Search Results (310)

Purpose: Predicting colorectal cancer liver metastasis (CRLM) is essential for prognostic assessment. This study aims to develop and validate an interpretable multimodal machine learning framework based on multiparametric MRI for predicting CRLM, and to enhance the clinical interpretability of the model through SHapley Additive exPlanations (SHAP) analysis and deep learning visualization. Methods: This multicenter retrospective study included 463 patients with pathologically confirmed colorectal cancer from two institutions, divided into training (n = 256), internal testing (n = 111), and external validation (n = 96) sets. Radiomics features were extracted from manually segmented regions on axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). Deep learning features were obtained from a pretrained ResNet101 network using the same MRI inputs. A least absolute shrinkage and selection operator (LASSO) logistic regression classifier was developed for clinical, radiomics, deep learning, and combined models. Model performance was evaluated by AUC, sensitivity, specificity, and F1-score. SHAP was used to assess feature contributions, and Grad-CAM was applied to visualize deep feature attention. Results: The combined model integrating features across the three modalities achieved the highest performance across all datasets, with AUCs of 0.889 (training), 0.838 (internal test), and 0.822 (external validation), outperforming single-modality models. Decision curve analysis (DCA) revealed enhanced clinical net benefit from the integrated model, while calibration curves confirmed its good predictive consistency. SHAP analysis revealed that radiomic features related to T2WI texture (e.g., LargeDependenceLowGrayLevelEmphasis) and clinical biomarkers (e.g., CA19-9) were among the most predictive for CRLM. Grad-CAM visualizations confirmed that the deep learning model focused on tumor regions consistent with radiological interpretation. Conclusions: This study presents a robust and interpretable multiparametric MRI-based model for noninvasively predicting liver metastasis in colorectal cancer patients. By integrating handcrafted radiomics and deep learning features, and enhancing transparency through SHAP and Grad-CAM, the model provides both high predictive performance and clinically meaningful explanations. These findings highlight its potential value as a decision-support tool for individualized risk assessment and treatment planning in the management of colorectal cancer. Full article

Detecting manipulated document images is essential for verifying the authenticity of official records and preventing document forgery. However, forgery artifacts are often subtle and localized in fine-grained regions, such as text boundaries or character outlines, where visual symmetry and structural regularity are typically expected. These manipulations can disrupt the inherent symmetry of document layouts, making the detection of such inconsistencies crucial for forgery identification. Conventional CNN-based models face limitations in capturing such edge-level asymmetric features, as edge-related information tends to weaken through repeated convolution and pooling operations. To address this issue, this study proposes an edge-focused method composed of two components: the Edge Attention (EA) layer and the Edge Concatenation (EC) layer. The EA layer dynamically identifies channels that are highly responsive to edge features in the input feature map and applies learnable weights to emphasize them, enhancing the representation of boundary-related information, thereby emphasizing structurally significant boundaries. Subsequently, the EC layer extracts edge maps from the input image using the Sobel filter and concatenates them with the original feature maps along the channel dimension, allowing the model to explicitly incorporate edge information. To evaluate the effectiveness and compatibility of the proposed method, it was initially applied to a simple CNN architecture to isolate its impact. Subsequently, it was integrated into various widely used models, including DenseNet121, ResNet50, Vision Transformer (ViT), and a CAE-SVM-based document forgery detection model. Experiments were conducted on the DocTamper, Receipt, and MIDV-2020 datasets to assess classification accuracy and F1-score using both original and forged text images. Across all model architectures and datasets, the proposed EA–EC method consistently improved model performance, particularly by increasing sensitivity to asymmetric manipulations around text boundaries. These results demonstrate that the proposed edge-focused approach is not only effective but also highly adaptable, serving as a lightweight and modular extension that can be easily incorporated into existing deep learning-based document forgery detection frameworks. By reinforcing attention to structural inconsistencies often missed by standard convolutional networks, the proposed method provides a practical solution for enhancing the robustness and generalizability of forgery detection systems. Full article

End-to-end relation extraction (E2ERE) generally performs named entity recognition and relation extraction either simultaneously or sequentially. While numerous studies on E2ERE have centered on enhancing span representations to improve model performance, challenges remain due to the gaps between subtasks (named entity recognition and relation extraction) and the modeling discrepancies between entities and relations. In this paper, we propose a novel Label Annotation Interaction-based representation enhancement method for E2ERE, which institutes a two-phase semantic interaction to augment representations. Specifically, we firstly feed label annotations that are easy to manually annotate into a language model, and conduct the first-round interaction between three types of tokens with a partial attention mechanism; Then we construct a latent multi-view graph to capture various possible links between label and entity (pair) nodes, facilitating the second-round interaction between entities and labels. A series of comparative experiments with methods of various transformer-based architectures currently in use show that LAI-Net can maintain performance on par with the current SOTA in terms of NER task, and achieves significant improvements over existing SOTA models in terms of RE task. Full article

Background/Objectives: Frailty is a multifactorial clinical syndrome characterized by diminished physiological reserves and increased vulnerability to stressors. It is increasingly recognized as a predictor of poor outcomes in cardiac rehabilitation (CR). However, how frailty is defined, assessed, and addressed across outpatient CR programmes remains unclear. This scoping review aimed to map the extent, range, and nature of research examining frailty in the context of outpatient CR, including how frailty is measured, its impact on CR participation and outcomes, and whether sex and gender considerations or participation barriers are reported. Methods: Following the PRISMA-ScR guidelines, we conducted a comprehensive search across six electronic databases (from inception to 15 May 2025). Eligible peer-reviewed studies included adult participants assessed for frailty using validated tools and enrolled in outpatient CR programmes. Two reviewers independently screened citations and extracted data. Results were synthesized descriptively and narratively across three domains: frailty assessment, sex and gender considerations, and barriers to CR participation. The protocol was registered with the Open Science Framework. Results: Thirty-nine studies met inclusion criteria, all conducted in the Americas, Western Pacific, or Europe. Frailty was assessed using 26 distinct tools, most commonly the Kihon Checklist, Fried’s Frailty Criteria, and Frailty Index. The median pre-CR frailty prevalence was 33.5%. Few studies (n = 15; 38.5%) re-assessed frailty post-CR. Sixteen studies reported sex or gender data, but none applied sex- or gender-based analysis (SGBA) frameworks. Only eight studies examined barriers to CR participation, identifying physical limitations, emotional distress, cognitive concerns, healthcare system-related factors, personal and social factors, and transportation as key barriers. Conclusions: The literature on frailty in CR remains fragmented, with heterogeneous assessment methods, limited global representation, and inconsistent attention to sex, gender, and participation barriers. Standardized frailty assessments and individualized CR programme adaptations are urgently needed to improve accessibility, adherence, and outcomes for frail individuals. Full article

Enhanced weathering of silicate rocks in agriculture is an option for atmospheric CO₂ removal and fertility improvement. The objective of our work is to characterise some of the agricultural consequences of a basaltic powder amendment on soil-crop systems. Two doses of basalt (80 and 160 t ha⁻¹) were applied to two types of slightly acid soils (sandy or silty clayey), derived from long-term trials at Bordeaux (INRAE, France) and Rothamsted Research (England), respectively. For each soil, half of the pots were planted with ryegrass; the other half were left bare. Thus, the experiment had twelve treatments with four replications per treatment. Soil pH increased with the addition of basalt (+0.8 unit), with a 5% equivalence of that of reactive chalk. The basalt contained macro- and micronutrients. Some cations extractable in the basalt before being mixed to the soil became more extractable with increased weathering, independent of plant cover. Plant uptake generally increased for macronutrients and decreased for micronutrients, due to increased stock (macro) and reduced availability (micronutrients and P), related to pH increases. K supplied in the basalt was responsible for a significant increase in plant yield on the sandy soil, linked to an average basalt K utilisation efficiency of 33%. Our general conclusion is that rock dust applications have to be re-evaluated at each site with differing soil characteristics. Full article

Background: Electroencephalography (EEG) systems based on textile electrodes are increasingly being developed to address the need for more wearable sensor systems for brain function monitoring. Blink-related oscillations (BROs) are a new measure of brain function that corresponds to brainwave responses occurring after spontaneous blinking, and indexes neural processes as the brain evaluates new visual information appearing after eye re-opening. Prior studies have reported BRO utility as both a clinical and non-clinical biomarker of cognition, but no study has demonstrated BRO measurement using textile-based EEG devices that facilitate user comfort for real-world applications. Methods: We investigated BRO measurement using a four-channel EEG system with textile electrodes by extracting BRO responses using existing, publicly available EEG data (n = 9). We compared BRO effects derived from textile-based electrodes with those from standard dry Ag/Ag-Cl electrodes collected at the same locations (i.e., Fp1, Fp2, F7, F8) and using the same EEG amplifier. Results: Results showed that BRO effects measured using textile electrodes exhibited similar features in both time and frequency domains compared to dry Ag/Ag-Cl electrodes. Data from both technologies also showed similar performance in artifact removal and signal capture. Conclusions: These findings provide the first demonstration of successful BRO signal capture using four-channel EEG with textile electrodes, providing compelling evidence toward the development of a comfortable and user-friendly EEG technology that uses the simple activity of blinking for objective brain function assessment in a variety of settings. Full article

This article examines the struggles for water justice led by women in the Aconcagua River Basin (Valparaíso, Chile) through a hydrofeminist perspective. Chile’s water crisis, rooted in a colonial extractivist model and exacerbated by neoliberal policies of water privatization, reflects a deeper crisis of socio-environmental injustice. Rather than understanding water merely as a resource, this research adopts a relational epistemology that conceives water as a living entity shaped by and shaping social, cultural, and ecological relations. Drawing on life-history interviews and the construction of a hydrofeminist cartography with women river defenders, this article explores how gendered and racialized bodies experience the crisis, resist extractive practices, and articulate alternative modes of co-existence with water. The hydrofeminist framework offers critical insights into the intersections of capitalism, colonialism, patriarchy, and environmental degradation, emphasizing how women’s embodied experiences are central to envisioning new water governance paradigms. This study reveals how women’s affective, spiritual, and territorial ties to water foster strategies of resilience, recovery, and re-existence that challenge the dominant extractivist logics. By centering these hydrofeminist life histories, this article contributes to broader debates on environmental justice, decolonial feminisms, and the urgent need to rethink human–water relationships within the current climate crisis. Full article

Objectives: Pneumothorax is a critical condition frequently encountered in emergency departments (EDs), with spontaneous pneumothorax (SP) and traumatic pneumothorax (TP) presenting distinct clinical challenges. This study aimed to evaluate the epidemiological characteristics, clinical outcomes, and treatment strategies for SP and TP across different age groups and provide insights for optimizing emergency management protocols. Methods: This retrospective cohort study analyzed 2797 cases of pneumothorax over five years (2018–2023) at a tertiary care center. Patients were stratified by age (18–39, 40–64, and >65 years) and pneumothorax type (SP vs. TP). Data on demographics, clinical presentation, treatment, hospital stay, recurrence, and complications were extracted from medical records. Comparative statistical analyses were also conducted. Results: The mean age of patients with SP was 32.5 ± 14.7 years, whereas patients with TP were older (37.8 ± 16.2 years, p < 0.001). Male predominance was observed in both groups: 2085 (87.0%) in the SP group and 368 (92.0%) in the TP group (p = 0.01). The right lung was more frequently affected in the SP (64.2%) and TP (56.0%) groups (p < 0.001). Age-related differences were evident in both groups of patients. In the SP group, younger patients (18–39 years) represented the majority of cases, whereas older patients (≥65 years) were more likely to present with SSP and required more invasive management (p < 0.01). In the TP group, younger patients often had pneumothorax due to high-energy trauma, whereas older individuals developed pneumothorax due to falls or iatrogenic causes (p < 0.01). SP predominantly affected younger patients, with a history of smoking and male predominance associated with younger age (p < 0.01). TP is more frequent in older patients, often because of falls or iatrogenic injuries. Management strategies varied by age group; younger patients were often managed conservatively, whereas older patients underwent more invasive procedures (p < 0.01). Surgical intervention was more common in younger patients in the TP group, whereas conservative management was more frequent in elderly patients (p < 0.01). The clinical outcomes differed significantly, with older patients having longer hospital stays and higher rates of persistent air leaks (p < 0.01). Recurrence was more common in younger patients with SP, whereas TP recurrence rates were lower across all age groups (p < 0.01). No significant differences were observed in re-expansion pulmonary edema, empyema, or mortality rates between the age groups, suggesting that age alone was not an independent predictor of these complications when adjusted for pneumothorax severity and management strategy (p = 0.22). Conclusions: Age, pneumothorax subtype, and underlying pulmonary comorbidities were identified as key predictors of clinical outcomes. Advanced age, secondary spontaneous pneumothorax, and COPD were independently associated with recurrence, prolonged hospitalization, and in-hospital mortality, respectively. These findings highlight the need for risk-adapted management strategies to improve triaging and treatment decisions for spontaneous and traumatic pneumothorax. Full article

Re-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individuals, arbitrary poses, and significant background noise. To address these challenges, we propose a multi-view network for silkworm ReID, called WormNet, which is built upon an innovative strategy termed extraction purification extraction interaction. Specifically, we introduce a multi-order feature extraction module that captures a wide range of fine-grained features by utilizing convolutional kernels of varying sizes and parallel cardinality, effectively mitigating issues of high individual similarity and diverse poses. Next, a feature mask module (FMM) is employed to purify the features in the spatial domain, thereby reducing the impact of background interference. To further enhance the data representation capabilities of the network, we propose a channel interaction module (CIM), which combines an efficient channel attention network with global response normalization (GRN) in parallel to recalibrate features, enabling the network to learn crucial information at both the local and global scales. Additionally, we introduce a new silkworm ReID dataset for network training and evaluation. The experimental results demonstrate that WormNet achieves an mAP value of 54.8% and a rank-1 value of 91.4% on the dataset, surpassing both state-of-the-art and related networks. This study offers a valuable reference for ReID in insects and other organisms. Full article

Accurate prediction of soil lead (Pb) content in small sample scenarios is often limited by data scarcity and variability in soil properties, with traditional spectral modeling methods yielding suboptimal precision. To address this, we propose a transfer learning-based framework integrated with SHAP analysis for predicting soil Pb content in the Gejiu mining area, Yunnan. Using pH data from the European LUCAS soil database as the source domain, spectral features were extracted via a 1D-ResNet model and transferred to the target domain (130 soil samples from Gejiu) for Pb prediction. SHAP analysis was applied to clarify the role of spectral characteristics in cross-component transfer learning, uncovering shared and adaptive features between pH and Pb predictions. The transfer learning model (ResNet-pH-Pb) significantly outperformed direct modeling methods (PLS-Pb, SVM-Pb, and ResNet-Pb), with an R² of 0.77, demonstrating superior accuracy. SHAP analysis showed that the model retained key pH-related wavelengths (550–750 nm and 1600–1700 nm) while optimizing Pb-related wavelengths (e.g., 919 nm and 959 nm). This study offers a novel approach for soil heavy metal prediction under small sample constraints and provides a theoretical basis for understanding spectral prediction mechanisms through interpretability analysis. Full article

Cross-document relation extraction (CodRE) aims to predict the semantic relationships between target entities located in different documents, a critical capability for comprehensive knowledge graph construction and multi-source intelligence analysis. Existing approaches primarily rely on bridge entities to capture interdependencies between target entities across documents. However, these models face two potential limitations: they employ entity-centered context filters that overlook relation-specific information, and they fail to account for varying semantic distances between document paths. To address these challenges, we propose CLEAR (Cross-document Link-Enhanced Attention for Relations), a novel framework integrating three key components: (1) the Relation-aware Context Filter that incorporates relation type descriptions to preserve critical relation-specific evidence; (2) the Path Distance-Weighted Attention mechanism that dynamically adjusts attention weights based on semantic distances between document paths; and (3) a cross-path entity matrix that leverages inner- and inter-path relations to enrich target entity representations. Experimental results on the CodRED benchmark demonstrate that CLEAR outperforms all competitive baselines, achieving state-of-the-art performance, with 68.78% AUC and 68.42% F1 scores, confirming the effectiveness of our framework. Full article

Five beetle species can occur in potato fields simultaneously, including one quarantine pest (the Colorado potato beetle (CPB)), one phytophagous pest (the 28-spotted potato ladybird beetle), and three predatory ladybird beetles (the 7-spotted lady beetle, the tortoise beetle, and the harlequin ladybird beetle). The timely detection and accurate identification of CPB and other phytophagous or predatory beetles are critical for the effective implementation of monitoring and control strategies. However, morphological identification requires specialized expertise, is time-consuming, and is particularly challenging due to the dark brown body color of these beetles when in the young larval stages. This study provides an effective solution to distinguish between phytophagous and/or quarantine and predatory beetles. This solution is in the form of a new convolutional neural network architecture, known as MSAC-ResNet. Specifically, it comprises several multiscale asymmetric convolution blocks, which are designed to extract features at multiple scales, mainly by integrating different-sized asymmetric convolution kernels in parallel. We evaluated the MSAC-ResNet through comprehensive model training and testing on a beetle image dataset of 11,325 images across 20 beetle categories. The proposed recognition model achieved accuracy, precision, and recall rates of 99.11%, 99.18%, and 99.11%, respectively, outperforming another five existing models, namely, AlexNet, MobileNet-v3, EfficientNet-b0, DenseNet, and ResNet-101. Notably, the developed field investigation mini-program can identify all the developmental stages of these five beetle species, from young larvae to adults, and provide timely management (or protection) suggestions to farmers. Our findings could be significant for future research related to precise pest control and the conservation of natural enemies. Full article

Speaker verification (SV) is an exceptionally effective method of biometric authentication. However, its performance is heavily influenced by the effectiveness of the extracted speaker features and their suitability for use in resource-limited environments. Transformer models and convolutional neural networks (CNNs), leveraging self-attention mechanisms, have demonstrated state-of-the-art performance in most Natural Language Processing (NLP) and Image Recognition tasks. However, previous studies indicate that standalone Transformer and CNN architectures present distinct challenges in speaker verification. Specifically, while Transformer models deliver good results, they fail to meet the requirements of low-resource scenarios and computational efficiency. On the other hand, CNNs perform well in resource-constrained environments but suffer from significantly reduced recognition accuracy. Several existing approaches, such as Conformer, combine Transformers and CNNs but still face challenges related to high resource consumption and low computational efficiency. To address these issues, we propose a novel solution that enhances the Transformer model by introducing multi-scale convolutional attention and a Global Response Normalization (GRN)-based feed-forward network, resulting in a lightweight backbone architecture called the lightweight simple transformer (LST). We further improve LST by incorporating the Res2Net structure from CNN, yielding the Res2Former model—a low-parameter, high—precision SV model. In Res2Former, we design and implement a time-frequency adaptive feature fusion(TAFF) mechanism that enables fine-grained feature propagation by fusing features at different depths at the frame level. Additionally, holistic fusion is employed for global feature propagation across the model. To enhance performance, multiple convergence methods are introduced, improving the overall efficacy of the SV system. Experimental results on the VoxCeleb1-O, VoxCeleb1-E, VoxCeleb1-H, and Cn-Celeb(E) datasets demonstrate that Res2Former achieves excellent performance, with the Large configuration attaining Equal Error Rate (EER)/Minimum Detection Cost Function (minDCF) scores of 0.81%/0.08, 0.98%/0.11, 1.81%/0.17, and 8.39%/0.46, respectively. Notably, the Base configuration of Res2Former, with only 1.73M parameters, also delivers competitive results. Full article

Visible and thermal-infrared re-identification (VTI-ReID) based on aerial images is a challenging task due to the large range of elevation angles, which exacerbates the modality differences between different modalities. The substantial modality gap makes it challenging for existing methods to extract identity information from aerial images captured at wide elevation angles. This limitation significantly reduces VTI-ReID accuracy. This issue is particularly pronounced in elongated targets. To address this issue, a robust framework for extracting identity representation (RIRE) is proposed, specifically designed for VTI-ReID in aerial cross-modality images. This framework adopts a mapping method based on global representation decomposition and local representation aggregation. It effectively extracts features related to identity from aerial images and aligns the global representations of images captured from different angles within the same identity space. This approach enhances the adaptability of the VTI-ReID task to elevation angle differences. To validate the effectiveness of the proposed framework, a dataset group for elongated target VTI-ReID based on unmanned aerial vehicle (UAV)-captured data has been created. Extensive evaluations of the proposed framework on the proposed dataset group indicate that the framework significantly improves the robustness of the extracted identity information for elongated targets in aerial images, thereby enhancing the accuracy of VTI-ReID. Full article

In the present study, we characterized and investigated the effect of the araçá-boi extract on antioxidant activity, cell viability, and the regulation of genes related to tumor suppression and epigenetic mechanisms in ovarian cancer cells. The results showed that araçá-boi extract revealed a remarkable diversity of phytochemicals (organic acids, phenolic acids, and flavonoids), significant antioxidant potential, and efficient scavenging of reactive oxygen species, particularly hydroxyl and peroxyl radicals. Gallic acid, one of the phenolic acids present in the extract, was used alone to verify its contribution to cytotoxic activities. Exposure of human ovarian cancer cells (NCI/ADR-RES and OVCAR3) to the extract (0.15–150 μg/mL) and gallic acid (6–48 μg/mL) resulted in a significant reduction in cell viability, particularly after 48 h of treatment. Both treatments modulated genes involved in DNA repair, tumor suppression, and epigenetic regulation. However, no changes were observed in the methylation status of the BRCA1 gene promoter region with either araçá-boi extract or gallic acid. These findings reinforce the therapeutic potential of araçá-boi extract and its phenolic compounds against ovarian cancer and point to the need for further studies to better elucidate the molecular pathways involved and validate these effects in vivo. Full article