS: Cordycepin showed lower cytotoxicity in vitro compared with cisplatin, anlotinib and etoposide, but showed comparable anti-proliferation and anti-BM effects in zebrafish SCLC xenograft model. Cordycepin showed significant anti-SCLC BM effects when administrated by both soaking and microinjection. RNA-seq demonstrated that cordycepin was involved in vitamin D metabolism, lipid transport, and proteolysis in cellular protein catabolic process pathways in SCLC BM microenvironment in zebrafish, and was involved in regulating the expressions of key genes such as cyp24a1, apoa1a, ctsl. The anti-BM effect of cordycepin in SCLC was mediated by reversing the expression of these genes. CONCLUSION: Our work is the first to describe the mechanism of cordycepin against SCLC BM from the perspective of regulating the brain microenvironment, providing new evidence for the anti-tumor effect of cordycepin.

A turn-on fluorescent probe based on ESIPT and AIEE mechanisms for the detection of butyrylcholinesterase activity in living cells and in non-alcoholic fatty liver of zebrafish.

Butyrylcholinesterase (BChE) and acetylcholinesterase (AChE) are two important cholinesterase enzymes in human metabolism which are closely related to various diseases of the liver. BChE and AChE are difficult to be distinguished due to their similarity in biochemical properties. Therefore, developing BChE-specific probes with high sensitivity and low background reading is desirable for the relevant biological applications. Herein, we reported the design and synthesis of a fluorescent probe HBT-BChE for biological detection and imaging of BChE. The probe is triggered by BChE-mediated hydrolysis, releasing a fluorophore that holds AIEE and ESIPT properties with large Stokes shift (>100 nm), rendering the probe features of low background interference and high sensitivity. The probe can also distinguish BChE from AChE with a low detection limit of 7.540 × 10-4 U/mL. Further in vitro studies have shown the ability of HBT-BChE to detect intracellular BChE activity, as well as to evaluate the efficiency of the BChE inhibitor. More importantly, the in vivo studies of imaging the BChE activity level in liver tissues using zebrafish as the model animal demonstrated the potential of HBT-BChE as a powerful tool for non-alcoholic fatty liver disease.

Evaluation of Cardiovascular Toxicity of Folic Acid and 6S-5-Methyltetrahydrofolate-Calcium in Early Embryonic Development.

Folic acid (FA) is a synthetic and highly stable version of folate, while 6S-5-methyltetrahydrofolate is the predominant form of dietary folate in circulation and is used as a crystalline form of calcium salt (MTHF-Ca). The current study aims to evaluate the toxicity and safety of FA and MTHF-Ca on embryonic development, with a focus on cardiovascular defects. We began to analyze the toxicity of FA and MTHF-Ca in zebrafish from four to seventy-two hours postfertilization and assessed the efficacy of FA and MTHF-Ca in a zebrafish angiogenesis model. We then analyzed the differently expressed genes in in vitro fertilized murine blastocysts cultured with FA and MTHF-Ca. By using gene-expression profiling, we identified a novel gene in mice that encodes an essential eukaryotic translation initiation factor (Eif1ad7). We further applied the morpholino-mediated gene-knockdown approach to explore whether the FA inhibition of this gene (eif1axb in zebrafish) caused cardiac development disorders, which we confirmed with qRT-PCR. We found that FA, but not MTHF-Ca, could inhibit angiogenesis in zebrafish and result in abnormal cardiovascular development, leading to embryonic death owing to the downregulation of eif1axb. MTHF-Ca, however, had no such cardiotoxicity, unlike FA. The current study thereby provides experimental evidence that FA, rather than MTHF-Ca, has cardiovascular toxicity in early embryonic development and suggests that excessive supplementation of FA in perinatal women may be related to the potential risk of cardiovascular disorders, such as congenital heart disease.

Identification of citrus diseases based on AMSR and MF-RANet.

BACKGROUND: As one of the most widely planted fruit trees in southern China, citrus occupies an important position in the agriculture field and forestry economy in China. There are many kinds of citrus diseases. If citrus infected with diseases cannot be controlled in time, it easily seriously affects citrus production and causes large economic losses. Timely monitoring of disease characteristics in the citrus growth process is important for implementing timely control measures. Citrus images are easily disturbed by environmental factors such as dust, low light, clouds or leaf shadows. This makes it easy for some disease spot features in citrus pictures to be obscured. Occluded lesions cannot be effectively extracted and recognized. Second, similar characteristics of different diseases also make it difficult to distinguish the different types of diseases. However, the existing machine vision technology for identifying citrus diseases still has some difficulties in dealing with the above problems. RESULTS: This paper proposes a new citrus disease identification framework. First, a citrus image enhancement algorithm based on the MSR-AMSR algorithm is proposed, which can enhance the image and highlight the disease characteristic information. The AMSR algorithm can also greatly alleviate the interference of clouds and low light on image lesions, making the image features clearer. Second, an MF-RANet network is proposed to recognize citrus disease images. MF-RANet is composed of a main feature frame and a detail feature frame. The main feature frame uses the cross stacking structure of ResNet50 and RAM to extract the main features in the citrus image dataset. RAM is used to extract the attention weight in the feature layer, which enables RAM to give higher weight to disease features. The detailed feature frame path uses AugFPN to extract features from multiple scales and fuse the main feature frame path. AugFPN enables the network to retain more detailed features, so it can effectively distinguish similar features in different diseases. In addition, we use the ELU activation function not only to solve the problem of gradient explosion and gradient disappearance but also to effectively use the negative input of the network. Finally, we use the label smoothing regularization method to prevent overfitting the network in the classification process. Finally, the experimental results show that the highest detection accuracy of the network for Huanglong disease, Corynespora blight of citrus, fat spot macular disease, citrus scab, citrus canker and healthy citrus is 96.77%, 96.22%, 95.96%, 95.93%, 94.04% and 97.55%, respectively. CONCLUSIONS: The citrus disease algorithm based on AMSR and MF-RANet can effectively perform the disease detection function. It has a high recognition rate for different kinds of citrus diseases. With the addition of AMSR preprocessing, RAM, AugFPN, ELU activation function and other structures, the MF-RANet network performance improves.

DS-MENet for the classification of citrus disease.

Affected by various environmental factors, citrus will frequently suffer from diseases during the growth process, which has brought huge obstacles to the development of agriculture. This paper proposes a new method for identifying and classifying citrus diseases. Firstly, this paper designs an image enhancement method based on the MSRCR algorithm and homomorphic filtering algorithm optimized by Laplacian (HFLF-MS) to highlight the disease characteristics of citrus. Secondly, we designed a new neural network DS-MENet based on the DenseNet-121 backbone structure. In DS-MENet, the regular convolution in Dense Block is replaced with depthwise separable convolution, which reduces the network parameters. The ReMish activation function is used to alleviate the neuron death problem caused by the ReLU function and improve the robustness of the model. To further enhance the attention to citrus disease information and the ability to extract feature information, a multi-channel fusion backbone enhancement method (MCF) was designed in this work to process Dense Block. We use the 10-fold cross-validation method to conduct experiments. The average classification accuracy of DS-MENet on the dataset after adding noise can reach 95.02%. This shows that the method has good performance and has certain feasibility for the classification of citrus diseases in real life.

MDAM-DRNet: Dual Channel Residual Network With Multi-Directional Attention Mechanism in Strawberry Leaf Diseases Detection.

The growth of strawberry plants is affected by a variety of strawberry leaf diseases. Yet, due to the complexity of these diseases' spots in terms of color and texture, their manual identification requires much time and energy. Developing a more efficient identification method could be imperative for improving the yield and quality of strawberry crops. To that end, here we proposed a detection framework for strawberry leaf diseases based on a dual-channel residual network with a multi-directional attention mechanism (MDAM-DRNet). (1) In order to fully extract the color features from images of diseased strawberry leaves, this paper constructed a color feature path at the front end of the network. The color feature information in the image was then extracted mainly through a color correlogram. (2) Likewise, to fully extract the texture features from images, a texture feature path at the front end of the network was built; it mainly extracts texture feature information by using an area compensation rotation invariant local binary pattern (ACRI-LBP). (3) To enhance the model's ability to extract detailed features, for the main frame, this paper proposed a multidirectional attention mechanism (MDAM). This MDAM can allocate weights in the horizontal, vertical, and diagonal directions, thereby reducing the loss of feature information. Finally, in order to solve the problems of gradient disappearance in the network, the ELU activation function was used in the main frame. Experiments were then carried out using a database we compiled. According to the results, the highest recognition accuracy by the network used in this paper for six types of strawberry leaf diseases and normal leaves is 95.79%, with an F1 score of 95.77%. This proves the introduced method is effective at detecting strawberry leaf diseases.