Search

In order to solve the problem of difficult deployment of existing deep learning-based defect detection models in terminal equipment with limited computational capacity, a lightweight steel surface defect testing model LSKA-YOLOv8 was proposed based on the YOLOv8n target detection framework. The model uses KernelWarehouse Conv (KWConv) with lower computational volumes, which significantly reduces the required computational resources. By updating the traditional Feature Pyramid Network (FPN) structure to Bi-directional Feature Pyramid Network (BiFPN), enhance the capture of contextual information and reduce the number of parameters of the model. In addition, the Spatial Pyramid Pooling Fast (SPPF) module was replaced with a more accurate Receptive Field Block (RFB) module, expanding the model’s sensory field and improving characteristic representation. At the same time, the Large Separable Kernel Attention (LSKAttention) module was introduced in the detection head, effectively enhancing the understanding and capture of the target characteristics, thus significantly improving the overall detection performance. Experiments on the NEU-DET dataset showed that the average accuracy of LSKA-YOLO increased by 4.4% on the map@0.5 indicator compared to the benchmark model, while the number of parameters and calculations of the model decreased by 26.7% and 50%, respectively. Provides valuable references and practical applications for deployment of defect detection models on computing-resource-limited terminal devices.

Abstract Chrysosplenium sinicum, a traditional Tibetan medicinal plant, can successfully thrive in low-light environments for long periods of time. To investigate the adaptive evolution of shade plants in low-light environments, we generated a chromosome-scale genome assembly (~320 Mb) for C. sinicum by combining PacBio sequencing and Hi-C technologies. Based on our results, gene families related to photosynthesis and cell respiration greatly expanded and evolved in C. sinicum genome due to intracellular DNA transfer from organelle genome to nuclear genome. Under positive selective pressure, adaptive evolution of light-harvesting complex II (LHCII) component protein CsLhcb1s resulted in the expansion of threonine residues at the phosphorylation site of STN7 kinase, potentially establishing a crucial genomic foundation for enhancing C. sinicum’s adaptability in low-light environments. Through transcriptome and metabolome analysis, we identified chrysosplenol and chrysosplenoside as predominant flavonoid metabolites of C. sinicum and predicted their synthesis pathways. In addition, analysis of alternative splicing (AS) revealed that AS events help regulate state transition and flavonoid biosynthesis. The present study provides new insights into the genomes of shade plants exposed to low-light conditions and adaptive evolution of these genomes; in addition, the results improve our current knowledge on the biosynthetic and regulatory processes of chrysosplenol and chrysosplenoside.

ObjectivesNonselective beta blockers (NSBBs) or endoscopic therapies are currently recommended by guidelines for preventing the first variceal bleed in patients with high-risk varices. However, there is a lack of detailed treatment strategies for patients who are intolerant to both NSBBs and endoscopic approaches. Our study aimed to assess the efficacy and safety of variceal embolization as a primary prophylaxis method in cirrhosis patients who are not suitable candidates for NSBBs or endoscopic treatments.MethodsThe study included 43 cirrhotic patients with high-risk varices who were candidates for primary prophylaxis against variceal bleeding. These patients underwent variceal embolization at the Xijing Hospital between January 2020 and June 2022. The primary endpoint was the occurrence of bleeding from varices, and the secondary endpoints were the recurrence of varices and the emergence of complications.ResultsThe procedure of variceal embolization had a success rate of 93.0% (40 out of 43 patients). Over a 2-year follow-up period, the rate of variceal bleeding was 11.6% (5 out of 43 patients), the recurrence rate of varices was 14.0% (6 out of 43 patients), and the rate of severe complications was limited to 2.3% (1 out of 43 patients).ConclusionVariceal embolization is a viable primary prophylactic intervention for cirrhotic patients who are at risk of variceal bleeding when standard treatments, such as NSBBs or endoscopic therapies, are difficult to perform.

Cotton is a crucial crop in the global textile industry, with major production regions including China, India, and the United States. While smart agricultural mechanization technologies, such as automated irrigation and precision pesticide systems, have improved crop management, weeds remain a significant challenge. These weeds not only compete with cotton for nutrients but can also serve as hosts for diseases, affecting both cotton yield and quality. Existing weed detection models perform poorly in the complex environment of cotton fields, where the visual features of weeds and crops are similar and often overlap, resulting in low detection accuracy. Furthermore, real-time deployment on edge devices is difficult. To address these issues, this study proposes an improved lightweight weed detection model, YOLO-WL, based on the YOLOv8 architecture. The model leverages EfficientNet to reconstruct the backbone, reducing model complexity and enhancing detection speed. To compensate for any performance loss due to backbone simplification, CA (cross-attention) is introduced into the backbone, improving feature sensitivity. Finally, AFPN (Adaptive Feature Pyramid Network) and EMA (efficient multi-scale attention) mechanisms are integrated into the neck to further strengthen feature extraction and improve weed detection accuracy. At the same time, the model maintains a lightweight design suitable for deployment on edge devices. Experiments on the CottonWeedDet12 dataset show that the YOLO-WL model achieved an mAP of 92.30%, reduced the detection time per image by 75% to 1.9 ms, and decreased the number of parameters by 30.3%. After TensorRT optimization, the video inference time was reduced from 23.134 ms to 2.443 ms per frame, enabling real-time detection in practical agricultural environments.

Background: Hepatocellular carcinoma (HCC) is one of the most common malignant tumors in China. Most HCC patients have the complications of chronic liver disease and need overall consideration and whole-course management, including diagnosis, treatment, and follow-up. To develop a reasonable, long-term, and complete management plan, multiple factors need to be considered, including the patient’s general condition, basic liver diseases, tumor stage, tumor biological characteristics, treatment requirements, and economic cost. Summary: To better guide the whole-course management of HCC patients, the Chinese Association of Liver Cancer and the Chinese Medical Doctor Association has gathered multidisciplinary experts and scholars in relevant fields to formulate the “Chinese Expert Consensus on The Whole-Course Management of Hepatocellular Carcinoma (2023).” Key Messages: This expert consensus, based on the current clinical evidence and experience, proposes surgical and nonsurgical HCC management pathways and involves 18 recommendations, including perioperative treatment, systematic treatment combined with local treatment, conversion treatment, special population management, symptomatic support treatment, and follow-up management.

Objectives The efficacy of transjugular intrahepatic portosystemic shunt (TIPS) plus extrahepatic collateral embolisation (TIPS+E) in reducing rebleeding and hepatic encephalopathy (HE) post-TIPS was recently reported in a meta-analysis, but further validation is essential. This study aims to confirm the effectiveness of TIPS+E using real-world data.Methods The multicentre retrospective cohort included 2077 patients with cirrhosis who underwent TIPS±E (TIPS: 631, TIPS+E: 1446) between January 2010 and December 2022. Regression and propensity score matching (PSM) were used to adjust for baseline characteristic differences. After PSM, clinical outcomes, including rebleeding, HE, survival and further decompensation (FDC), were analysed. Baseline data from all patients contributed to the construction of prognostic models.Results After PSM, 1136 matched patients (TIPS+E: TIPS=568:568) were included. TIPS+E demonstrated a significant reduction in rebleeding (HR 0.77; 95% CI 0.59 to 0.99; p=0.04), HE (HR 0.82; 95% CI 0.68 to 0.99; p=0.04) and FDC (HR 0.85; 95% CI 0.73 to 0.99; p=0.04), comparing to TIPS. Significantly, TIPS+E also reduced rebleeding, HE and FDC in subgroup of using 8 mm diameter stents and embolising of gastric varices+spontaneous portosystemic shunts (GV+SPSS). However, there were no differences in overall or subgroup survival analysis. Additionally, the random forest models showed higher accuracy and AUROC comparing to other models. Controlling post-TIPS portal pressure gradient (pPPG) within 7 mm Hg

Due to the existence of cotton weeds in a complex cotton field environment with many different species, dense distribution, partial occlusion, and small target phenomena, the use of the YOLO algorithm is prone to problems such as low detection accuracy, serious misdetection, etc. In this study, we propose a YOLOv8-DMAS model for the detection of cotton weeds in complex environments based on the YOLOv8 detection algorithm. To enhance the ability of the model to capture multi-scale features of different weeds, all the BottleNeck are replaced by the Dilation-wise Residual Module (DWR) in the C2f network, and the Multi-Scale module (MSBlock) is added in the last layer of the backbone. Additionally, a small-target detection layer is added to the head structure to avoid the omission of small-target weed detection, and the Adaptively Spatial Feature Fusion mechanism (ASFF) is used to improve the detection head to solve the spatial inconsistency problem of feature fusion. Finally, the original Non-maximum suppression (NMS) method is replaced with SoftNMS to improve the accuracy under dense weed detection. In comparison to YOLO v8s, the experimental results show that the improved YOLOv8-DMAS improves accuracy, recall, mAP0.5, and mAP0.5:0.95 by 1.7%, 3.8%, 2.1%, and 3.7%, respectively. Furthermore, compared to the mature target detection algorithms YOLOv5s, YOLOv7, and SSD, it improves 4.8%, 4.5%, and 5.9% on mAP0.5:0.95, respectively. The results show that the improved model could accurately detect cotton weeds in complex field environments in real time and provide technical support for intelligent weeding research.

As one of the main factors decreasing current efficiency and product quality, the growth of nodules deserves attention in the copper electrorefining process. Three-dimensional (3D) Finite Element Method models combining tertiary current distribution and fluid flow were established in this study to investigate the details of the growth of columnar nodules, including the electrolyte flow around the nodule and its effects. Compared with an inert nodule, a significant impact of the electrochemical reaction of an active nodule has been observed on the fluid flow, which may be one of the reasons for the formation of small nodule clusters on the cathode. Furthermore, the local current density is not even on the nodule surface under the comprehensive influence of local electrolyte flow, local overvoltage, and the angle with the anode surface. Thus, the head of an active nodule grows faster than the root, and the upper parts grow faster than the lower parts, leading to asymmetric growth of the nodules.

When aiming at the problems such as missed detection or misdetection of recognizing green walnuts in the natural environment directly by using target detection algorithms, a method is proposed based on improved UNet3+ for green walnut image segmentation, which incorporates the channel and spatial attention mechanism CBAM (convolutional block attention module) and cross-entropy loss function (cross-entropy loss) into the UNet3+ network structure, and introduces the five-layer CBAM in the encoder module to construct the improved UNet3+ network model. The model consists of an encoder module (down-sampling), a decoder module (up-sampling) and a full-scale skip connection module, a full-scale feature supervision module, and a classification guidance module. After utilizing data-enhanced approaches to expand the green walnut dataset, the improved UNet3+ model was trained. The experimental findings demonstrate that the improved UNet3+ network model achieves 91.82% average precision, 96.00% recall rate, and 93.70% F1 score in the green walnut segmentation task; the addition of five-layer CBAM boosts the model segmentation precision rate by 3.11 percentage points. The method can precisely and successfully segment green walnuts, which can serve as a guide and research foundation for precisely identifying and localizing green walnuts and finishing the autonomous sorting for intelligent robots.

BackgroundGastric cancer (GC) is one of the most malignant and lethal cancers worldwide. Multiple microRNAs (miRNAs) have been identified as key regulators in the progression of GC. However, the underlying pathogenesis that miRNAs govern GC malignancy remains uncertain. Here, we identified a novel miR-585-5p as a key regulator in GC development.MethodsThe expression of miR-585-5p in the context of GC tissue was detected by in situ hybridization for GC tissue microarray and assessed by H-scoring. The gain- and loss-of-function analyses comprised of Cell Counting Kit-8 assay and Transwell invasion and migration assay. The expression of downstream microphthalmia-associated transcription factor (MITF), cyclic AMP-responsive element-binding protein 1 (CREB1) and mitogen-activated protein kinase 1 (MAPK1) were examined by Immunohistochemistry, quantitative real-time PCR and western blot. The direct regulation between miR-585-5p and MITF/CREB1/MAPK1 were predicted by bioinformatic analysis and screened by luciferase reporter assay. The direct transcriptional activation of CREB1 on MITF was verified by luciferase reporter assay, chromatin immunoprecipitation (ChIP) and electrophoretic mobility shift assays (EMSAs). The interaction between MAPK1 and MITF was confirmed by co-immunoprecipitation (Co-IP) and immunofluorescent double-labelled staining.ResultsMiR-585-5p is progressively downregulated in GC tissues and low miR-585-5p levels were strongly associated with poor clinical outcomes. Further gain- and loss-of-function analyses showed that miR-585-5p possesses strong anti-proliferative and anti-metastatic capacities in GC. Follow-up studies indicated that miR-585-5p targets the downstream molecules CREB1 and MAPK1 to regulate the transcriptional and post-translational regulation of MITF, respectively, thus controlling its expression and cancer-promoting activity. MiR-585-5p directly and negatively regulates MITF together with CREB1 and MAPK1. According to bioinformatic analysis, promotor reporter gene assays, ChIP and EMSAs, CREB1 binds to the promotor region to enhance transcriptional expression of MITF. Co-IP and immunofluorescent double-labelled staining confirmed interaction between MAPK1 and MITF. Protein immunoprecipitation revealed that MAPK1 enhances MITF activity via phosphorylation (Ser73). MiR-585-5p can not only inhibit MITF expression directly, but also hinder MITF expression and pro-cancerous activity in a CREB1-/MAPK1-dependent manner indirectly.ConclusionsIn conclusion, this study uncovered miR-585-5p impedes gastric cancer proliferation and metastasis by orchestrating the interactions among CREB1, MAPK1 and MITF.

Medical image segmentation plays a vital role in computer-aided diagnosis procedures. Recently, U-Net is widely used in medical image segmentation. Many variants of U-Net have been proposed, which attempt to improve the network performance while keeping the U-shaped structure unchanged. However, this U-shaped structure is not necessarily optimal. In this article, the effects of different parts of the U-Net on the segmentation ability are experimentally analyzed. Then a more efficient architecture, Half-UNet, is proposed. The proposed architecture is essentially an encoder-decoder network based on the U-Net structure, in which both the encoder and decoder are simplified. The re-designed architecture takes advantage of the unification of channel numbers, full-scale feature fusion, and Ghost modules. We compared Half-UNet with U-Net and its variants across multiple medical image segmentation tasks: mammography segmentation, lung nodule segmentation in the CT images, and left ventricular MRI image segmentation. Experiments demonstrate that Half-UNet has similar segmentation accuracy compared U-Net and its variants, while the parameters and floating-point operations are reduced by 98.6 and 81.8%, respectively, compared with U-Net.

ObjectiveAccidental ingestion of button batteries (BB), usually occurred in children and infants, will rapidly erode the esophagus and result in severe complications, even death. It has been recommended that treatment of this emergent accident as soon as possible with drinking of pH-neutralizing viscous solutions such as honey and sucralfate before surgical removal can mitigate the esophageal injury. Recently, we reported that the electric insulating solutions such as edible oils could mitigate tissue damage in BB-exposed esophageal segments. In this study, we compared the protective effect of kitchen oil with honey or sucralfate, the recommended pH-neutralizing beverages, and with their mixture on esophageal injury caused by BB ingestion in pig esophageal segments and in living piglets.MethodsEffect of olive oil irrigations was compared to that of honey or sucralfate irrigations in the BB-damaged esophageal segments freshly collected from the local abattoir and in live Bama miniature piglets with the proximal esophagus exposed to BB for 60 min. Also, the effect of olive oil and honey mixture (MOH) irrigations was assessed in live animals. The BB voltage was recorded before insertion and after its removal. Gross and histological analysis of the esophageal injury was performed after BB exposure in segmented fresh esophagus and 7 days after BB exposure in live animals, respectively.ResultsOlive oil irrigations demonstrated better protective effect against BB-induced esophageal damage, compared to honey or sucralfate for BB-induced esophageal damage in vitro. But in vivo study showed that olive oil alone exacerbated esophageal injury because all esophagi irrigated with olive oil perforated. Surprisingly, irrigations with the MOH showed considerable protective effect for BB-induced esophageal damage in live animals, significantly better than irrigations with honey alone. The MOH decreased BB discharge, reduced area of surface injury, attenuated injured depth of esophageal wall thickness, and downed the mucosal injury index in comparison to using honey alone.ConclusionIrrigations with olive oil alone couldn’t prevent the BB discharge and is harmful for BB ingestion before surgical removal. However, mixed with honey, olive oil very effectively prevents the BB discharging and produces better esophageal protection than honey.

The silent information regulator sirtuin 1 (SIRT1) protein, a highly conserved NAD+-dependent deacetylase belonging to the sirtuin family, is a post-translational regulator that plays a role in modulating inflammation. SIRT1 affects multiple biological processes by deacetylating a variety of proteins including histones and non-histone proteins. Recent studies have revealed intimate links between SIRT1 and inflammation, while alterations to SIRT1 expression and activity have been linked to inflammatory diseases. In this review, we summarize the mechanisms that regulate SIRT1 expression, including upstream activators and suppressors that operate on the transcriptional and post-transcriptional levels. We also summarize factors that influence SIRT1 activity including the NAD+/NADH ratio, SIRT1 binding partners, and post-translational modifications. Furthermore, we underscore the role of SIRT1 in the development of inflammation by commenting on the proteins that are targeted for deacetylation by SIRT1. Finally, we highlight the potential for SIRT1-based therapeutics for inflammatory diseases.

Agricultural diseases and insect pests are one of the most important factors that seriously threaten agricultural production. Early detection and identification of pests can effectively reduce the economic losses caused by pests. In this paper, convolution neural network is used to automatically identify crop diseases. The data set comes from the public data set of the AI Challenger Competition in 2018, with 27 disease images of 10 crops. In this paper, the Inception-ResNet-v2 model is used for training. The cross-layer direct edge and multi-layer convolution in the residual network unit to the model. After the combined convolution operation is completed, it is activated by the connection into the ReLu function. The experimental results show that the overall recognition accuracy is 86.1% in this model, which verifies the effectiveness. After the training of this model, we designed and implemented the Wechat applet of crop diseases and insect pests recognition. Then we carried out the actual test. The results show that the system can accurately identify crop diseases, and give the corresponding guidance.

MicroRNAs play key roles in tumor metastasis. Here, we describe the regulation and function of miR-218 in gastric cancer (GC) metastasis. miR-218 expression is decreased along with the expression of one of its host genes, Slit3 in metastatic GC. However, Robo1, one of several Slit receptors, is negatively regulated by miR-218, thus establishing a negative feedback loop. Decreased miR-218 levels eliminate Robo1 repression, which activates the Slit-Robo1 pathway through the interaction between Robo1 and Slit2, thus triggering tumor metastasis. The restoration of miR-218 suppresses Robo1 expression and inhibits tumor cell invasion and metastasis in vitro and in vivo. Taken together, our results describe a Slit-miR-218-Robo1 regulatory circuit whose disruption may contribute to GC metastasis. Targeting miR-218 may provide a strategy for blocking tumor metastasis.