Search Results (3,360)

This paper addresses the issue of low detection accuracy in underwater optical images for unmanned underwater vehicles (UUVs) during practical operations, caused by factors such as uneven lighting, blur, complex backgrounds, and target occlusion. To enhance the autonomous perception and control capabilities of UUVs, a high-precision algorithm named MBACA-YOLO is proposed based on the YOLOv13n model. Firstly, the convolutional layers in the backbone network of YOLOv13n are optimized by replacing stride-2 convolutions with stride-1 and embedding SPD layers to enable richer feature extraction. Secondly, the newly proposed MBACA attention mechanism is integrated into the final layer of the backbone network, enhancing effective features and suppressing background noise interference. Thirdly, traditional upsampling in the neck network is replaced with CARAFE upsampling to mitigate noise pollution. Finally, an Alpha-Focal-CIoU loss function is designed to improve the accuracy of bounding box regression for underwater targets. To validate the algorithm’s effectiveness, experiments were conducted on the URPC dataset with the following evaluation protocol: 640 × 640 input resolution, batch size 1, FP32 precision, and standard NMS. All results are from a single random seed with 300 epochs of training. The proposed MBACA-YOLO algorithm outperforms the baseline YOLOv13n model, improving mAP@0.5 and mAP@0.5:0.95 by 3.1% and 2.8% respectively, while adding only 0.49M parameters and 1.0 GFLOPs, with an FPS drop of just 2 frames. This makes it an efficient, deployable perception solution for automated Unmanned Underwater Vehicles (UUVs), significantly advancing intelligent underwater systems. Full article

Monitoring the freshness of Salmo salar within cold chain logistics is paramount for ensuring food safety. However, conventional physicochemical and microbiological assays are impeded by inherent limitations, including destructiveness and significant time latency, rendering them inadequate for the real-time, non-invasive inspection demands of modern industry. Here, we present a novel detection framework synergizing hyperspectral imaging (400–1000 nm) with the Transformer deep learning architecture. Through a rigorous comparative analysis of twelve preprocessing protocols and four feature wavelength selection algorithms (Lasso, Genetic Algorithm, Successive Projections Algorithm, and Random Frog), prediction models for Total Volatile Basic Nitrogen (TVB-N) and Total Viable Count (TVC) were established. Furthermore, the capacity of the Transformer to capture long-range spectral dependencies was systematically investigated. Experimental results demonstrate that the model integrating Savitzky-Golay (SG) smoothing with the Transformer yielded optimal performance across the full spectrum, achieving determination coefficients (R²) of 0.9716 and 0.9721 for the Prediction Sets of TVB-N and TVC, respectively. Following the extraction of 30 characteristic wavelengths via the Successive Projections Algorithm (SPA), the streamlined model retained exceptional predictive precision (R² ≥ 0.95) while enhancing computational efficiency by a factor of approximately six. This study validates the superiority of attention-mechanism-based deep learning algorithms in hyperspectral data analysis. These findings provide a theoretical foundation and technical underpinning for the development of cost-effective, high-efficiency portable multispectral sensors, thereby facilitating the intelligent transformation of the aquatic product supply chain. Full article

As the demand for poultry meat and eggs is increasing in the world, and the use of antibiotics is forbidden in Europe (since 2006), with countries such as the Philippines, Thailand, Bangladesh and China having imposed restriction or prohibitions, researchers and producers have sought for effective non-antibiotic alternatives. Probiotics, prebiotics, synbiotics and phytobiotics are frequently used as alternatives in the field of poultry production. Phytobiotics, plant-derived substances, also referred to as botanicals or phytogenics, are used as animal diets supplements due to their wide range of bioactive compounds (menthol, curcumin, eugenol, allicin and others) and many advantages. They are classified as herbs, spices, plant extracts and essential oils. Some of the benefits offered by the dietary phytobiotics are antimicrobial, antioxidant, digestion stimulant, anti-inflammatory, immunomodulatory, carminative, antiseptic and appetite stimulant, the modulation of gut microbiota and improvement in the intestinal histology. Some representatives of phytobiotics are turmeric, oregano, sage, thyme, black pepper, ginger, garlic, echinacea, rosemary and others. Despite the significant potential of phytobiotics, their widespread adaptation is currently inhibited by challenges regarding cost-effectiveness (high price for raw materials), scarce regulatory frameworks, and inconsistent biological efficacy. The lack of standardization reflects a dual challenge, enclosing both the inherent chemical variability of raw botanical materials and the technical inconsistencies present throughout the industrial manufacturing, and extraction processes as producers use different machinery for extracting and producing the animal feed. To address these systemic impediments, a joint effort across the entire value chain—from primary producers to regulatory authorities—is essential for the development of unified testing protocols and standardization dosage guidelines that ensure the pharmacological safety and reliability of phytobiotic products. Full article

The skin microbiome comprises a diverse community of bacteria, fungi, and archaea, all of which play a foundational role in maintaining skin health, immune tolerance, and barrier integrity. Recent advances in cosmetic science focus on the skin microbiome through the incorporation of prebiotics, probiotics and postbiotics in topical skincare formulations. This review critically examines the scientific understanding of the skin microbiome, explores the mechanisms and extractions of key “biotics” ingredients, and evaluates the clinical and regulatory landscape surrounding their use in the cosmetic industry. Despite promising scientific data and early clinical findings, there are notable challenges, including limited robust in vivo evidence, regulatory ambiguity, difficulties in formulation, and inconsistent definition and marketing claims. Regulatory harmonisation and the development of standardised testing protocols are necessary to fill the gap in today’s research and to maximise the benefits of “biotics” in the cosmetic industry. Full article

Background and Objectives: The regeneration of the pulp–dentin complex represents an alternative to conventional root canal treatment, aiming to preserve tooth biology and function. Cell-free regenerative endodontic therapy (CF-RET) exploits endogenous stem cells from the periapical region without ex vivo cell manipulation. Despite growing interest, the biological mechanisms, clinical indications, and predictability of CF-RET remain not clearly defined. This structured narrative review aimed to update a previous review by analyzing recent human studies on CF-RET. Materials and Methods: This review was conducted using the PRISMA 2020 guidelines to guide transparent reporting of the literature search and study selection process and was registered in PROSPERO (CRD420251075131). In vitro and in vivo human studies published between January 2017 and December 2024 investigating CF-RET were included, while studies involving cell transplantation, non-human models, case reports, and reviews were excluded. Study selection, data extraction, and quality assessment using the QuADS tool were performed, and the evidence was synthesized using a qualitative narrative approach. Results: Sixty-four studies were included. In vitro studies reported favorable effects of growth factors, exosomes, and biomimetic scaffolds on stem cell viability, migration, proliferation, odontogenic differentiation, and angiogenesis, while neurogenic differentiation was less consistently investigated. Scaffold composition, microstructure, and rheological properties were also considered. In vivo studies mainly focused on immature teeth with incomplete root development and demonstrated positive clinical and radiographic outcomes, including root development and canal diameter reduction. Conclusions: The current evidence supports the biological potential of CF-RET as a regenerative approach; however, substantial heterogeneity, the limited number of clinical studies and the absence of standardized protocols preclude definitive conclusions, highlighting the need for further well-designed translational and clinical investigations considering clinical applicability. Full article

In this paper, we propose a standardized framework for automatic tuberculosis (TB) detection from cough audio and routinely collected clinical data using machine learning. While TB screening from audio has attracted growing interest, progress is difficult to measure because existing studies vary substantially in datasets, cohort definitions, feature representations, model families, validation protocols, and reported metrics. Consequently, reported gains are often not directly comparable, and it remains unclear whether improvements stem from modeling advances or from differences in data and evaluation. We address this gap by establishing a strong, well-documented baseline for TB prediction using cough recordings and accompanying clinical metadata from a recently compiled dataset from several countries. Our pipeline is reproducible end-to-end, covering feature extraction, multimodal fusion, cougher-independent evaluation, and uncertainty quantification, and it reports a consistent suite of clinically relevant metrics to enable fair comparison. We further quantify performance for cough audio-only and fused (audio + clinical metadata) models, and release the full experimental protocol to facilitate benchmarking. This baseline is intended to serve as a common reference point and to reduce methodological variance that currently holds back progress in the field. Full article

Alveolitis remains a common postoperative complication following tooth extraction, characterized by inflammation and delayed socket healing. Collagen-based materials have shown promise in promoting tissue regeneration and reducing inflammation. This review evaluates the efficacy of collagen in the prevention of alveolitis, with a focus on the development and application of topical delivery systems such as gels and collagen sponges. Special attention is given to the local application of these systems within the extraction socket and their performance under oral conditions. The study analyzes current evidence on the pathogenesis of alveolitis, the biological properties of collagen relevant to wound healing, and pharmaceutical strategies for enhancing its clinical effectiveness. The findings support the feasibility of using biodegradable, site-specific collagen-based formulations for alveolitis prevention. Such systems may provide a prolonged therapeutic effect, stabilize blood clots, reduce microbial contamination, and support angiogenesis and osteogenesis throughout the healing process. This approach offers a promising direction for improving post-extraction management protocols in dental surgery. Full article

Surface electromyography (EMG) can drive assistive training systems in neurorehabilitation. This systematic review and meta-analysis evaluated whether EMG-driven device-assisted rehabilitation improves upper-limb (UL) and lower-limb (LL) outcomes versus conventional therapy (CT). The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and was registered in PROSPERO (CRD420251029642). We searched databases for randomized controlled trials in adults with neurological disorders; three reviewers screened records, extracted data, and assessed risk of bias using the Revised Cochrane risk-of-bias tool (RoB 2). Seven trials (n = 160) were included, all in post-stroke populations (UL: 3; LL: 4). UL trials showed mixed findings, and pooled effects were imprecise and not statistically significant for activities of daily living (ADL) (standardized mean difference, SMD −0.55; p = 0.09; I² = 0%). LL pooled estimates showed no significant differences in motor function (Fugl-Meyer Assessment, lower extremity, FMA-LE) (mean difference, MD −1.69; p = 0.40), walking independence (Functional Ambulation Categories, FAC) (MD −0.24; p = 0.61), balance (SMD 0.12; p = 0.61), mobility (Timed Up and Go, TUG) (MD −3.24; p = 0.71), or endurance (SMD −0.19; p = 0.43). Current evidence does not demonstrate clinical superiority over CT. EMG-driven systems may be used as an adjunct, but larger trials with standardized protocols, implementation outcomes, and neurological pathologies beyond stroke are needed. Full article

Background: Chronic shoulder pain is a frequent musculoskeletal complaint that significantly affects function, productivity, and quality of life. Mesenchymal stem cell (MSC)-based therapies have emerged as a potential regenerative option due to their anti-inflammatory and tissue-repair properties. This study aims to evaluate the safety and short-term effectiveness of intra-articular injections of umbilical cord-derived MSCs (UC-MSCs) in patients with chronic shoulder pain. Methods: A retrospective pragmatic observational study was conducted at the Regenerative Medicine Institute in Costa Rica. Medical records were reviewed to extract clinical, sociodemographic, and treatment-related variables. The primary outcome was functional improvement measured with the American Shoulder and Elbow Surgeons (ASES) score. Changes between baseline and the 3-month follow-up were analyzed using paired tests, effect size calculations, and regression models to explore predictors of treatment response. Results: Twenty patients met the inclusion criteria. A significant improvement in shoulder function was observed, with a mean ASES increase of 17.17 points, exceeding the minimum clinically important difference of 12. Sixty percent of patients achieved clinically meaningful improvement. Effect size estimates indicated a large magnitude of change. Regression analyses showed that baseline ASES predicted follow-up scores, while higher UC-MSC doses were associated with greater functional improvement. No adverse events were documented during the study period. Conclusions: The study shows that UC-MSC therapy is a safe, minimally invasive, and clinically beneficial option for chronic shoulder pain. These findings support the therapeutic potential of MSCs and highlight the need for larger controlled studies to validate long-term efficacy and optimize treatment protocols. Full article

Accurate delineation of rural settlements at large spatial extents is fundamental to territorial spatial governance, rural revitalization, and the improvement of human living environments. However, in medium-resolution remote sensing imagery, rural settlement patches are typically small, morphologically complex, and easily confused with other impervious surfaces. As a result, existing products still fall short in characterizing these features. Here, we propose a lightweight Transformer-based semantic segmentation model, SELPFormer, and develop a multi-source fusion automatic labeling pipeline that integrates Global Impervious Surface Dynamics dataset, OpenStreetMap spatial priors, and nighttime lights constraints. Built upon SegFormer as the backbone, SELPFormer introduces a lightweight pyramid pooling module at the deepest feature level to aggregate multi-scale global context and embeds an SCSE channel–spatial attention mechanism into deep features to suppress background interference. In addition, it incorporates an efficient local attention module into multi-scale lateral connections to enhance boundary and texture representations, thereby jointly improving small-object recognition and fine boundary preservation. We evaluate the proposed method using Landsat multispectral imagery covering five provinces on the North China Plain. SELPFormer achieves IoU = 74.23%, mIoU = 86.43%, F1 = 85.21%, OA = 98.69%, and Kappa = 0.8452 under a unified training and evaluation protocol, yielding IoU gains of +1.44, +3.98, and +12.35 percentage points over SegFormer, U-Net, and DeepLabV3+, respectively. SELPFormer has 15.44 M parameters and attains a parameter efficiency of 3.93% IoU per million parameters and an ROC-AUC of 0.993, indicating strong threshold-independent discriminative capability. These results indicate that the proposed method can effectively extract rural settlements from medium-resolution imagery and provides a generic “global–channel–local” collaborative framework for model design and data construction. Full article

Background: Post-extraction alveolar bone resorption complicates implant planning and compromises functional and aesthetic outcomes. High-power lasers, including surgically applied Er:YAG and Nd:YAG lasers, as well as Nd:YAG-based photobiomodulation (PBM), have been proposed as adjunctive approaches to decontaminate extraction sockets, modulate inflammation, and stimulate osteogenesis, potentially limiting post-extraction ridge collapse. Methods: This systematic review and meta-analysis included prospective and retrospective clinical studies evaluating changes in alveolar ridge height, width, volume, or density following tooth extraction treated with Er:YAG, surgically applied Nd:YAG, or Nd:YAG-based PBM. Outcomes were assessed using cone-beam computed tomography (CBCT) or calibrated mechanical or optical measurement methods. Study selection followed PRISMA guidelines. Quantitative synthesis was performed using random-effects meta-analysis, and certainty of evidence was assessed using the GRADE approach. Results: All laser modalities demonstrated statistically and clinically significant preservation of alveolar bone compared with standard care. Er:YAG laser therapy resulted in a mean ridge preservation of 1.12 mm (95% CI: 0.9–1.4), while surgically applied Nd:YAG achieved a comparable effect of 1.15 mm (95% CI: 0.88–1.4). Nd:YAG-based PBM showed the most consistent effect, with a mean difference of 1.20 mm (95% CI: 1.0–1.4) and the lowest heterogeneity (I² = 22%). The largest effects were observed within the first month after extraction (mean difference 1.26 mm) and diminished with longer follow-up. CBCT-based assessments demonstrated the highest measurement precision, with an average effect of 1.32 mm. Overall certainty of evidence was rated as moderate due to risk of bias, incomplete methodological reporting, and possible publication bias. Conclusions: Er:YAG, Nd:YAG, and Nd:YAG-based PBM represent effective adjunctive approaches for alveolar ridge preservation following tooth extraction, particularly during the early healing phase. Their effects appear enhanced when combined with barrier membranes or osteoconductive grafting materials. CBCT should be preferred for outcome assessment in both clinical practice and research. These findings support the evidence-based integration of laser technologies into ridge preservation protocols in implant dentistry and oral surgery. Full article

Background. Virtual reality (VR) is emerging as a non-pharmacological tool to support rehabilitation and self-management. Evidence of its effectiveness, however, remains fragmented. This umbrella review synthesized systematic reviews and meta-analyses on VR interventions in chronic conditions. Methods. Following the Joanna Briggs Institute Manual for Evidence Synthesis, comprehensive searches were conducted in MEDLINE, CINAHL, Cochrane Database, Web of Science, and Scopus. Eligible studies were systematic reviews and meta-analyses assessing VR interventions. Two reviewers independently performed screening, quality appraisal, and data extraction. Results. Seventeen reviews, including 229 primary studies, were analyzed. Stroke and chronic obstructive pulmonary disease were most frequently investigated. VR tools ranged from web- and smartphone-based systems to wearable devices and interactive games. Significant improvements were reported in respiratory outcomes, functional mobility, balance, and psychological symptoms. Cognitive effects were mixed. Reported adverse events, mainly cybersickness and dizziness, were mild. Conclusions. VR may improve physical, respiratory, psychological, and selected cognitive outcomes in chronic conditions. Despite study heterogeneity, evidence supports its integration into chronic care. Future work should standardize protocols, assess long-term effects, broaden target populations, and address equity and ethical issues to fully realize VR’s potential as a person-centered tool. Full article

Electroencephalogram (EEG) signals serve as a primary input for brain–computer interface (BCI) systems, and extensive research has been conducted on EEG-based emotion recognition. However, because EEG signals are inherently contaminated with various types of noise, the performance of emotion recognition is often degraded. Furthermore, the use of a Band Feature Extraction Neural Network (BFE-Net), a state-of-the-art (SOTA) method in this field, has limitations with respect to independent band-wise feature extraction and a simplistic band aggregation process to obtain final classification results. To address these problems, this study proposes the noise-robust band-attention BFE-Net framework, aiming to improve the conventional BFE-Net from two perspectives. First, we implement multiple-input, multiple-output (MIMO)-based preprocessing. Specifically, we utilize multichannel minima-controlled recursive averaging for precise non-stationary noise covariance estimation and generalized eigenvalue decomposition for subspace filtering to enhance the signal-to-noise ratio. Second, we propose an attention-based band aggregation mechanism. By integrating a band-wise self-attention mechanism, the model learns dynamic inter-band dependencies for more sophisticated feature fusion for classification. Experimental results on the SEED and SEED-IV datasets under a subject-independent protocol show that our model outperforms the SOTA BFE-Net by 3.27% and 3.34%, respectively. This confirms that rigorous MIMO noise reduction, combined with frequency-centric attention, significantly enhances the reliability and generalization of BCI systems. Full article

Soil harbors the highest concentration of microorganisms in ecosystems, and their molecular characterization through high-throughput sequencing is essential for metagenomic studies. However, obtaining high-quality, high-concentration DNA is limited by physicochemical properties (pH, heavy metals, humic acids) and adsorption to clay minerals. Although standardized commercial protocols exist, they present variable limitations depending on soil type. This study developed and validated the National Center for Genetic Resources—Microorganism Collection (CNRG-CM) method, which incorporates innovative pre-washing steps using phosphate-buffered saline (PBS) and sodium phosphate to effectively remove inhibitory humic acids and metal ions, combined with cetyltrimethylammonium bromide (CTAB)/chloroform extraction to achieve high-molecular-weight metagenomic DNA isolation. The CNRG-CM method was applied to three diverse soil types with variable physicochemical properties, recovering DNA concentrations ranging from 1000 to 1300 ng/μL ith a yield of 30 to 48 µg/g⁻¹, significantly exceeding those obtained with a standard commercial kit with maximum DNA concentrations of 360 ng/μL and a yield of 43 µg/g⁻¹. The CNRG-CM protocol is established as an effective and adaptable alternative for metagenomic DNA extraction across diverse agricultural and ecological contexts. It enables subsequent metagenomic studies of soil microbial communities. Full article

Background: Digital implant impressions using intraoral scanners are increasingly adopted; however, their accuracy remains challenging in complete-arch and extended edentulous scenarios due to limited anatomical reference points and cumulative stitching errors. Various splinting techniques, scan-body modifications, and auxiliary geometric devices have been proposed to enhance digital accuracy, yet the available evidence is highly heterogeneous and lacks comprehensive synthesis. Methods: This scoping review was conducted according to PRISMA-ScR guidelines. A systematic search of PubMed/MEDLINE, Embase, Scopus, and Web of Science databases identified studies evaluating materials, designs, or techniques intended to splint, stabilize, or geometrically augment intraoral scan bodies in digital implant workflows. In vitro, clinical, and mixed-design studies were included. Data were extracted descriptively and synthesized narratively. Results: Seventy-three studies met the inclusion criteria, the majority of which were in vitro investigations focused on fully edentulous arches. Splinting strategies included direct resin-based connections, rigid or semi-rigid auxiliary geometric devices, modified scan bodies with extensional geometries, and artificial landmarks. Most studies reported improved trueness, precision, or scanning efficiency when rigid or geometrically enriched devices were used, particularly in long-span or angulated implant configurations. However, flexible or optically interfering splints occasionally reduced accuracy, and outcomes were strongly scanner-dependent. Conclusions: Splinting and auxiliary scanning strategies generally enhance the accuracy of complete-arch digital implant impressions, especially when rigid, well-engineered, or geometrically complex designs are employed. Modified scan bodies and calibrated auxiliary devices appear particularly promising, while flexible splints may be counterproductive. Standardized protocols and further in vivo validation are required to optimize digital implant workflows. Full article