Search Results (3,527)

Ultrasound imaging is widely used for early breast cancer screening to enhance patient survival. However, interpreting these images is inherently challenging due to speckle noise, low lesion-to-tissue contrast, and highly variable tumor morphology within complex anatomical structures. Additionally, variations in image characteristics across institutions and devices further impede the development of robust and generalizable computer-aided diagnostic systems. To alleviate these issues, this paper presents a cross-domain segmentation prior guided classification strategy for robust breast tumor diagnosis in ultrasound imaging, implemented through a novel Dual-Stream Diagnosis Network (DSDNet). DSDNet adopts a decoupled dual-stream architecture, where a frozen segmentation branch supplies spatial priors to guide the classification backbone. This design enables stable and accurate performance across diverse imaging conditions and clinical settings. To realize the proposed DSDNet framework, three novel modules are created. The Dual-Stream Mask Attention (DSMA) module enhances lesion priors by jointly modeling foreground and background cues. The Segmentation Prior Guidance Fusion (SPGF) module integrates multi-scale priors into the classification backbone using cross-domain spatial cues, improving tumor morphology representation. The Mamba-Inspired Linear Transformer (MILT) block, built upon the Mamba-Inspired Linear Attention (MILA) mechanism, serves as an efficient attention-based feature extractor. On the BUSI, BUS, and GDPH_SYSUCC datasets, DSDNet achieves ACC values of 0.878, 0.836, and 0.882, and Recall scores of 0.866, 0.789, and 0.878, respectively. These results highlight the effectiveness and strong classification performance of our method in ultrasound breast cancer diagnosis. Full article

Background/Objectives: Accurate nuclear segmentation is a fundamental step in computational pathology, enabling reliable estimation of cellularity and nuclear morphology. However, segmentation models are typically evaluated under ideal imaging conditions, while real-world microscopy data are affected by staining variability, noise, and image degradation. This study aims to comparatively evaluate three representative convolutional architectures for nuclei segmentation, with emphasis on robustness and clinical relevance under perturbed imaging conditions. Methods: U-Net, Attention U-Net, and U-Net++ were trained and evaluated on the BBBC038 nuclei microscopy dataset using fixed train–validation–test splits. Robustness was assessed under three types of synthetic perturbations: Gaussian blur, additive noise, and color jitter. Segmentation performance was quantified using the Dice coefficient and Intersection-over-Union (IoU). Paired Wilcoxon signed-rank tests with Holm correction and Cliff’s delta were used for statistical comparison. In addition, clinically relevant nuclear descriptors—nuclear count, median nuclear area, area interquartile range (IQR), and nuclear density—were extracted from predicted masks, and descriptor stability was analyzed as relative deviation from clean conditions. Results: Under clean imaging conditions, Attention U-Net achieved the highest mean Dice score, while paired statistical analysis indicated that U-Net++ exhibited the most consistent performance across test samples. Under image perturbations, Attention U-Net demonstrated greater robustness to blur and noise, whereas U-Net++ showed superior stability under color variations. Descriptor-based analysis further indicated that U-Net++ preserved nuclear count and density most reliably under chromatic perturbations, while U-Net exhibited larger instability in nuclear count and density, particularly under noise. Conclusions: Architectural design choices strongly influence not only pixel-level segmentation accuracy but also the stability of clinically relevant nuclear morphology descriptors. Robustness evaluation under multiple perturbation types reveals important trade-offs between architectures that are not captured by clean-image benchmarks alone. These findings highlight the necessity of multi-level evaluation strategies combining overlap metrics, statistical testing, robustness analysis, and descriptor stability assessment for future benchmarking and clinically reliable deployment of nuclei segmentation systems. Full article

Urban sustainability is increasingly defined by the resilience of the built environment against hazards. While Agent-Based Models (ABMs) are commonly used to simulate these dynamics, their predictive capacity is often limited by a lack of empirical behavioral data. This study addresses this gap by introducing a Human-Centric Digital Twin framework that integrates procedural generation with immersive Virtual Reality (VR) to quantify ‘spatial sustainability’, defined as the capacity of an urban form to support life safety without compromising its morphological identity. In this framework, VR serves as a controlled environment for observing navigation under stress, while procedural generation creates structurally distinct urban morphologies (orthogonal vs. organic) to enable universal calibration. The approach was validated through evacuation experiments with 37 participants under varying visibility conditions. Results reveal that while performance was similar in daylight, significant behavioral divergence emerged at night; the organic layout (Type A) exhibited greater variability and longer evacuation times compared to the orthogonal grid (Type B). These findings confirm that spatial configuration dictates resilience when sensory inputs degrade. Consequently, this study offers a transferable, data-independent protocol for measuring and monitoring urban resilience in data-scarce environments. Full article

Among the options to improve the establishment of jalapeno pepper (Capsicum annuum L.), physical biostimulants such as far-infrared bioceramics (FIR) and static magnetic fields (MF) have emerged as non-chemical alternatives. This study evaluated, under in vitro conditions, the individual and combined effects of FIR and positive or negative MF on seed germination dynamics, early seedling morphology, water status, and photosynthetic pigments. A completely randomized design with eight treatments was implemented, including FIR applied continuously throughout the entire experimental period, positive or negative MF applied for 24 h (MF⁺₂₄, MF⁻₂₄), and FIR + MF combinations under continuous or 24 h exposure regimes (n = 7). Germination percentage, mean germination time (MGT), mean germination rate (MGR), germination index (GI), morphological variables, water content (WC), and photosynthetic pigments were measured; ANOVA/alternative tests (a = 0.05), Principal Components Analysis (PCA) and exploratory Spearman’s correlations were used to assess relationships among the evaluated variables. Germination percentage did not change (97.64%), but kinetics did: FIR + MF⁻₂₄ reduced MGT to 4.32 d, FIR increased MGR to 5.83 seeds day⁻¹ (+11.69%), and FIR₂₄ + MF⁺₂₄ showed the highest GI (4.57). For morphological, MF⁺₂₄ increased hypocotyl length (+16.29%), FIR increased collar diameter (+27.27%), and FIR + MF⁻₂₄ increased cotyledon area (25%), and FIR increased chlorophyll a (+139%), chlorophyll b (+141%), and carotenoids (+114%). PCA explained 66.9% of the variance, grouping FIR with growth variables and FIR + MF combinations with WC and pigments. Inferences are limited to one cultivar and controlled in vitro conditions. This study provides novel quantitative evidence that continuous and short-term applications of FIR and MF modulate germination dynamics and early physiological traits without altering final germination, related to structure and pigments, without changing final germination percentage. Full article

This study presents a measurement–modeling pathway for diagnosing corrosion-driven contact degradation in power equipment using infrared thermography and color-channel analysis. Thermal data were acquired with a Fluke Ti450 (LWIR, 7.5–14 $\mathsf{\mu }\mathrm{m}$) under typical high-altitude, temperate conditions in Quito, Ecuador. Radiometric parameters (emissivity, distance, ambient/reflected temperature, and humidity) are reported explicitly, and images are processed with a reproducible pipeline that combines adaptive thresholding, morphology, and region-of-interest statistics, including $\Delta T$ relative to a reference region. A worked example links an observed hotspot to emissivity-corrected temperature and discusses qualitative implications for the effective contact resistance $R_{\mathrm{eff}}$. Uncertainty is summarized through a per-case template that propagates $u_{\Delta T}$ to $u\left(R_{\mathrm{eff}}\right)$ and Weibull characteristic life $\eta$. Environmental influences (solar load, wind, and emissivity variability) are acknowledged and mitigated. Two field cases illustrate the approach to substation assets. Because the dataset comprises single-visit inspections, formal parameter estimation (e.g., EIS-validated $R_{\mathrm{eff}}$ and full Weibull/Arrhenius fits) is reserved for longitudinal follow-up. By making radiometry, processing steps, and limitations explicit, the study reduces ambiguity in the transition from temperature contrast to physics-based interpretation and supports auditable maintenance decisions. Full article

Background/Objectives: This research covers both tumoral and non-tumoral (adjacent normal) tissues. Non-tumoral tissue samples were obtained from surgical resection margins located at least 5 cm from the tumor edge, with histological confirmation of the absence of tumor involvement. Methods: These samples, varying from 0 weeks to 1 week, were systematically evaluated. The assessment encompassed critical histological aspects such as tissue architecture, nuclear morphology, cytoplasmic features, and membrane characteristics. A scoring system comprising three categories (good, fair, and bad) was employed to gauge the extent of morphological alterations observed in tissue specimens. Statistical analyses were conducted using the “IBM SPSS Statistics 26.0” software. Results: Our findings unveiled a statistically significant association between tissue type and morphological degradations, highlighting the impact of prolonged cold ischemia time and fixation time on cellular swelling, cellular integrity loss, and tissue architecture disruption. The correlation between normal and tumor tissue was statistically significant for pre-analytical parameters evaluated with a strong influence on tumor tissue in cold ischemia time with a p = 0.046, p = 0.020, p = 0.029. For fixation times, the impact was significant for most of the morphological parameters, p = 0.021, p = 0.005, p = 0.023. Conclusions: These observations underscore the critical importance of minimizing cold ischemia time and refining fixation protocols to uphold tissue morphology, protein and molecular integrity. Such endeavors are pivotal in ensuring accurate histopathological evaluation and facilitating precise molecular analyses in the context of digestive cancer research. Full article

The equilibrium shape of a crystal is a fundamental problem in materials science and condensed matter physics. The Wulff construction, a cornerstone of crystal morphology prediction, is traditionally presented and utilized as a powerful geometric algorithm to derive equilibrium shapes from anisotropic surface energy $\gamma \left(\mathbf{n}\right)$. While its application across materials science is vast, the profound mathematical physics underpinning it, specifically its intrinsic identity as a manifestation of the Legendre transform, is often relegated to a passing remark. This work recenters the focus on this fundamental duality. We present a comprehensive, step-by-step derivation of the Wulff shape from the variational principle of surface energy minimization under a constant volume, employing the language of support functions and differential geometry. We then rigorously demonstrate that the equilibrium shape, defined by the support function $h\left(\mathbf{n}\right)$, and the surface energy density $\gamma \left(\mathbf{n}\right)$ are conjugate variables linked by a Legendre transformation; the Wulff shape $\mathcal{W}$ is precisely the zero-sublevel set of the dual function ${\gamma }^{*}\left(\mathbf{x}\right)={sup}_{\mathbf{n}}[\mathbf{x}·\mathbf{n}-\gamma \left(\mathbf{n}\right)]$. This perspective elevates the Wulff construction from a mere graphical tool to a canonical example of convex duality in thermodynamic systems, connecting it to deeper principles in convex analysis and statistical mechanics. To bridge theory and computation, we provide a robust computational algorithm implemented in pseudocode capable of generating Wulff shapes for two-dimensional (2D) crystals with arbitrary N-fold symmetry. Finally, we discuss the relevance and extensions of the classical theory in contemporary research, including non-equilibrium growth, nanoscale effects, and machine learning approaches. Full article

Marijuana (Cannabis sativa L.) has a great economic potential due to its phytotherapeutic properties. Its propagation, however, faces numerous challenges due to the limited availability of standardized technical protocols for the crop. Vegetative propagation represents a, or even the, viable method for multiplying the genetically identical individuals while preserving their phytochemical profile, at lower costs and with shorter production times. This study investigated the morphological and colorimetric attributes associated with vegetative propagation success, aiming to develop sustainable cultivation strategies. Four cutting lengths (5, 10, 15 and 20 cm) were evaluated after 21 days of rooting, considering fresh mass, basal diameter, presence of apical meristem, number of root primordia, root length, and foliar and stem color parameters. Logistic regressions indicated that longer cuttings (p = 0.0101), greater fresh mass (p = 0.073) and the presence of apical meristem (p = 0.065), as well as greener leaves (p = 0.089), were positively associated with rooting probability (p < 0.10). Positive correlations between morphological and colorimetric variables were confirmed by Principal Component Analysis, with the first two principal components explaining 31.2% of the total variance in the dataset. The results provide support for the development of more efficient and low-cost vegetative propagation protocols, promoting uniformity and autonomy in local cutting production of marijuana. Full article

Background: Cardiac magnetic resonance [CMR] is a non-invasive tool to assess ventricular function in pediatric pulmonary arterial hypertension [PAH]. However, CMR parameters in children remain underexplored. Methods: Thirty-six children with PAH were prospectively evaluated using CMR. Right and left ventricular volumetric and functional parameters, including right and left ventricular ejection fraction [RVEF, LVEF], right and left ventricular end-systolic volume indexed to body surface area [RVESVi, LVESVi], right ventricular mass index [RVMi], ventricular mass index [VMI], septal curvature duration index [SCDI], and regional area change [RAC], were assessed. Clinical variables included brain natriuretic peptide [BNP], New York Heart Association [NYHA] class, and six-minute walk distance [6MWD]. Correlations, logistic regression, and Kaplan–Meier analyses were performed to determine associated factors for mortality. Results: RVEF was negatively correlated with BNP [r = −0.538, p = 0.001], while no correlation was found with LVEF. Decreased RVEF and LVESVi and VMI were associated with mortality in univariate analysis. Patients with VMI > 0.75 or leftward septal shift had significantly lower one-year survival [p = 0.016 and p = 0.040, respectively]. SCDI and RAC were not associated with mortality. Conclusions: RVEF, LVESVi, and VMI are associated with mortality in pediatric PAH. BNP reflects right ventricular dysfunction. VMI and septal morphology are strong associated markers and may enhance risk stratification in children with PAH. Full article

Urban heat not only affects thermal comfort but also constrains the sustainable development of cities, underscoring the necessity of understanding the temporal response of land surface temperature (LST) to urban characteristics over time. Most existing studies rely on single-overpass satellite observations or daily averages, failing to capture continuous diurnal variability and the time-dependent influence of different drivers. In this study, we reconstructed seasonal hourly LST series for Beijing using an improved diurnal temperature cycle (DTC) model (${\mathrm{GEM}}_{\eta }$) based on MODIS data, and employed a random forest framework to quantify the relative contributions of natural, urban morphological, and anthropogenic factors throughout the diurnal cycle. Unlike previous studies that rely on traditional DTC models and machine learning for largely static or single-scale assessments, our research provides a unified, time-explicit comparison of LST driver dominance across seasons, hourly diurnal cycles, and urban–rural contexts. The results indicate that persistent urban heat island (UHI) effects occur in all seasons, with the maximum intensity reaching approximately 5.0 °C in summer. Generally, natural factors exert a cooling influence, whereas urban morphology and human activities contribute to warming. More importantly, the dominant drivers show strong temporal dependence: a nature-dominated regime prevails in summer, where vegetation exerts an overwhelming cooling effect. Conversely, during transition seasons and winter, LST variability is governed by a mixed-driven mechanism characterized by an hourly-resolved diurnal handoff, in which the dominant contributors shift hour by hour between surface physical properties and anthropogenic proxies. Our findings challenge the static view of urban heat drivers and provide quantitative evidence for developing time-sensitive and seasonally adaptive mitigation strategies, thereby supporting sustainable urban planning and enhancing climate resilience in megacities. Full article

Dicing is an important process in the packaging segment of the semiconductor manufacturing process, and due to the high hardness and brittleness of 4H-SiC wafers, they are prone to crack propagation and severe chipping during the dicing process. To reduce chipping defects, this study investigates the effects of key process parameters on the chipping behavior of 4H-SiC wafers, as well as the associated chipping formation and material removal mechanisms during dicing. Firstly, a spindle current measurement scheme was designed to indirectly reflect changes in grinding force during the cutting process, and the change in the cutting process in a single pass was analyzed. Secondly, experiments controlling single-factor variables were designed to explore the influence of laws of process parameters, including depth of cut, spindle speed, feed speed, and the dicing blade parameter, abrasive grain size, on the quality of chipping, and the optimal process parameters were obtained. Thirdly, the morphology of the 4H-SiC cutting contact arc area, front–back chipping, and sidewalls was analyzed in order to investigate the chipping formation and material removal mechanism. This study contributes to a fundamental understanding of material removal mechanisms during the cutting of 4H-SiC wafers and other advanced semiconductor materials and provides guidance for optimizing cutting process parameters. Full article

Background: Obstructive Sleep Apnea (OSA) is one of the most prevalent sleep disorders associated with cardiovascular complications, cognitive impairments, and reduced quality of life. Early and accurate diagnosis is essential. The present gold standard, polysomnography, is expensive and resource-intensive. This work develops a non-invasive machine-learning-based framework to classify four OSA severity groups (non, mild, moderate, and severe) using tracheal breathing sounds (TBSs) and anthropometric variables. Methods: A total of 199 participants were recruited, and TBS were recorded whilst awake (wakefulness) using a suprasternal microphone. The workflow included the following steps: signal preprocessing (segmentation, filtering, and normalization), multi-domain feature extraction representing spectral, temporal, nonlinear, and morphological features, adaptive feature normalization, and a three-stage feature selection that combined univariate filtering, Shapley Additive Explanations (SHAP)-based ranking, and recursive feature elimination (RFE). The classification included training ensemble learning models via bootstrap aggregation and validating them using stratified k-fold cross-validation (CV), while preserving the OSA severity and anthropometric distributions. Results: The proposed framework performed well in discriminating among OSA severity groups. TBS features, combined with anthropometric ones, increased classification performance and reliability across all severity classes, providing proof for the efficacy of non-invasive audio biomarkers for OSA screening. Conclusions: TBS-based model’s features, coupled with anthropometric information, offer a promising alternative or supplement to PSG for OSA severity detection. The approach provides scalability and accessibility to extend screening and potentially enables earlier detection of OSA, compared to cases that might remain undiagnosed without screening. Full article

Background: Sickle cell disease (SCD) is a prevalent hereditary hemoglobinopathy associated with substantial morbidity, particularly in regions with limited access to advanced laboratory diagnostics. Conventional diagnostic workflows, including manual peripheral blood smear examination and biochemical or molecular assays, are resource-intensive, time-consuming, and subject to observer variability. Recent advances in artificial intelligence (AI) enable automated analysis of blood smear images and offer a scalable alternative for SCD screening. Methods: This study presents a controlled benchmark of CNNs, Vision Transformers, hierarchical Transformers, and hybrid CNN–Transformer architectures for image-level SCD classification using a publicly available peripheral blood smear dataset. Eleven ImageNet-pretrained models were fine-tuned under identical conditions using an explicit leakage-safe evaluation protocol, incorporating duplicate-aware, group-based data splitting and repeated splits to assess robustness. Performance was evaluated using accuracy and macro-averaged precision, recall, and F1-score, complemented by bootstrap confidence intervals, paired statistical testing, error-type analysis, and explainable AI (XAI). Results: Across repeated group-aware splits, CNN-based and hybrid architectures demonstrated more stable and consistently higher performance than transformer-only models. MaxViT-Tiny and DenseNet121 ranked highest overall, while pure ViTs showed reduced effectiveness under data-constrained conditions. Error analysis revealed a dominance of false-positive predictions, reflecting intrinsic morphological ambiguity in challenging samples. XAI visualizations suggest that CNNs focus on localized red blood cell morphology, whereas hybrid models integrate both local and contextual cues. Conclusions: Under limited-data conditions, convolutional inductive bias remains critical for robust blood-smear-based SCD classification. CNN and hybrid CNN–Transformer models offer interpretable and reliable performance, supporting their potential role as decision-support tools in screening-oriented research settings. Full article

Accurate segmentation of ischemic stroke lesions from multimodal magnetic resonance imaging (MRI) is fundamental for quantitative assessment, treatment planning, and outcome prediction; yet, it remains challenging due to highly heterogeneous lesion morphology, low lesion–background contrast, and substantial variability across scanners and protocols. This work introduces Tri-UNetX-2D, a large-kernel and scale-aware 2D convolutional network with explicit boundary refinement for automated ischemic stroke lesion segmentation from DWI, ADC, and FLAIR MRI. The architecture is built on a compact U-shaped encoder–decoder backbone and integrates three key components: first, a Large-Kernel Inception (LKI) module that employs factorized depthwise separable convolutions and dilation to emulate very large receptive fields, enabling efficient long-range context modeling; second, a Scale-Aware Fusion (SAF) unit that learns adaptive weights to fuse encoder and decoder features, dynamically balancing coarse semantic context and fine structural detail; and third, a Boundary Refinement Head (BRH) that provides explicit contour supervision to sharpen lesion borders and reduce boundary error. Squeeze-and-Excitation (SE) attention is embedded within LKI and decoder stages to recalibrate channel responses and emphasize modality-relevant cues, such as DWI-dominant acute core and FLAIR-dominant subacute changes. On the ISLES 2022 multi-center benchmark, Tri-UNetX-2D improves Dice Similarity Coefficient from 0.78 to 0.86, reduces the 95th-percentile Hausdorff distance from 12.4 mm to 8.3 mm, and increases the lesion-wise F1-score from 0.71 to 0.81 compared with a plain 2D U-Net trained under identical conditions. These results demonstrate that the proposed framework achieves competitive performance with substantially lower complexity than typical 3D or ensemble-based models, highlighting its potential for scalable, clinically deployable stroke lesion segmentation. Full article

Background: Pediatric gastrointestinal polyps represent a heterogeneous entity with variable clinical behavior, ranging from solitary benign lesions to syndromic forms associated with significant malignant potential. This study provides contemporary data, including upper GI and small-bowel polyps, with an unusually high syndromic yield (27.6%) compared to prior pediatric cohorts. Methods: This retrospective single-center study included children aged 0–18 years who underwent esophagogastroduodenoscopy and/or colonoscopy and were diagnosed with at least one gastrointestinal polyp between January 2015 and October 2025. Demographic characteristics, presenting symptoms, endoscopic features, histopathology, management strategies, and status of polyposis syndrome were collected. Statistical analyses were performed using IBM SPSS Statistics 27.0, with a significance threshold of p < 0.05. Results: Seventy-six patients (mean age 10.6 ± 5.0 years; 47.4% female) were evaluated. Gastrointestinal bleeding was the most common presenting symptom (37.1%). Solitary (63.2%) and sessile (59.2%) polyps predominated, with a median size of 7.0 mm (IQR 3.2–20.0). Juvenile (28.9%) and inflammatory (22.4%) polyps were the most frequent histologic subtypes. Polyposis syndromes were identified in 27.6% of patients and were significantly associated with multiple polyps (p < 0.001), proximal or intestinal distribution (p < 0.001), and adenomatous or hamartomatous histology (p < 0.001). Endoscopic polypectomy was successful in 94.7% of cases, with no major complications reported. Conclusions: Given the 27.6% prevalence of polyposis syndromes observed in this cohort, pediatric gastrointestinal polyps cannot be assumed to be uniformly benign. Our findings support comprehensive endoscopic evaluation, routine histopathology, and early genetic referral, specifically in patients with multiple, proximal, or mixed-morphology polyps. Full article