Search Results (306)

Dense image prediction tasks require both strong semantic category information and precise boundary delineation in order to be effectively applied to downstream applications. However, existing networks typically fuse deep coarse features with adjacent fine features directly through upsampling. Such a straightforward upsampling strategy not only blurs boundaries due to the loss of high-frequency information, but also amplifies intra-class conflicts caused by high-frequency interference within the same object. To address these issues, this paper proposes an Adaptive High–Low Frequency Collaborative Auxiliary Feature Alignment Network(AHLFNet), which consists of an Adaptive Low-Frequency Multi-Kernel Smoothing Unit(ALFU), a Gate-Controlled Selector(GCS), and an Adaptive High-Frequency Edge Enhancement Unit(AHFU). The ALFU suppresses high-frequency components within objects, mitigating interference during upsampling and thereby reducing intra-class conflicts. The GCS adaptively chooses suitable convolutional kernels based on the size of similar regions to ensure accurate upsampled features. The AHFU preserves high-frequency details from low-level features, enabling more refined boundary delineation. Extensive experiments demonstrate that the proposed network achieves state-of-the-art performance across various downstream tasks. Full article

Narrow-diameter implants (≤3.5 mm) have garnered significant attention due to their widespread application in areas with insufficient bone volume. However, their mechanical performance is limited. The cervical region, serving as a pivotal stress concentration zone, exhibits a thread form that directly modulates stress distribution and determines the long-term stability of the implant–bone interface. This study was designed to investigate the influence of varying thread forms and face angles on microstrain and stress distribution patterns in narrow-diameter implants (NDIs) and their adjacent cortical bone structures. Through systematic modification of implant thread forms and face angle parameters, finite element analysis (FEA) was employed to develop nine distinct implant models featuring varied geometric characteristics. Each model was implanted into Type III bone tissue, followed by the application of a 100 N occlusal force, including a vertical load and an oblique load deviated 30 degrees lingually from the long axis of the implants. Subsequent biomechanical evaluation quantified peak von Mises stress concentrations at the bone–implant interface, maximum equivalent elastic strain distributions in peri-implant bone tissue, and abutment stress profile characteristics. The results indicated that in the RB thread group, the optimal thread face angle parameter was 60 degrees; in the B thread group, this optimal thread face angle parameter was 45 degrees, whereas in the V thread group, the optimal thread face angle parameter was 30 degrees. Full article

Mesoscale convective systems (MCSs) play a pivotal role in the occurrence of severe weather phenomena, with convective cells constituting their fundamental elements. The precise identification of these cells from satellite imagery is crucial yet presents significant challenges, including issues related to merging errors and sensitivity to threshold parameters. This study introduces a novel detection algorithm for convective cells that leverages H-maxima transformation and incorporates multichannel data from the FY-2F satellite. The proposed method utilizes H-maxima transformation to identify seed points while maintaining the integrity of core structural features, followed by a novel neighborhood labeling method, region growing and adaptive merging criteria to effectively differentiate adjacent convective cells. The neighborhood labeling method improves the accuracy of seed clustering and avoids “over-clustering” or “under-clustering” issues of traditional neighborhood criteria. When compared to established methods such as RDT, ETITAN, and SA, the algorithm demonstrates superior performance, attaining a Probability of Detection (POD) of 0.87, a False Alarm Ratio (FAR) of 0.21, and a Critical Success Index (CSI) of 0.71. These results underscore the algorithm’s efficacy in elucidating the internal structures of convective complexes and mitigating false merging errors. Full article

Background: Latent myofascial trigger points (MTrPs) are clinically relevant because they lower local pressure pain thresholds (PPTs), can perturb motor control, and may sustain shoulder symptoms even when overt pain is absent. However, even if previous studies assessed stiffness and mechanosensitivity differences between MTrPs and asymptomatic regions, objective patient-level cut-offs and diagnostic-accuracy metrics to distinguish latent MTrPs from adjacent asymptomatic tissue are lacking. Objective: To quantify the diagnostic accuracy of pressure algometry (PPT) and shear-wave elastography (SWE) for distinguishing latent MTrPs from adjacent asymptomatic tissue. Methods: A single-center cross-sectional study was conducted including 76 volunteers with ≥1 latent infraspinatus MTrP (assessed by following the current Delphi consensus criteria). The most sensitive latent MTrP and a control site 2 cm cranial was measured on the dominant side infraspinatus muscle in each participant. PPT and SWE were acquired with a standardized protocol (long-axis imaging, anisotropy control, minimal probe pressure; three captures per site; 1 cm rectangular ROI; operator blinded to site type). ROC analyses estimated areas under the curve (AUCs), Youden-optimal cut-offs, sensitivity, specificity, and likelihood ratios (LR+/−). Results: Latent MTrPs showed lower PPTs than controls (p < 0.001) and higher stiffness (shear modulus: p = 0.009; shear-wave speed: p = 0.022). PPT yielded AUC = 0.704 with an optimal cut-off of 47.5 N (sensitivity 0.75; specificity 0.592; LR+ 1.84; LR− 0.42), outperforming SWE metrics (shear modulus AUC 0.611; cut-off 23.6 kPa; sensitivity 0.632; specificity 0.605; LR+ 1.60; LR− 0.61; shear-wave speed AUC 0.601; cut-off 2.55 m/s; sensitivity 0.592; specificity 0.632; LR+ 1.61; LR− 0.65). Conclusions: In the infraspinatus, PPT provides moderate discrimination between latent MTrPs and adjacent asymptomatic tissue, whereas resting SWE—despite small mean differences—exhibited lower accuracy. These findings support mechanosensitivity as a primary measurable signal and position SWE as an adjunct. External validation across devices and operators, and multivariable models integrating sensory, imaging, and clinical features, are warranted. Full article

The method addresses the challenges of non-steady conditions at an early age by combining wavelet filtering and empirical mode decomposition (EMD) to separate strain components arising from shrinkage, expansive agent compensation, temperature variations, construction disturbances, and live loads. The approach incorporates construction logs as external constraints to ensure accurate correspondence between signal features and physical events. Scientifically, this study addresses the fundamental problem of identifying and quantifying multi-source strain components under transient and non-steady construction conditions, which remains a major challenge in the field of structural monitoring. Field monitoring was conducted on typical cast-in-place concrete components: a full-width bridge deck in the negative moment region. The results show that both structural types exhibit a distinct shrinkage–recovery process at an early age but differ in amplitude distribution, recovery rate, and restraint characteristics. During the construction procedure stage, the cast-in-place segment in the negative moment region was sensitive to prestressing and adjacent segment construction. Under variable loads, the former showed higher live load sensitivity, while the latter exhibited more pronounced temperature-driven responses. Total strain decomposition revealed that temperature and dead load were the primary long-term components in the structure, with differing proportional contributions. Representative strain variations observed in the field ranged from 10 to 50 µε during early-age shrinkage–expansion cycles to 80–100 µε reductions during prestressing operations, quantitatively illustrating the evolution characteristics captured by the proposed method. This approach demonstrates the method’s capability to reveal transient stress mechanisms that conventional steady-state analyses cannot capture, providing a reliable basis for strain monitoring, disturbance identification, and performance evaluation during construction, as well as for long-term prediction and optimization of operation–maintenance strategies. Full article

This study investigates the species composition and distribution of blackflies (Diptera: Simuliidae) in Kazakhstan, with a focus on two species newly recorded for the country: Simulium murmanum (Enderlein, 1935) and Simulium reptans (Linnaeus, 1758). The presence of S. murmanum in Kazakhstan is reported for the first time, supported by morphological and molecular genetic analyses. Diagnostic features of the larva, pupa, and adult stages are described in detail, including the structure and coloration of the larval head capsule, pupal cocoon, and genitalia of both sexes. Habitat preferences and pupal substrate attachment patterns are illustrated, with observations on variations in cocoon branching across different flow regimes. Species identification was conducted using the morphological keys of Rubtsov and Yankovsky, and taxonomic classification was confirmed using the framework proposed by Adler. Molecular confirmation of S. murmanum was performed via DNA analysis. The species was found to be restricted to the foothill regions of East Kazakhstan, suggesting a distribution closely associated with the Altai mountain systems and adjacent regions in Mongolia and China. Unlike its status as a dominant hematophagous species in parts of Russia, S. murmanum has not demonstrated biting activity in Kazakhstan, Mongolia, or China. Additionally, the study provides the first records of S. reptans within the fauna of Kazakhstan, initially identified in the Irtysh River (Pavlodar Region). Subsequent sampling conducted in June 2024 revealed a continuous distribution of S. reptans along the Irtysh River through to the mountain streams of East Kazakhstan. The species was found in mountainous, foothill, and lowland environments, highlighting its wide ecological plasticity. Full article

Objectives: Employing 18F-FDG PET/CT radiomic properties both within and surrounding tumors, in conjunction with clinical attributes, to precisely differentiate among several pathological subtypes of non-small-cell lung cancer (NSCLC). Approaches: The study comprised 222 patients who received 18F-FDG PET/CT scans from January 2015 to December 2020 and were later diagnosed with NSCLC, encompassing 169 cases of lung adenocarcinoma (LUAD) and 53 cases of lung squamous cell carcinoma (LUSC). They were arbitrarily allocated into a training group and a validation group in a 7:3 ratio. Radiomics feature extraction was conducted on 18F-FDG PET/CT images of primary tumors and adjacent tumor regions with LIFE-x (5.2.0). A multivariate logistic regression analysis was employed to develop a nomogram for differentiating lung adenocarcinoma (LUAD) from lung squamous cell carcinoma (LUSC). The clinical efficacy of each model was assessed and contrasted utilizing accuracy (Acc), sensitivity (Sen), specificity (Spe), receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). Outcomes: The nomogram model that integrates 18F-FDG PET/CT radiomics features with clinical characteristics showed superior efficacy in differentiating adenocarcinoma from squamous cell carcinoma in NSCLC patients, surpassing models based only on PET or CT radiomics. The validation set exhibited an Area under curve (AUC) of 0.880, an Acc of 0.929, a Sen of 0.808, and a Spe of 0.962. This model exhibits the most superior overall performance in DCA. Conclusions: A nomogram model integrating radiomic features derived from 18F-FDG PET/CT images of tumors and adjacent tissues with clinical characteristics can effectively differentiate between LUAD and LUSC. Full article

This study pioneers a fully remote sensing-based framework for mapping heatwave susceptibility, integrating the TabTransformer deep learning model with Particle Swarm Optimization (PSO) for robust hyperparameter tuning. The central question addressed is whether a fully remote sensing-driven, PSO-optimized TabTransformer can achieve accurate, scalable, and spatially detailed heatwave susceptibility mapping in data-scarce regions such as Central Asia. Utilizing ERA5-derived heatwave evidence and thirteen environmental and socio-economic predictors, the workflow produces high-resolution susceptibility maps spanning five Central Asian countries. Comparative analysis evidences that the PSO-optimized TabTransformer model outperforms the baseline across multiple metrics. On the test set, the optimized model achieved an RMSE of 0.123, MAE of 0.034, and R² of 0.938, outperforming the standalone TabTransformer (RMSE = 0.132, MAE = 0.038, R² = 0.93). Discriminative capacity also improved, with AUROC increasing from 0.933 to 0.940. The PSO-tuned model delivered faster convergence, lower final loss, and more stable accuracy during training and validation. Spatial outputs reveal heightened susceptibility in southern and southwestern sectors—Turkmenistan, Uzbekistan, southern Kazakhstan, and adjacent lowlands—with statistically significant improvements in spatial precision and class delineation confirmed by Chi-squared, Friedman, and Wilcoxon tests, all with congruent p-values of <0.0001. Feature importance analysis consistently identifies maximum temperature, frequency of hot days, and rainfall as dominant predictors. These advancements validate the potential of data-driven, deep learning approaches for reliable, scalable environmental hazard assessment, crucial for climate adaptation planning in vulnerable regions. Full article

Rice is one of the most important staple crops in China, and the rapid and accurate extraction of rice planting areas plays a crucial role in the agricultural management and food security assessment. However, the existing rice field identification methods faced the significant challenges in mountainous regions due to the severe cloud contamination, insufficient utilization of multi-dimensional features, and limited classification accuracy. This study presented a novel rice field identification method based on the Graph Convolutional Networks (GCN) that effectively integrated multi-source remote sensing data tailored for the complex mountainous terrain. A coarse-to-fine cloud removal strategy was developed by fusing the synthetic aperture radar (SAR) imagery with temporally adjacent optical remote sensing imagery, achieving high cloud removal accuracy, thereby providing reliable and clear optical data for the subsequent rice mapping. A comprehensive multi-feature library comprising spectral, texture, polarization, and terrain attributes was constructed and optimized via a stepwise selection process. Furthermore, the 19 key features were established to enhance the classification performance. The proposed method achieved an overall accuracy of 98.3% for the rice field identification in Huoshan County of the Dabie Mountains, and a 96.8% consistency compared to statistical yearbook data. The ablation experiments demonstrated that incorporating terrain features substantially improved the rice field identification accuracy under the complex topographic conditions. The comparative evaluations against support vector machine (SVM), random forest (RF), and U-Net models confirmed the superiority of the proposed method in terms of accuracy, local performance, terrain adaptability, training sample requirement, and computational cost, and demonstrated its effectiveness and applicability for the high-precision rice field distribution mapping in mountainous environments. Full article

Background: Supplemental teeth are a rare subtype of supernumerary elements that closely resemble the morphology of normal dentition. Their occurrence in the mandibular anterior region is extremely uncommon. Aim: To describe the clinical features, diagnosis, and phased orthodontic management of a rare case involving bilateral supplemental mandibular incisors in a pediatric patient. Case report: A 7-year-old female patient presented with early mixed dentition and significant lower anterior crowding due to the presence of two fully erupted supplemental mandibular incisors. Treatment phase I included extraction of the malpositioned supplemental teeth and rapid maxillary expansion to transversally coordinate the arches. By the end of phase I, spontaneous alignment of the remaining lower incisors was observed. Discussion: The presence of two supplemental mandibular incisors is extremely rare in Caucasian populations. Supernumerary teeth can cause crowding, impaction, or delayed eruption of adjacent permanent teeth. Timely extraction can prevent such complications and often allows spontaneous alignment. Conclusions: The prompt removal of supplemental mandibular incisors, when they have just erupted, might lead to the alignment of the other incisors, considering that they spontaneously occupy the extractive spaces often without the aid of fixed appliances first line. Full article

In SF₆ gas-insulated equipment, solid dielectrics critically degrade insulation performance by reducing the electric field’s ability to withstand gas gaps. To investigate the critical role played by solid dielectric surfaces during the initial phase of gas–solid interface discharge phenomena, this paper experimentally measures the AC breakdown voltage (U_bd) of both dielectric surface-initiated breakdown (DIBD) and electrode surface-initiated breakdown (EIBD) across eight types of post insulator samples. Tests are conducted in 36 mm SF₆ gas gaps under pressures ranging from 0.1 to 0.4 MPa. Combined with electrostatic field simulations, the results reveal that DIBD requires substantially lower U_bd than EIBD under comparable maximum electric field (E_max) conditions. As gas pressure increases, this difference becomes more pronounced. This phenomenon can be explained by three key mechanisms: First, due to the regulatory effect of dielectric materials and shielding electrodes on the electric field distribution, the high-electric-field zone along the gas–solid interface exhibits a longer effective discharge path compared to that in a pure gas gap. This configuration creates more favorable conditions for discharge initiation and subsequent propagation toward the opposite electrode. Second, microscopic irregularities on the dielectric surface induce stronger local electric field enhancement than comparable features on metallic electrodes. Third, in high-electric-field regions adjacent to the dielectric surface, desorption processes significantly enhance electron multiplication during gas discharge, and this enhancement effect becomes more pronounced as gas pressure increases, further lowering the discharge inception threshold. As a result, discharge initiation at dielectric interfaces requires less stringent electric field conditions compared to breakdown in a gas gap, especially at high gas pressure. This conclusion not only accounts for the saturation behavior in the U_bd-p characteristic of SF₆ gas–solid interface discharges but also explains why surface contaminants/defects disproportionately degrade interfacial insulation performance relative to their impact on gas gaps. Full article

Aiming at common problems such as high classification error rate, environmental noise interference, regional discontinuity, and structural absence in the semantic segmentation of residential areas, this paper proposes a CrossAtt-UNet architecture based on the Cross Attention mechanism. This network is based on the Att-UNet framework and innovatively proposes a Cross Attention module. Cross-level information features are extracted by establishing cross-associations on the feature map’s horizontal and vertical coordinate axes. It ensures the efficient utilization of computing resources and significantly improves the accuracy of semantic segmentation and the adjacency relationship of the target region. After many experimental verifications, this network architecture performs outstandingly on the semantic segmentation dataset of living areas, with an accuracy of 95.47%, an mAP (mean average precision) of 94.57%, an mIoU (mean intersection over union) of 89.80%, an F1-score of 94.63%, a train_loss (training loss) of 0.0878, and a val_loss (validation loss) of 0.1459. Its segmentation performance, area integrity, and edge recognition accuracy are higher than those of mainstream networks. The concrete damage detection experiment further indicates that this network has good generalization ability, demonstrating stable performance and robustness. Full article

We hereby present a case of a 51-year-old woman with a pigmented nodule in the right axillary region. Histopathological examination revealed features consistent with an intradermal nevus. Notably, adjacent to the nevus, intralymphatic protrusion and lymphatic invasion were observed, comprising cells with morphological and immunohistochemical characteristics consistent with nevus cells. Next-generation sequencing revealed the BRAF V600E mutation. To date, 26 similar cases involving intralymphatic nevus cell protrusion and lymphatic invasion have been reported in the literature. Although this finding is rare and may pose a diagnostic challenge for pathologists, it should not be interpreted as indicative of malignancy. Rather, it must be assessed in the context of the lesion’s overall histological architecture. Full article

Deep learning for precipitation forecasting remains constrained by complex meteorological factors affecting accuracy. To address this issue, this paper proposes TransMambaCNN, which is a spatiotemporal transformer network fusing state-space models and CNNs for short-term precipitation forecasting. The core of the model employs a Convolutional State-Space Module (C-SSM), which efficiently extracts spatiotemporal features from multi-source meteorological variables by replacing the self-attention mechanism in the Vision Transformer (ViT) with an Attentive State-Space Module (ASSM) and augmenting its feature extraction capacity with integrated depthwise convolution. Its dual-branch architecture consists of a global branch, where C-SSM captures long-range dependencies and global spatiotemporal patterns, and a local branch, which leverages multi-scale convolutions based on SimVP’s Inception structure to extract fine-grained local features. The deep fusion of these dual branches significantly enhances spatiotemporal feature representation.Experiments demonstrate that in southeastern China and adjacent marine areas (period of high precipitation: April–September), TransMambaCNN achieves a 13.38% and 47.67% improvement in Threat Score (TS) over PredRNN at thresholds of ≥25 mm and ≥50 mm, respectively. In the Qinghai Sanjiangyuan region of western China (a precipitation-scarce area), TransMambaCNN’s TS score surpasses SimVP by 11.86 times at the ≥25 mm threshold. Full article

Road extraction from high-resolution remote sensing images (HRSIs) provides critical support for downstream tasks such as autonomous driving path planning and urban planning. Although deep learning-based pixel-level segmentation methods have achieved significant progress, they still face challenges in handling occlusions caused by vegetation and shadows, and often exhibit limited model robustness and generalization capability. To address these limitations, this paper proposes the SAM2MS model, which leverages the powerful generalization capabilities of the foundational vision model, segment anything model 2 (SAM2). Firstly, an adapter-based fine-tuning strategy is employed to effectively transfer the capabilities of SAM2 to the HRSI road extraction task. Secondly, we subsequently designed a subtraction block (Sub) to process adjacent feature maps, effectively eliminating redundancy during the decoding phase. Multiple Subs are cascaded to form the multi-scale subtraction module (MSSM), which progressively refines local feature representations, thereby enhancing segmentation accuracy. During training, a training-free lossnet module is introduced, establishing a multi-level supervision strategy that encompasses background suppression, contour refinement, and region-of-interest consistency. Extensive experiments on three large-scale and challenging HRSI road datasets, including DeepGlobe, SpaceNet, and Massachusetts, demonstrate that SAM2MS significantly outperforms baseline methods across nearly all evaluation metrics. Furthermore, cross-dataset transfer experiments (from DeepGlobe to SpaceNet and Massachusetts) conducted without any additional training validate the model’s exceptional generalization capability and robustness. Full article