Search

Micro-expression is extensively studied due to their ability to fully reflect individuals' genuine emotions. However, accurate micro-expression recognition is a challenging task due to the subtle motion of facial muscle. Therefore, this paper introduces a Graph Attention Mechanism-based Motion Magnification Guided Micro-Expression Recognition Network (GAM-MM-MER) to amplify delicate muscle motions and focus on key facial landmarks. First, we propose a Swin Transformer-based network for micro-expression motion magnification (ST-MEMM) to enhance the subtle motions in micro-expression videos, thereby unveiling imperceptible facial muscle movements. Then, we propose a graph attention mechanism-based network for micro-expression recognition (GAM-MER), which optimizes facial key area maps and prioritizes adjacent nodes crucial for mitigating the influence of noisy neighbors, while attending to key feature information. Finally, experimental evaluations conducted on the CASME II and SAMM datasets demonstrate the high accuracy and effectiveness of the proposed network compared to state-of-the-art approaches. The results of our network exhibit significant superiority over existing methods. Furthermore, ablation studies provide compelling evidence of the robustness of our proposed network, substantiating its efficacy in micro-expression recognition.

Digital transformation has become an inevitable choice for enterprises to survive and compete. This article aims to investigate mechanisms and impacts of peer effects in digital transformation within supply chain networks. Using a sample of listed companies in China from 2011 to 2020, the findings suggest the existence of peer effects in the digital transformation of enterprises within supply chain networks. These effects become more significant as the perception of uncertainty and environmental uncertainty increase. Further analysis reveals that the greater the disparity in discourse power and the degree of digital transformation among peer enterprises within the supply chain, the stronger the peer effects. The study also examines various scenarios in which enterprises operate, finding that greater supply chain stability significantly enhances the peer effects of digital transformation. Heterogeneity tests indicate that peer effects in digital transformation are more evident when peer enterprises within the supply chain are located in different regions, operate in different industries, are non-state-owned, have directorial connections and common institutional ownership, and possess fluctuating executive teams. Additionally, the study discusses the spillover effects of digitalization among peer enterprises on the focal company. This research provides a micro-level exploration of the peer effects of digital transformation from a supply chain perspective, offering theoretical references and practical insights for enterprises seeking to achieve digital transformation.

Multilabel classification in remote sensing is very significant and plays an important role in extracting valuable information from satellite imagery. Ignoring the distinct information provided by labels in each image or transforming images into content-aware category representations without considering the inherent correlation of labels within the dataset can result in the establishment of improper relationships between images and labels, ultimately leading to a significant degradation in accuracy. To address this problem, this article proposes a label-driven graph convolutional network (LD-GCN) to excavate substantial information using the inherent correlation of labels from datasets and build a strong relationship between labels and images. The framework consists of two modules, i.e., the label recognition GCN (LRGCN) and the semantic enrichment module (SEM). The LRGCN module yields rich and valuable information from the inherent correlation of labels and builds a strong relationship between images and labels. The SEM further enriches the semantics obtained from LRGCN. Experiments conducted on UCM, AID, and DFC15 multilabel remote sensing datasets illustrate that LD-GCN outperforms the state-of-the-art methods on key evaluation metrics.

BackgroundCervical cancer remains a significant gynecologic malignancy in both China and the United States, posing a substantial threat to women’s lives and health due to its high morbidity and mortality rates. Altered energy metabolism and dysregulated mitochondrial function play crucial roles in the development, growth, metastasis, and recurrence of malignant tumors. In this study, we aimed to predict prognosis and assess efficacy of anti-tumor therapy in cervical cancer patients based on differential genes associated with mitochondrial metabolism.MethodsTranscriptomic data and clinical profiles of cervical cancer patients were retrieved from the TCGA and GEO databases. Differential gene-related cellular pathways were identified through GO, KEGG, and GSEA analyses. Prognostic indices were constructed using LASSO regression analysis. Immune cell infiltration was assessed using CIBERSORT and ssGSEA, and the correlation between immune checkpoint inhibitor genes and differential genes was examined. Tumor mutation load (TMB) and its association with prognostic indices were analyzed using nucleotide variant data from the TCGA database. Patient response to immunotherapy and sensitivity to antitumor drugs were determined using the TIDE algorithm and the oncoPredic algorithm, respectively.ResultsA prognostic index based on metabolism-related differential genes was developed to predict the clinical outcome of cervical cancer patients, enabling their classification into two distinct subtypes. The prognostic index emerged as an independent risk factor for unfavorable prognosis. The high-index group exhibited a significantly worse overall prognosis, along with elevated tumor mutation burden (TMB), increased immune cell infiltration, and lower TIDE scores, indicating a potential benefit from immunotherapy. Conversely, the low-index group demonstrated increased sensitivity to metabolism-related antitumor agents, specifically multikinase inhibitors.ConclusionThe aim of this study was to develop a prognostic index based on differential genes associated with mitochondrial metabolism, which could be used to predict cervical cancer patients’ prognoses. When combined with TIDE and TMB analyses, this prognostic index offers insights into the immune cell infiltration landscape, as well as the potential efficacy of immunotherapy and targeted therapy. Our analysis suggests that the Iron-Sulfur Cluster Assembly Enzyme (ISCU) gene holds promise as a biomarker for cervical cancer immunotherapy.

The mechanisms underlying autophagic defects in nonalcoholic steatohepatitis (NASH) remain largely unknown. We aimed to elucidate the roles of hepatic cyclooxygenase 1 (COX1) in autophagy and the pathogenesis of diet-induced steatohepatitis in mice. Human nonalcoholic fatty liver disease (NAFLD) liver samples were used to examine the protein expression of COX1 and the level of autophagy. Cox1Δhepa mice and their wildtype littermates were generated and fed with 3 different NASH models. We found that hepatic COX1 expression was increased in patients with NASH and diet–induced NASH mice models accompanied by impaired autophagy. COX1 was required for basal autophagy in hepatocytes and liver specific COX1 deletion exacerbated steatohepatitis by inhibiting autophagy. Mechanistically, COX1 directly interacted with WD repeat domain, phosphoinositide interacting 2 (WIPI2), which was crucial for autophagosome maturation. Adeno-associated virus (AAV)-mediated rescue of WIPI2 reversed the impaired autophagic flux and improved NASH phenotypes in Cox1Δhepa mice, indicating that COX1 deletion-mediated steatohepatitis was partially dependent on WIPI2-mediated autophagy. In conclusion, we demonstrated a novel role of COX1 in hepatic autophagy that protected against NASH by interacting with WIPI2. Targeting the COX1–WIPI2 axis may be a novel therapeutic strategy for NASH.

Ships are important targets for modern naval warfare detection and reconnaissance. The accurate detection of ships contributes to the maintenance of maritime rights and interests and the realisation of naval strategy. Synthetic Aperture Radar (SAR) image detection tasks play a vital role in ship detection, which has consistently been a research hotspot in the field of SAR processing. Although significant progress has been achieved in SAR ship detection techniques using deep learning methods, some challenges still persist. Natural images and SAR images significantly diverge in imaging mechanisms and scattering characteristics. In complex background environments, ships exhibit multiscale variations and dense arrangements, and numerous small-sized ships may be present, culminating in false or missed detections. To address these issues, we propose a novel SAR ship detection network, namely, a Wavelet-Driven Feature-Enhanced Attention–You Only Look Once X (WDFA-YOLOX) network. Firstly, we propose a Wavelet Cascade Residual (WCR) module based on the traditional image processing technique wavelet transform, which is embedded within an improved Spatial Pyramid Pooling (SPP) module, culminating in the formation of the effective wavelet transform-based SPP module (WSPP). The WSPP compensates for the loss of fine-grained feature information during pooling, enhancing the capability of the network to detect ships amidst complex background interference. Secondly, a Global and Local Feature Attention Enhancement (GLFAE) module is proposed, leveraging a parallel structure that combines convolutional modules with transformer modules to reduce the effect of irrelevant information and effectively strengthens valid features associated with small-sized ships, resulting in a reduction in false negatives in small-sized ship detection. Finally, a novel loss function, the Chebyshev distance-generalised IoU loss function, is proposed to significantly enhance both the precision of the detection box and the network convergence speed. To support our approach, we performed thorough experiments on the SSDD and HRSID, achieving an average precision (AP) of 99.11% and 96.20%, respectively, in ship detection. The experimental results demonstrate that WDFA-YOLOX has significant advantages in terms of detection accuracy, generalisation capability, and detection speed and can effectively realise more accurate detection in SAR images, consistently exhibiting superior performance and application value in SAR ship detection.

Deep Learning (DL) has become a popular method for Remote Sensing (RS) Change Detection (CD) due to its superior performance compared to traditional methods. However, generating extensive labeled datasets for DL models is time-consuming and labor-intensive. Additionally, the imbalance between changed and unchanged areas in object CD datasets, such as buildings, poses a critical issue affecting DL model efficacy. To address this issue, this paper proposes a change detection enhancement method using artificial image generation and attention mechanism. Firstly, the content of the imbalanced CD dataset is enhanced using a data augmentation strategy that synthesizes effective building CD samples using artificial RS image generation and building label creation. The created building labels, which serve as new change maps, are fed into a generator model based on a conditional Generative Adversarial Network (c-GAN) to generate high-resolution RS images featuring building changes. The generated images with their corresponding change maps are then added to the CD dataset to create the balance between changed and unchanged samples. Secondly, a channel attention mechanism is added to the proposed Adversarial Change Detection Network (Adv-CDNet) to boost its performance when training on the imbalanced dataset. The study evaluates the Adv-CDNet using WHU-CD and LEVIR-CD datasets, with WHU-CD exhibiting a higher degree of sample imbalance compared to LEVIR-CD. Training the Adv-CDNet on the augmented dataset results in a significant 16.5% F1-Score improvement for the highly imbalanced WHU-CD. Moreover, comparative analysis showcases the superior performance of the Adv-CDNet when complemented with the attention module, achieving a 6.85% F1-Score enhancement.

Background: Few studies have explored air and surface contamination by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in healthcare settings. Methods: Air and surface samples were collected from the isolation wards and intensive care units designated for coronavirus disease 2019 (COVID-19) patients. Clinical data and the results of nasopharyngeal specimen and serum antibody testing were also collected for the patient sample. Results: A total of 367 air and surface swab samples were collected from the patient care areas of 15 patients with mild COVID-19 and nine patients with severe/critical COVID-19. Only one air sample taken during the intubation procedure tested positive. High-touch surfaces were slightly more likely to be contaminated with SARS-CoV-2 RNA than low-touch surfaces. Contamination rates were slightly higher near severe/critical patients than near mild patients, although this difference was not statistically significant (p > 0.05). Surface contamination was still found near the patients with both positive IgG and IgM. Conclusions: Air and surface contamination with viral RNA was relatively low in these healthcare settings after the enhancement of infection prevention and control. Environmental contamination could still be found near seroconverted patients, suggesting the need to maintain constant vigilance in healthcare settings to reduce healthcare-associated infection during the COVID-19 pandemic.