Search Results (1,172)

Background/Objectives: Data augmentation is a foundational component of modern deep learning for enhancing robustness and generalization. However, medical imaging lacks a universally reliable augmentation strategy, forcing researchers into an inefficient “augmentation lottery” that hinders experimental progress and reproducibility. To address this challenge, we introduce Stepwise Upper and Lower Boundaries Augmentation (SULBA), a simple, parameter-free framework designed to eliminate per-task augmentation tuning. Methods: SULBA generates training variations through stepwise cyclic shifts applied along data dimensions, making it inherently applicable to 2D, 3D, and higher-dimensional medical imaging data. To evaluate the efficacy of SULBA as a default DA strategy, we performed benchmarking across 27 publicly available datasets spanning classification and segmentation tasks and 10 convolutional and transformer-based architectures using standard deep learning performance metrics. Results: The results demonstrate that SULBA achieves the highest overall performance and consistently outperforms 16 widely used standard augmentation techniques while delivering robust and reliable improvements without task- or parameter-specific tuning Conclusions: SULBA establishes a principled universal default for data augmentation in medical imaging, with the potential to accelerate the development of generalizable and reproducible medical AI systems. Full article

In project-based organizations, novices engaged in project-contextualized learning often struggle to balance sustained project learning with immediate task delivery, creating a tension between developmental sustainability and execution sustainability. While informal support mechanisms such as apprenticeship help alleviate this tension, their effectiveness remains limited. To address this issue, this study adopts a Design Science Research approach to develop a generative AI-driven project scaffolding system prototype. The study contributes design knowledge comprising two core elements. First, based on the task execution process, scaffolding support is organized into three dimensions, namely contextualization, cognitive guidance, and cognitive evolution, which correspond to the progression from task understanding to cognitive construction. Second, a cognition-driven scaffolding mechanism is constructed through prompt-driven and knowledge-augmented generation, enabling human-centered intelligent guidance, augmentation, and automation during task execution. Evaluation in a software implementation firm suggests that the system may improve task output quality and support novices’ application of task-relevant strategies in subsequent tasks. These findings indicate the system’s potential to support the sustainability of both project learning and task execution in project practice. This study provides design insights for embedding GenAI-driven scaffolding in project practice, helping organizations in similar project contexts establish sustainable project support approaches. Full article

Surface-enhanced Raman spectroscopy (SERS) has evolved from a fundamental optical phenomenon to a powerful, molecule-specific analytical technique capable of detecting ultra-trace-level species across biomedicine, catalysis, environmental monitoring, and national security applications. In this review, we summarize recent advances in SERS probe design and fabrication along three major directions: (i) engineering plasmonic hotspots with enhanced field confinement to achieve stronger and more uniform signals; (ii) analyte-directed strategies that precisely position and retain target molecules via tailored surface chemistries, nanoscale confinement, and on-surface reactions for single hotspot SERS; and (iii) hybrid architectures integrating plasmonic metals with functional materials, including high entropy materials, semiconductors, and graphene and other 2D materials, to synergistically couple electromagnetic and chemical enhancement mechanisms. Despite significant progress, key challenges remain for practical applications outside laboratories, including substrate reproducibility and stability, diverse analyte compatibility, unknown molecule identification and standardized quantitative performance in complex environments. We highlight emerging solutions, such as large-area nanomanufacturing for controlled nanoscale gaps, high-resolution Raman mapping for spatial–temporal characterization, density-functional-theory-guided molecular interpretation, and machine-learning-enabled spectral analysis. Advances in foundational AI models and data-driven discovery are positioning SERS to become an increasingly versatile platform, from decoding unknown molecular structures to analyzing complicated multi-component systems for environmental, biomedical, and national security applications with high sensitivity and selectivity. Full article

Worldwide, breast cancer is the leading cause of death in women. This emphasizes the significance of an accurate breast cancer detection system. This study presents a unified framework for segmentation of breast cancer using multimodal imaging, such as histopathology, MRI, mammogram, and ultrasound. This framework integrates the CNN with Transformer modules and has three core technical innovations. First, features are extracted using an encoder–decoder design. The encoder has Residual Blocks with a base channel of 32, following feature extraction, which are progressively mapped and downsampled into four stages (32 → 64 → 128 → 256) of channels. The spatial channel is reduced using MaxPool2d operations from 256 × 256 to 128 × 128, 64 × 64, 32 × 32, and 16 × 16. After further convolutional refinement, a Transformer encoder is used on the 16 × 16 feature maps in the bottleneck. The Transformer comprises four encoders with multi-head self-attention (eight heads) and a 4.0 MLP ratio, enabling the model to capture local and global contextual dependencies at the lowest resolution. The proposed framework is trained with a learning rate of 1 × 10⁻⁴, up to 50 epochs with early stopping (patience = 12), using a combined Dice and binary cross-entropy loss that balances pixel-wise accuracy and overlap-based learning. Gradient clipping with a maximum norm of 5.0 is used to ensure training stability; ReduceLROnPlateau (factor = 0.5, patience = 5) is used to dynamically adjust the learning rate; and early stopping is used to prevent overfitting. To improve generalization and enhance robustness to data variability, data augmentation techniques such as random horizontal and vertical flips, intensity variations, and small rotations (±15°) are applied. Incremental learning was implemented in this study as a warm-start fine-tuning strategy, where the model was initialized based on learned weights from a previously trained model instead of training from scratch. This is done by loading saved checkpoints of the best-performing model and continuing training on a new dataset. The performance of the proposed framework is evaluated on four publicly available datasets and one local dataset, such as BUS-UCLM, BUSI, BreastDM, TNBC NucleiSegmentation, and BCSD-2024. The impressive results are achieved with Dice scores of 0.974 on ULCM, 0.975 on BUSI, 0.971 on BreastDM, 0.904 on TNBC nuclei segmentation, and 0.982 on BCSD-2024. The proposed model consistently performed better than classical U-Net models. Full article

Plastic design enables efficient structural systems by exploiting controlled inelastic deformation and force redistribution. While mature in steel structures due to stable ductility and well-defined yielding, its extension to reinforced concrete (RC) remains challenging because cracking, stiffness degradation, confinement dependency, and progressive damage govern deformation capacity and collapse mechanisms. This paper presents a state-of-the-art review of optimal plastic design methodologies for RC structures by tracing the evolution from classical plasticity theory to modern damage-informed, reliability-oriented, and sustainability-driven formulations. A systematic and structured literature review of more than 90 peer-reviewed journal articles (1990–2025) was conducted using Scopus, Web of Science, and ScienceDirect. The selected studies are classified by structural system type, plastic analysis approach, constitutive modeling strategy, and strengthening technique, including CFRP and hybrid fiber systems, optimization framework, and uncertainty treatment. The review highlights how nonlinear elasto-plastic and damage–plasticity models improve the prediction of plastic hinge development, redistribution, and failure-mode transitions, and how metaheuristic optimization, topology optimization, surrogate modeling, and machine learning are increasingly used to manage discrete design variables and computational cost. Reliability-based methods (e.g., FORM/SORM and simulation) are shown to be essential for quantifying deformation-capacity uncertainty and ensuring consistent collapse-prevention performance. A comparative assessment of nine plastic design methodologies is also provided, identifying their core assumptions, limitations, and domains of applicability within a structured evaluative framework. Remaining challenges include robust deformation-capacity prediction, reproducible calibration of damage models, and integration of life-cycle sustainability criteria within reliability-constrained plastic optimization. Future research directions are proposed toward multi-objective reliability-based design, durability-informed plastic modeling, and hybrid physics-informed AI-assisted workflows. Full article

Background: Age-related macular degeneration (AMD) is a common retinal degenerative disease linked to adaptive immune response dysregulation. This study aimed to identify shared immune-related biomarkers and explore their underlying mechanisms. Methods: GSE29801 and GSE135092 served as training and validation sets. Adaptive immune response-related genes (AIR-RGs) from MSigDB were intersected with AMD-related differentially expressed genes (DEGs) to identify candidate genes. Machine learning algorithms were applied to screen biomarkers, validated in datasets and a mouse model of choroidal neovascularization by qPCR. A nomogram was constructed and assessed. GSEA and immune infiltration analyses explored mechanisms and immune microenvironment associations. Results: A total of 148 DEGs were identified, yielding 15 candidate genes after intersection with AIR-RGs. Machine learning identified C3 and HLA-DOA as potential biomarkers, with their differential expression validated across datasets. A nomogram based on these biomarkers demonstrated good predictive performance for AMD pathology (AUC = 0.795). Biomarkers were associated with some immune-inflammatory pathways. Significant differences in immune cell infiltration were observed between AMD and control groups, with biomarkers positively correlated with differentially infiltrated immune cells, such as natural killer cells. Conclusions: The identification of the established biomarker C3 serves as a proof-of-principle for the analytical approach, rather than a novel discovery, thereby validating the model’s capacity to uncover other critical immune targets. Consequently, C3 and HLA-DOA serve as potential biomarkers for AMD, significantly correlated with disease progression via immune pathways and offering insights for immune-based therapeutic strategies. Full article

Objectives: Myelodysplastic syndromes (MDSs) are a heterogeneous group of clonal hematopoietic disorders characterized by ineffective hematopoiesis, genomic instability, and a high risk of progression to acute myeloid leukemia. Oxidative stress (OS) has emerged as a central factor in MDS pathophysiology, contributing to DNA damage, altered cellular signaling, and disease progression. Recent advances in artificial intelligence (AI) and machine learning (ML) offer a transformative approach for integrating multidimensional datasets including oxidative stress markers, hematologic parameters, and molecular profiles to enhance diagnosis, prognostication, and therapeutic monitoring in MDS. Methods: A comprehensive literature search was conducted in PubMed and Scopus, using the keywords “OS biomarkers,” “AI,” and “MDS’’. Results: Modified redox biomarkers can be correlated with oxidative imbalance and disease progression. ML models such as neural networks, decision trees, and support vector machines effectively capture complex relationships among redox biomarkers, enhancing risk stratification and prediction of treatment response. AI-driven proteomic analyses further revealed OS-related protein signatures linked to MDS pathophysiology. Overall, AI and ML enable the transformation of multidimensional OS data into clinically actionable tools for personalized management in MDS. Conclusions: Integrating biomarker research with AI-based analytics holds promise for advancing personalized diagnostics, prognostication, and therapeutic strategies in MDS, paving the way toward precision medicine. Full article

Facial expression recognition (FER) is a well-established task in computer vision, yet its application to non-photorealistic domains, such as anime and manga, remains largely underexplored. The stylized, exaggerated, and often non-proportional facial features of illustrated characters present unique challenges for deep learning models trained predominantly on realistic imagery. In this work, we construct a balanced dataset of 3000 manga and anime face images spanning six emotion categories (Angry, Embarrassed, Happy, Manic–Euphoric, Sad, Scared) and conduct a systematic comparison of two major deep learning paradigms: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Specifically, we evaluate ResNet-18, ResNet-50, ViT-B/16, and ViT-S/16 under four fine-tuning strategies: linear probing, partial fine-tuning, full fine-tuning, and progressive unfreezing, enabling a controlled comparison of both architectural families and transfer learning depth. Our results show that fine-tuning strategy significantly impacts performance: the best configuration (ViT-B/16 with progressive unfreezing) achieves 81.33% test accuracy (single run, seed 42), compared to 61.33% for the weakest linear probe baseline (ViT-S/16), a gap of 20.00 percentage points. To isolate architectural differences from strategy effects, we note that under full fine-tuning, the only strategy applied identically to all four models, ViT-S/16 (76.00%) outperforms ResNet-18 (74.44%) by 1.56 percentage points and ViT-B/16 (74.22%) by 1.78 percentage points, confirming a modest but consistent architectural advantage for Transformers once backbone adaptation is permitted. Vision Transformers benefit disproportionately from fine-tuning, and the relative ranking of architectures changes across fine-tuning regimes. Confusion matrix analysis reveals persistent cross-class confusion between visually similar emotions (e.g., Happy vs. Embarrassed), while the highly distinctive Manic–Euphoric category is consistently well recognized across all architectures. To the best of our knowledge, this is the first work to conduct a controlled multi-architecture, multi-strategy transfer learning benchmark specifically for FER in anime and manga, revealing findings that are not predictable from photographic FER literature and that carry direct practical implications for model selection in non-photorealistic visual recognition tasks. The anime and manga domain provides a uniquely controlled testbed for studying transfer learning under deliberate stylization, where the domain gap from realistic imagery is not an artifact of image degradation or environmental noise but a principled artistic choice with codified visual conventions; observing that fine-tuning depth dominates architectural choice in this domain suggests the same conclusion likely holds in other non-photorealistic transfer scenarios such as medical illustrations, architectural drawings, and synthetic training data. Full article

Chirality has emerged as a critical determinant in the design, efficacy, and environmental behavior of modern insecticides. While a significant proportion of agrochemicals are inherently chiral, most are still commercialized as racemic mixtures, despite well-documented differences in biological activity, toxicity, and degradation pathways between enantiomers. In this review, we provide a comprehensive and critical analysis of advances in the stereoselective synthesis and resolution of chiral insecticides, with particular emphasis on neonicotinoids, pyrethroids, and oxadiazines, including indoxacarb. A systematic survey of the literature (1985–2025), including peer-reviewed articles and patents, reveals that multiple strategies have been developed to access enantiomerically enriched compounds, including asymmetric organocatalysis, transition-metal catalysis, chiral-pool approaches, biocatalytic transformations, and chromatographic resolution techniques. Among these, recent developments in photoredox catalysis, recyclable metal complexes, and enzyme-mediated processes have significantly improved enantioselectivity and scalability, bridging the gap between academic methodologies and industrial applications. Despite these advances, challenges remain in achieving cost-effective, sustainable, and universally applicable asymmetric processes. Importantly, the relationship between stereochemistry and biological performance underscores the need for integrating synthetic chemistry with toxicological and environmental studies. Future directions point toward the incorporation of green chemistry principles, continuous-flow processes, and computational tools, including machine learning and molecular modeling, to accelerate the rational design of enantiopure agrochemicals. This review highlights both the progress achieved and the critical gaps that must be addressed to realize the potential of stereoselective insecticide development fully. Full article

Introduction: Declines in children’s fine motor skills (FMS) are increasingly reported across UK primary education, raising concerns for school readiness, independence, and long-term health. This study examined whether structured classroom-based cooking activities could enhance FMS in children aged 7–8 years. Methodology: Informed by physical literacy and experiential learning, a six-week intervention (n = 30) used progressive pizza-making sessions to target effective pincer grip, consistent hand-eye coordination, and control over hand and wrist motions, a mixed-methods design that combined curriculum-aligned observational assessments with qualitative field notes. Results: Statistically significant progressive increases were observed across effective pincer grip, consistent hand-eye coordination, and hand and wrist control (χ², p < 0.001), suggesting improvements in fine motor competence within this sample. Performance increased from 30–40% skill demonstration in session one to 70–85% by session five. Qualitative data indicated enhanced confidence, task persistence, and independence. Discussion: In this sample, authentic, goal-directed cooking tasks were associated with improvements in FMS, reinforcing links to cognitive and academic outcomes. Cooking offers a low-cost, inclusive approach that integrates movement, learning, and health priorities. Embedding structured cooking within the curriculum may provide a scalable strategy to support FMS development and health equity, establishing a strong foundation for future controlled research. Full article

Biomechanics sits at the interface of engineering and medical sciences, offering essential insight into how tissues, organs, and biological systems respond to mechanical loading. This review brings together recent advances in musculoskeletal and cardiovascular biomechanics, illustrating how experimental techniques, computational modeling, and multiscale analysis are used to characterize load transfer, tissue deformation, fatigue, and injury mechanisms. In musculoskeletal applications, predictive simulations, wearable sensing technologies, and neuromechanical assessment tools support improved injury prevention, rehabilitation planning, and assistive device development. In the cardiovascular domain, patient-specific modeling, fluid–structure interaction analyses, and advanced imaging approaches clarify how hemodynamics, vessel wall mechanics, and device–tissue interactions influence disease progression, implant performance, and therapeutic outcomes. Emerging technologies including artificial intelligence, machine learning, digital twin frameworks, biofabrication, soft robotics, and self-powered sensing are enabling data-driven, real-time, and personalized interventions that connect mechanistic understanding with clinical practice. Despite these advances, challenges remain in accounting for individual variability, integrating multiscale data, and translating computational predictions into clinically validated solutions. By emphasizing interdisciplinary strategies that unite biomechanics, computational analytics, and innovative device engineering, this review outlines a pathway toward predictive, patient-centered healthcare and next-generation therapeutic and rehabilitation solutions. Full article

Historically, pharmaceutical formulation development relied heavily on trial-and-error experimentation, which was useful for empirical progress but often provided limited mechanistic understanding and insufficient efficiency for increasingly complex drug products. The introduction of Design of Experiments (DoE) and Quality by Design (QbD) established a more systematic framework for studying formulation variables, manufacturing parameters, and Critical Quality Attributes (CQAs). Approaches such as factorial designs, response-surface methodology, and mixture designs have therefore become central to modern pharmaceutical development because they improve experimental efficiency and support the definition of design space. However, as formulations become more nonlinear, high-dimensional, and multi-objective, these classical approaches may no longer be sufficient on their own. This review examines the evolution of experimental design in pharmaceutical research, from one-factor-at-a-time experimentation to structured DoE/QbD strategies, and then to emerging intelligent optimization methods. Its central objective is to clarify when conventional DoE/QbD remains appropriate and when it should be complemented by machine learning, Bayesian optimization, digital twins, and closed-loop experimental systems. The review first summarizes the foundations and strengths of classical experimental design; then, it discusses its practical limitations in complex formulation settings, and finally evaluates how data-driven and hybrid approaches can extend pharmaceutical development. Evidence from tablets, capsules, nanocarriers, transdermal patches, and biotherapeutic systems suggests that intelligent optimization can improve predictive performance and experimental efficiency when used alongside, rather than instead of, established pharmaceutical development principles. Full article

Plant-derived nanovesicles (PDNVs) are a class of nanoscale vesicles derived from plant tissues; they are particles with a lipid bilayer and no ability to replicate autonomously. As a type of bioactive natural nanocarrier, they demonstrate immense potential for application in 21st-century nanomedicine, skincare and nutritional health, owing to their excellent biocompatibility, low immunogenicity and targeted delivery capabilities. However, the clinical translation of PDNVs still faces key bottlenecks, including low extraction efficiency, complex purification processes, and immature engineering modification techniques. Compared to the wealth of systematic reviews in the field of Mammalian Extracellular Vesicles (M-EVs), research on PDNVs still lacks a comprehensive exposition of its multifaceted research progress. This review endeavours to comprehensively summarise the shortcomings over the last 60 years regarding PDNV purification processes, research progress, composition and characterisation, engineering modifications, functional mechanisms, clinical translation and market regulation. It discusses the feasibility of innovative approaches such as AI deep learning technologies, interdisciplinary integration and cross-application, and outlines the latest frontiers in PDNV research. It provides comprehensive and reliable reference material for future research and application strategies regarding PDNVs, offering theoretical support and practical guidance to overcome barriers to their industrialisation. This will facilitate the transition from limited laboratory research to clinical application and drive technological innovation in the next generation of naturally derived nanomedicines. Full article

Monoethanolamine (MEA) remains the predominant solvent for carbon dioxide (CO₂) capture due to its rapid reaction kinetics, substantial absorption capacity, and demonstrated industrial effectiveness. Despite its established status, MEA-based systems are undergoing continuous development to lower energy requirements, enhance solvent stability, and expand operational adaptability. This review provides a critical assessment of recent progress in MEA-based CO₂ capture, encompassing molecular-level understanding, advancements in reactor and process design, solvent modification strategies, and system-wide optimization. Recent theoretical and experimental research has improved the understanding of CO₂ absorption mechanisms in MEA, highlighting the effects of reaction-product buildup, interfacial phenomena, and free amine availability on mass-transfer efficiency. Reboiler duty and comparable work have significantly decreased as a result of advances in process intensification, improved regeneration systems, and energy-integration techniques. New hybrid strategies that partially decouple capture from thermal regeneration, such as combined absorption–mineralization pathways, show promise for long-term CO₂ sequestration. To address regeneration energy, corrosion, degradation, and cyclic stability, this review examines advances in MEA-based solvents, including aqueous blends, non-aqueous and biphasic systems, ionic liquids, and deep eutectic solvent hybrids. It also critically assesses the trade-offs of developments in intensified contactors, surfactants, nanomaterials, and catalysts. The growing role of digital optimization, machine learning, and computational modeling in MEA process design and control is highlighted. Overall, this analysis underscores MEA’s continued importance as a versatile platform for next-generation carbon capture, utilization, and storage. Full article

Chronic obstructive pulmonary disease (COPD) is characterized by persistent airflow limitation, chronic airway inflammation, and immune dysregulation, and currently available therapies remain insufficient to effectively halt disease progression. In this study, we used an integrative, hypothesis-generating strategy to investigate the potential mechanisms of baicalein against COPD by combining multi-dataset transcriptomic analysis, single-cell transcriptomics, machine learning-based feature selection, Mendelian randomization (MR), molecular simulation, virtual knockout analysis, and in vitro validation. Putative targets of baicalein were predicted using CTD, SEA, and SwissTargetPrediction, and were intersected with COPD-related genes collected from GeneCards and OMIM. Four GEO datasets (GSE20257, GSE42057, GSE76925, and GSE130928) were integrated after batch-effect correction, yielding a combined cohort of 260 control samples and 250 COPD samples. Candidate genes were prioritized by intersecting the results of LASSO regression, random forest, and support vector machine. Immune-cell infiltration was estimated using CIBERSORT, and single-cell transcriptomic data were used to define the cellular localization of prioritized genes. Formal protein-level MR analysis was conducted for CD163 using deCODE plasma protein pQTL/GWAS summary statistics as the exposure dataset and the IEU OpenGWAS COPD dataset (ebi-a-GCST90018807) as the outcome dataset. Molecular docking, molecular dynamics simulation, and virtual knockout analysis were further used to provide structural and network-level supportive evidence. Finally, LPS-stimulated BEAS-2B cells were used as an epithelial inflammatory model to evaluate the effects of baicalein by CCK-8 assay, wound-healing assay, ELISA, and RT-qPCR. Five core genes were prioritized, namely ABCC1, CD163, CYP1B1, IKBKB, and PIK3CA. Immune infiltration and single-cell analyses suggested that macrophage-associated immune regulation may represent an important mechanistic direction. MR analysis provided supportive genetic evidence for prioritizing CD163 in COPD. Molecular simulation offered preliminary structural support for several target-compound interactions. In LPS-stimulated BEAS-2B cells, baicalein reduced inflammatory cytokine release and modulated the expression of IKBKB, PIK3CA, IL1B, IL6, and IL10, thereby providing epithelial-level support for the predicted network. Taken together, these findings suggest that baicalein may exert anti-inflammatory effects in COPD through a multi-target, immune-associated mechanism, with macrophage-related regulation and CD163 emerging as noteworthy candidate directions for further investigation. This study provides an integrative framework for target prioritization and mechanistic exploration, while the predicted macrophage-centered mechanisms still require dedicated validation in immune-cell and in vivo models. Full article