Search Results (25,957)

Background: Artificial intelligence-based computer-aided detection (AI-CAD) systems are increasingly being used in endovascular practice to support time-sensitive detection, triage and prioritization tasks in imaging and procedural workflows. Despite rapid technological advancements and expanding regulatory clearances, the translation to lasting clinical benefit varies. Objective: This narrative review synthesizes AI-CAD applications in endovascular interventions and proposes an evaluation-oriented framework to support responsible clinical translation; this framework emphasizes detection-specific metrics, external validation, bias-aware assessment, and workflow integration. Methods: A structured narrative review was conducted using targeted searches in PubMed, Google Scholar, and IEEE Xplore (2020–2026); this review was supported by an examination of US FDA device databases and citation tracking. Evidence was assessed using a pragmatic hierarchical classification framework based on regulatory status and validation rigor. Results: AI-CAD applications were mapped across four main endovascular domains: neurovascular interventions (e.g., large vessel occlusion triage), coronary interventions (CCTA-based stenosis detection and intravascular imaging support), aortic interventions/EVAR (endoleak detection and sac monitoring), and peripheral interventions (lesion detection and angiographic decision support). Across the domains, performance reporting was heterogeneous and often relied on retrospective, single-center assessments. Key barriers to clinical readiness included acquisition variability and dataset shift due to artifacts, limited multicenter validation, annotation variability, and human–AI workflow factors. Evaluation priorities included whether to assess at the lesion level or case level, false positive burden and calibration, external validation under real-world heterogeneity, and clinical impact measures such as treatment timing and procedural decision-making. Conclusions: AI-CAD systems hold significant potential for improving endovascular care; however, clinical readiness depends on rigorous, endovascular feature-specific assessment and transparent reporting, beyond retrospective accuracy. The proposed evidence level framework and assessment checklist provide practical tools for distinguishing mature technologies from research prototypes and guiding future validation, implementation, and post-market monitoring. Full article

Sequence-based tools have greatly improved the molecular description of soil bioremediation, but detection alone cannot confirm that a contaminant is being degraded by a defined pathway. In soils, bioavailability limitations, redox microsites, relic DNA, gene mobility, and community restructuring can decouple gene presence from reaction flux. This review synthesizes an operational framework that separates three inferential levels: pathway potential, in situ activity, and verified pathway operation. The framework links inoculant fate, functional gene abundance, gene expression, pathway reconstruction, stable isotope probing, and targeted chemical analysis under explicit quality assurance, quality control, and decision rules. Particular attention is given to distinguishing parent compound loss from mineralization and detoxification and to using isotopic attribution when functional redundancy or inoculant-native overlap obscures agency. Instead of being presented as conceptually new, these principles are organized into a practical workflow for soil systems. This structure clarifies what can be discerned from genes, transcripts, proteins, metabolites, and transformation products at each evidentiary tier and provides a conservative basis for integrating multi-omics with mechanistic and quantitative interpretation. Full article

Mispronunciation detection (MD) is a key component in computer-assisted pronunciation training (CAPT) and speaking tests. Most MD systems adopt a production view, measuring phone-level deviation from a canonical pronunciation (Native Norm) or the expected pronunciation of a target population (Target Norm). Yet, pronunciation assessment is fundamentally perceptual: listeners map speech to linguistic categories under uncertainty and with individual psychological priors, so judgments are inherently subjective and lack a single gold standard. Labels are therefore often aggregated (e.g., voting), but aggregation rules are themselves subjective, require many annotators, and entangle individual perception with social consensus, complicating model training. In this paper, we propose a “Perception Norm”, which models MD as the decision process of individual annotators and trains models to simulate single listeners rather than an annotator pool. To support this study, we introduce UY/CH-CHILD-MA, a corpus of Uyghur-accented child Mandarin words and phrases with four independent phone-level annotations. Our experiments reveal substantial inter-annotator variation and show that a Transformer with pre-training and fine-tuning can learn annotator-specific patterns with high accuracy. Finally, we present a committee ensemble that combines annotator models using application-matched aggregation rules to produce task-specific assessments. The data and source code will be made publicly available upon publication. Full article

In the present work, a novel series of eleven sulfonate derivatives with potent inhibitory activity against butyrylcholinesterase (BChE) is reported. Of these, compounds 2-[(E)-(2-Benzoylhydrazinylidene)methyl]phenyl 5-(dimethylamino)naphthalene-1-sulfonate (5c, IC₅₀ = 1.11 µM) and tert-butyl (2E)-2-[(2-{[5-(dimethylamino)naphthalene-1-sulfonyl]oxy}phenyl)methylidene]hydrazine-1-carboxylate (5b, IC₅₀ = 11.51 µM) exhibit stronger inhibitory activity than rivastigmine, the reference compound, and exhibit high selectivity for BChE over AChE (e.g., selectivity index 57 for 5c). Interestingly, compound 5c also exhibited anti-inflammatory effects, which is important for potential therapeutic applications, especially in Alzheimer’s disease. These new compounds were designed through a structure-based approach using molecular modeling techniques (docking, molecular dynamic (MD) simulations, and QTAIM (quantum theory of atoms in molecules) calculations). The most promising compounds show no detectable toxic effects and satisfy Lipinski’s rule of five, indicating that they represent attractive starting structures for the design of new derivatives acting as specific BChE inhibitors. In addition, our results indicate that relatively simple computational techniques such as docking calculations and toxicity prediction programs can be valuable when properly used in the search of new candidates for this particular target. Docking calculations show that the more active compounds of this series reach the bottom region of the gorge interacting with residues within the active site of BChE. However, our data further suggest that the use of more precise techniques, such as MD simulations and QTAIM analysis, is necessary to obtain detailed insight into ligand–enzyme interactions. Regarding QTAIM calculations, they demonstrate that such computations are very useful to evaluate the molecular interactions of the different molecular complexes. In summary, we report a new series of sulfonate derivatives as promising starting structures for the development of new selective BChE inhibitors. Full article

The coronavirus disease 19 pandemic disrupted pediatric respiratory infections through non-pharmaceutical interventions and altered contact patterns. Long-term comparisons across the pandemic timeline in children remain limited. In this study, we analyzed 15,657 respiratory specimens from patients ≤ 18 years at Dankook University Hospital (2007–2023) using multiplex polymerase chain reaction assays targeting 15 viruses. Age-stratified positivity rates were compared across pandemic phases. Children ≤ 6 years comprised 88.61% of the study population. Human rhinovirus showed the highest detection rate (24.06%), followed by adenovirus (12.33%), respiratory syncytial virus-subtypes A and B (RSV-A: 11.13%; RSV-B: 8.65%), human parainfluenza virus-type 3 (HPIV-3; 6.21%), human metapneumovirus (HMPV; 5.33%), and enterovirus (2018–2023; EV; 10.96%). Monthly distributions differed (p < 0.001). RSV peaked in late autumn and winter; influenza and seasonal coronaviruses in winter and spring; HMPV, HPIV-3, EV, and human bocavirus in summer and fall. Positivity declined during the pandemic, rebounding in 2023, most prominently among children aged 1–6 years (84.91%). HPIV-3 and EV increased (p < 0.001). RSV-A predominated pre-pandemic, whereas RSV-B showed a non-significant relative increase post-pandemic; no subtype differences occurred during the pandemic. Findings demonstrate pathogen-specific shifts in predominance and seasonality and support ongoing surveillance and pediatric care planning. Full article

Background: Traditional functional mobility assessments often fail to detect subclinical postural decline in active aging populations. This study introduces the Head–Sternum Dissociation Index as a novel digital biomarker to identify latent sensorimotor deficits before macroscopic balance failure occurs. Methods: Ninety-four participants (Young, Middle-Aged Civil, Middle-Aged Dancers, and Older Adults) performed instrumented limits of stability tasks, specifically functional and lateral reach tests, utilizing a three-sensor inertial measurement unit configuration. Postural strategies were quantified via the Head–Sternum Dissociation Index and the peak ratio of corrective micro-movements, validating the sensor output against a gold-standard force platform. Results: A significant kinematic breakpoint in postural control was identified at age 55 (p < 0.001). However, Middle-Aged Civilians exhibited early kinematic divergence despite maintaining normal Timed Up and Go test performance. Receiver operating characteristic analysis revealed distinct, sex-specific physiological limits: aging males predominantly adopted a rigid “Stiffness” strategy (peak ratio ≤ 1.15, head–sternum dissociation threshold > 0.63°), while females utilized a broader, more permissive “Continuous” strategy (head–sternum dissociation threshold > 0.31°). Notably, recreational rhythmic training (dance) completely neutralized this age-related decay, with middle-aged dancers maintaining highly efficient, youthful stabilization profiles (Cohen’s d = 2.20). Conclusions: The Head–Sternum Dissociation Index, combined with relative corrective frequency, successfully phenotypes early sensorimotor erosion. These findings advocate for the integration of sex-specific kinematic screening into primary care, allowing clinicians to prescribe targeted interventions well before clinical fall risk manifests. Full article

Fasciolosis is a globally prevalent trematode infection of major veterinary and public-health relevance. Juveniles migrate through liver tissue for weeks before patency, so clinically important infection may occur while faecal egg output is undetectable, complicating control and interpretation of apparent treatment failure. Triclabendazole (TCBZ) remains central because it targets both immature and adult flukes, but sustained use has been accompanied by geographically expanding reports of reduced efficacy and confirmed resistance. Most alternative fasciolicides, such as albendazole, closantel, oxyclozanide, rafoxanide, clorsulon and nitroxynil, are largely adulticidal and used alone or in combinations, yet reports of reduced efficacy/resistance are increasing worldwide. This review summarises drugs in current use and reported resistance status, and outlines a practical pathway for detecting and confirming resistance. We then appraise leading mechanistic hypotheses for TCBZ resistance as a central case study, organised around microtubule-associated phenotypes, reduced effective drug exposure, genetic architecture with tissue context, stress response and detoxification capacity, and we highlight mechanistic gaps for other fasciolicides. Finally, we discuss management implications, including monitoring-guided stewardship, stage-appropriate drug selection, rational combinations, integrated parasite management, and identify near-term priorities for harmonised surveillance, improved diagnostics and tool development. This review updates the resistance landscape and supports practical, monitoring-guided control of fasciolosis. Full article

Background: Arterial hypertension in childhood is an increasing health concern, often associated with structural and functional cardiovascular or renal alterations. This study aimed to investigate the prevalence and type of non-stenotic renal artery anatomical variants in children with systemic hypertension and to assess their possible association with cardiac involvement. Methods: A total of 107 children and adolescents with hypertension (mean age 15.4 ± 2.7 years) were evaluated. Hypertension was defined as blood pressure persistently above the 95th percentile for over one year, confirmed by 24 h ambulatory blood pressure monitoring. Patients with known secondary causes were excluded. All underwent renal vascular imaging by CT or MRI and echocardiographic assessment of left ventricular morphology and function. Results: Renal artery anatomical variants were found in 69 of 107 patients (65%), mainly unilateral or bilateral accessory polar arteries. Other anomalies found (left renal vein narrowing or duplication, severe left renal artery stenosis) were excluded from the statistical analysis. Normal renal vasculature was observed in only 32%. Left ventricular hypertrophy was detected in 41%, highlighting a significant prevalence of target-organ involvement. No statistically significant differences were found in terms of hypertension or hypertrophy between patients with renal artery anatomical variants and those without. However, patients with renal anomalies more frequently required dual antihypertensive therapy (p = 0.025). Conclusions: Renal artery anatomical variants, even in the absence of overt stenosis, may contribute to the pathogenesis of pediatric hypertension and complicate its management. Systematic evaluation of renal vasculature should be considered in the diagnostic workup to improve risk stratification and guide management strategies. Full article

Background: Neuronal apoptosis is the core pathological mechanism of cerebral ischemic–reperfusion injury (CIRI); although Astragaloside IV (AS-IV) has demonstrated neuroprotective activity against CIRI, its specific molecular mechanisms underlying the regulation of this apoptosis-related pathway remain to be systematically elucidated. Methods: We establish an in vivo model of middle cerebral artery occlusion/reperfusion (MCAO/R) in rats and an in vitro model of oxygen–glucose deprivation/reperfusion (OGD/R) in PC12 cells. Six core apoptotic proteins, including CytC, Apaf-1, BAX, Bcl-2, Caspase3, and Caspase9, were detected using neurological function scoring, TTC/HE/Nissl staining, TUNEL staining, Western blot, and immunofluorescence techniques. Molecular docking and molecular dynamics simulation were utilized to analyze the binding affinity between AS-IV and the aforementioned apoptotic proteins. Results: Molecular docking and dynamics simulation demonstrated AS-IV stably binds six core apoptotic proteins, and comparative analysis with target-specific reference ligands identified Apaf-1 as its primary target with the most favorable binding properties. In rat MCAO/R models, AS-IV alleviated neurological deficits, reduced cerebral infarct volume and improved brain pathological damage; in PC12 cell OGD/R models, it decreased neuronal apoptosis. Western blot and immunofluorescence confirmed AS-IV downregulated pro-apoptotic proteins (cytoplasmic CytC, Apaf-1, BAX, cleaved-Caspase9/3) and upregulated anti-apoptotic Bcl-2. Conclusions: This study clarifies the anti-apoptotic molecular mechanism of AS-IV, it alleviates CIRI by targeting the CytC/Apaf-1 mitochondrial apoptotic pathway. Full article

Satellite remote sensing plays an essential role in wildfire monitoring due to its large-scale observation capability. However, fire targets in satellite imagery are typically extremely small, sparsely distributed, and embedded in complex backgrounds, making accurate segmentation highly challenging for existing methods. To address these challenges, this paper proposes a multi-scale Mamba-based network for tiny fire segmentation, named FireMambaNet. The network adopts a nested U-shaped encoder-decoder architecture, primarily consisting of three modules: the Cross-layer Gated Residual U-shaped module (CG-RSU), the Fire-aware Directional Context Modulation module (FDCM), and the Multi-scale Mamba Attention Module (M2AM). The CG-RSU, as the core building block, adaptively suppresses background redundancy and enhances weak fire responses by extracting multi-scale features through cross-layer gating. The FDCM explicitly enhances the network’s ability to perceive anisotropic expansion features of fire points, such as those along the wind direction and terrain orientation, by modeling multi-directional context. The M2AM model employs a Mamba state-space model to suppress background interference through global context modeling during cross-scale feature fusion, while enhancing consistency among sparsely distributed tiny fire targets. In addition, experimental validation is conducted using two subsets from the Active Fire dataset, which have significant pixel-level sparse features: Oceania and Asia4. The results show that the proposed method significantly outperforms various mainstream CNN, Transformer, and Mamba baseline models on both datasets. It achieves an IoU of 88.51% and F1 score of 93.76% on the Oceania dataset, and an IoU of 85.65% and F1 score of 92.26% on the Asia4 dataset. Compared to the best-performing CNN baseline model, the IoU is improved by 1.81% and 2.07%, respectively. Overall, the FireMambaNet demonstrates significant advantages in detecting tiny fire points in complex backgrounds. Full article

Synthetic Aperture Radar (SAR) enables all-weather maritime surveillance, yet ship-oriented bounding box (OBB) detection remains challenging in complex scenes. Strong sea clutter and dense harbor scatterers often mask the slender characteristics of ships as well as the weak responses of small ships. Meanwhile, the periodicity of angle parameterization introduces regression discontinuities, and near-symmetric, bright-scatterer-dominated signatures further cause heading ambiguity, undermining the stability of orientation prediction. Moreover, in most detectors, multi-scale feature fusion and angle estimation lack explicit coordination, and rotated-box localization performance is often jointly affected by feature degradation and unstable orientation prediction. To this end, we propose a unified framework that simultaneously strengthens multi-scale representations and stabilizes orientation modeling. Specifically, we design a Gaussian-Guided Stage-Aware Deformable Feature Pyramid Network (GSDFPN) and a Coarse-to-Fine Unit-Circle Resolver (CF-UCR). GSDFPN enhances multi-scale fusion with two plug-in components: (i) a Gaussian-guided High-level Semantic Refinement Module (GHSRM) that suppresses clutter-dominated semantics while strengthening ship-responsive cues, and (ii) a Stage-aware Deformable Fusion Module (SDFM) for low-level features, which disentangles channels into a geometry-preserving spatial stream and a clutter-resistant semantic stream, and couples them via deformable interaction with bidirectional cross-stream gating to better capture the inherent slender characteristics of ships and localize small ships. For orientation, CF-UCR decomposes angle prediction into direction-cluster classification and intra-cluster residual regression on the unit circle, effectively mitigating periodicity-induced discontinuities and stabilizing rotated-box estimation. On SSDD+ and RSDD, our method achieves AP/AP${}_{50}$/AP${}_{75}$ of 0.5390/0.9345/0.4529 and 0.4895/0.9210/0.4712, respectively, while reaching AP${}_{s75}$/AP${}_{m75}$/AP${}_{l75}$ of 0.5614/0.8300/0.8392 and 0.4986/0.8163/0.8934, evidencing strong rotated-box localization across target scales in complex maritime scenes. Full article

To address the challenges of small targets, severe background clutter, and high deployment cost in UAV-based power-line defect detection, this paper proposes a lightweight defect detection model based on an improved YOLOv8n. In the downsampling stage, we design an improved lightweight adaptive downsampling module (ADownPro) to replace part of conventional convolutions, which uses a dual-branch parallel structure for stronger feature interaction and depthwise separable convolutions (DSConv) for complexity reduction. In the feature extraction stage, an integration of cross-stage partial connections and partial convolution (CSPPC) is proposed to replace the C2F module for efficient multi-scale feature fusion. In the detection head, mixed local channel attention (MLCA), which combines channel-spatial information and local–global contextual features, is introduced to strengthen defect-focused representations under complex backgrounds. For the loss function, a scale-annealed mixed-quality EIoU loss (SAMQ-EIoU) is proposed by combining iso-center scale transformation, scale factor annealing and focal-style quality reweighting to improve localization accuracy at high IoU thresholds. Experiments on a constructed dataset covering six typical defect categories show that the improved YOLOv8n achieves 91.4% mAP@0.50 and 64.5% mAP@0.50:0.95, with only 1.59 M parameters and 4.9 GFLOPs. Compared with mainstream detectors, the proposed model achieves a better balance between detection accuracy and lightweight design. In particular, compared with the recently proposed YOLOv8n-DSN and IDD-YOLO, it improves mAP@0.50 by 0.6% and 0.8%, and mAP@0.50:0.95 by 1.2% and 4.8%, respectively, while further reducing the parameter count by 1.00 M and 1.26 M, and the FLOPs by 1.7 G and 0.2 G. Moreover, the cross-dataset evaluation on the public UPID and SFID datasets further demonstrate the robustness and generalization ability of the proposed method. Full article

Infrared and visible image fusion aims to integrate complementary information from heterogeneous images captured by different optical sensors based on distinct imaging principles; however, existing methods often exhibit modality bias, leading to weakened targets or the loss of crucial texture details. To address this, we propose MBFTFuse, an adversarial fusion network based on modality balancing and feature tracing, which consists of a triple-path generator and dual discriminators. The architecture employs a generator with a triple-path structure: a central modality-balancing path for deep feature fusion and dual edge feature-tracing paths for modality-specific enhancement. Specifically, a multi-cognitive modality-balancing module is introduced to achieve feature weight equilibrium, while a Feature-Tracing Attention Module self-enhances single-modality features to compensate for information loss in the fusion results. Furthermore, a pixel loss based on intensity histograms is designed to optimize inter-modal balance at the pixel level. Comparative experiments against nine state-of-the-art methods across three public datasets demonstrate that MBFTFuse effectively highlights infrared targets while preserving intricate visible textures. The superior performance of this method in both quantitative metrics and downstream object detection tasks contributes to extending the boundaries of sensor-driven computer vision technologies. Full article

Electric power station confined spaces are high-risk and complex environments characterized by significant illumination variations. Whether safety helmets are properly worn directly affects the operational safety of workers in confined spaces. However, helmet detection in such environments faces several challenges, including drastic lighting changes and difficulties in small-object detection. Moreover, existing object detection models typically contain a large number of parameters, making real-time helmet detection difficult to deploy on field devices with limited computational resources. To address these issues, this paper proposes a lightweight safety helmet wearing detection algorithm named GSA-YOLO. To mitigate the effects of severe illumination variation and detail loss in confined spaces, a GCA-C2f module integrating GhostConv and the CBAM attention mechanism is embedded into the backbone network. This design reduces the number of parameters and computational cost while enhancing the model’s feature extraction capability under challenging lighting conditions. To improve detection performance for occluded targets, an improved efficient channel attention (I-ECA) mechanism is introduced into the neck structure, which suppresses irrelevant channel features and enhances occluded object detection accuracy. Furthermore, to alleviate missed detections of small objects and inaccurate localization under low-light conditions, a P2 detection branch is added to the head, and the WIoU loss function is adopted to dynamically adjust the weights of hard and easy samples, thereby improving small-object detection accuracy and localization robustness. A confined space helmet detection dataset containing 5000 images was constructed through on-site data collection for model training and validation. Experimental results demonstrate that the proposed GSA-YOLO achieves an mAP@0.5 of 91.2% on the self-built dataset with only 2.3 M parameters, outperforming the baseline model by 2.9% while reducing the parameter count by 23.6%. The experimental results verify that the proposed algorithm is suitable for environments with significant illumination variation and small-object detection challenges. It provides a lightweight and efficient solution for on-site helmet detection in confined space scenarios, thereby contributing to the reduction in industrial safety accidents. Full article

Dengue virus (DENV), an important mosquito-borne orthoflavivirus, represents a growing global threat due to its geographic expansion and recent outbreaks worldwide. In resource-limited endemic settings, the development of affordable diagnostic assays is needed. In this study, we developed and validated a colorimetric reverse transcription loop-mediated isothermal amplification assay (RT-LAMP) for the detection of DENV type 3 (DENV-3) using 95 previously diagnosed clinical samples from Southeastern Mexico. Primers targeting the 3′ untranslated region (3′ UTR) of DENV-3 were designed, and assay conditions were standardized. The colorimetric RT-LAMP DENV-3 system achieved a preliminary limit of detection of 1 × 10³ copies per reaction, with 90.7% sensitivity and 100% specificity. The colorimetric format enabled visual readout without specialized equipment, supporting its potential applicability in point-of-care and resource-limited settings. The developed colorimetric RT-LAMP detection for DENV-3 is intended as a rapid screening/triage tool that can trigger confirmatory testing or public-health actions. Full article