Search Results (1,206)

Precise tumor segmentation in multimodal MRI is crucial for glioma diagnosis and treatment planning; yet, deep learning models still struggle with irregular boundaries and severe class imbalance under computational constraints. An Enhanced 3D DenseNet with CDC architecture was proposed, integrating Central Difference Convolution, attention gates, and Atrous Spatial Pyramid Pooling for brain tumor segmentation on the BraTS 2023-GLI dataset. CDC layers enhance boundary sensitivity by combining intensity-level semantics and gradient-level features. Attention gates selectively emphasize relevant encoder features during skip connections, whereas the ASPP captures the multi-scale context with dilation rates. A hybrid loss function spanning three levels was introduced, consisting of a region-based Dice loss for volumetric overlap, a GPU-native 3D Sobel boundary loss for edge precision, and a class-weighted focal loss for handling class imbalance. The proposed model achieved a mean Dice score of 91.30% (ET: 87.84%, TC: 92.73%, WT: 93.34%) on the test set. Notably, these results were achieved with approximately 3.7 million parameters, representing a 17–76x reduction compared to the 50–200 million parameters required by transformer-based approaches. Enhanced 3D DenseNet with CDC architecture demonstrates that the integration of gradient-sensitive convolutions, attention mechanisms, multi-scale feature extraction, and multi-level loss optimization achieves competitive segmentation performance with significantly reduced computational requirements. Full article

For the purpose of fulfilling the dual requirements of persistent cellular network connectivity and flight safety for cellular-connected Unmanned Aerial Vehicles (UAVs) operating in dense urban airspace, this paper presents an A*-oriented comprehensive path-planning scheme for multiple connected UAVs that integrates a radio map and complex network. Existing research often lacks rigorous processing of environmental map data, while the traditional A* algorithm struggles to simultaneously handle constraints such as obstacle avoidance, flight maneuverability, and multi-UAV path conflicts. To overcome these limitations, this study first constructs a path-planning model based on complex-network theory using environmental data and the radio map, clarifying the separation of responsibilities between environment representation and algorithmic search. On this basis, we proposed an improved A* algorithm for multi-UAV scenarios termed MURM-A*. Simulation results demonstrate that the proposed algorithm effectively avoids collisions with obstacles, adheres to UAV flight dynamics, and prevents spatial conflicts between multi-UAV paths, while achieving a joint optimization between path efficiency and radio quality. In terms of performance comparison, the proposed algorithm shows a marginal difference but ensures operational validity compared to traditional A*, exhibits a slightly increase in flight time but achieves a substantial reduction in radio-outage time compared to the Deep Reinforcement Learning (DRL) method. Furthermore, employing the path-planning model enables the algorithm to more accurately identify environmental information compared to directly using raw environmental maps. The modeling time is also notably shorter than the training time required for DRL methods. This study provides a well-structured and extensible systematic framework for reliable path planning of multiple cellular-connected UAVs in complex radio environments. Full article

Building extraction from remote sensing imagery plays a pivotal role in applications such as smart cities, urban planning, and disaster assessment. Although deep learning has significantly advanced this task, existing methods still struggle to strike an effective balance among global semantic understanding, local detail recovery, and multi-scale contextual awareness—particularly when confronted with challenges including extreme scale variations, complex spatial distributions, occlusions, and ambiguous boundaries. To address these issues, we propose TriadFlow-Net, an efficient end-to-end network architecture. First, we introduce the Multi-scale Attention Feature Enhancement Module (MAFEM), which employs parallel attention branches with varying neighborhood radii to adaptively capture multi-scale contextual information, thereby alleviating the problem of imbalanced receptive field coverage. Second, to enhance robustness under severe occlusion scenarios, we innovatively integrate a Non-Causal State Space Model (NC-SSD) with a Densely Connected Dynamic Fusion (DCDF) mechanism, enabling linear-complexity modeling of global long-range dependencies. Finally, we incorporate a Multi-scale High-Frequency Detail Extractor (MHFE) along with a channel–spatial attention mechanism to precisely refine boundary details while suppressing noise. Extensive experiments conducted on three publicly available building segmentation benchmarks demonstrate that the proposed TriadFlow-Net achieves state-of-the-art performance across multiple evaluation metrics, while maintaining computational efficiency—offering a novel and effective solution for high-resolution remote sensing building extraction. Full article

Accurate joint estimation of heterogeneous hydraulic conductivity fields and time-varying contaminant source parameters in groundwater systems constitutes a challenging high-dimensional inverse problem, particularly under sparse observational conditions and high computational demands. To alleviate this limitation, this study proposes an autoregressive depthwise convolutional neural network (AR-DWCNN) as a lightweight surrogate model for coupled groundwater flow and contaminant transport simulations. The proposed model employs depthwise separable convolutions and dense connectivity within an encoder–decoder framework to capture nonlinear flow and spatiotemporal transport dynamics while reducing model complexity and computational demand relative to conventional convolutional architectures. The AR-DWCNN is further integrated with an enhanced Iterative Local Updating Ensemble Smoother incorporating Levenberg–Marquardt regularization, enabling efficient joint inversion of high-dimensional hydraulic conductivity fields and multi-period contaminant source strengths. Numerical experiments conducted on a synthetic two-dimensional heterogeneous aquifer demonstrate that the surrogate-assisted inversion framework achieves posterior estimates that closely match those obtained using the numerical forward model, while significantly improving computational efficiency. These results indicate that the AR-DWCNN-based inversion method provides an effective and scalable solution for high-dimensional groundwater contaminant transport inverse problems, offering practical potential for uncertainty quantification and remediation design in complex subsurface systems. Full article

Withcontinuous advancements in remote sensing technology, object detection in remote sensing images has emerged as a critical research direction in maritime surveillance, port management, and national defense. Among these applications, ship detection is a key task. Due to the fact that ships in images typically exhibit arbitrary rotations, multi-scale distributions, and complex backgrounds, conventional detection methods based on horizontal or rotated bounding boxes often fail to adequately capture the fine-grained information of the targets, thereby compromising detection accuracy. This paper proposes the Dense Representative Points-Guided Rotated-Ship Detection (DenseRRSD) method. The proposed approach represents ship objects using dense representative points (RepPoints) to effectively capture local semantic information, thereby avoiding the background noise issues associated with traditional rectangular bounding box representations. To further enhance detection accuracy, an edge region sampling strategy is devised to uniformly sample RepPoints from critical ship parts, and a Weighted Residual Feature Pyramid Network (WRFPN) is introduced to efficiently fuse the multi-scale features through residual connections and learnable weights. In addition, a Weighted Chamfer Loss (WCL) combined with a staged localization loss strategy is employed to progressively refine localization from coarse to fine stages. Experimental results on both the HRSC2016 dataset and the newly constructed DOTA-SHIP dataset demonstrate that DenseRRSD achieves state-of-the-art detection accuracy, with mean Average Precision (mAP) scores of 91.2% and 83.2%, respectively, significantly outperforming existing methods. These results verify the effectiveness and robustness of the proposed approach in rotated-ship detection under diverse conditions. Full article

Background/Objectives: SLC13A5 encodes a sodium–citrate cotransporter implicated in early-onset epileptic encephalopathy and metabolic brain dysfunction, yet its developmental regulation and molecular context in the human brain remain incompletely defined. Methods: Leveraging human developmental transcriptomes from the Evo-Devo resource, we delineated tissue trajectories and network context for SLC13A5 across the fetal–postnatal life. Results: In the cerebrum, SLC13A5 expression rises from late fetal stages to peak in the first postnatal year and then declines into adulthood, while cerebellar levels increase across the lifespan; liver shows a fetal decrease followed by sustained postnatal upregulation. A transcriptome-wide scan identified extensive positive and negative associations with SLC13A5, and a signed weighted gene co-expression network analysis (WGCNA) built on biweight midcorrelation placed SLC13A5 in a large module. The module eigengene tracked brain maturation (Spearman rho = 0.802, p = 8.62 × 10⁻⁶) and closely matched SLC13A5 abundance (rho = 0.884, p = 2.73 × 10⁻⁶), with a significant partial association after adjusting for developmental rank (rho = 0.672, p = 6.17 × 10⁻⁴). Functional enrichment converged on oxidative phosphorylation and mitochondria. A force-directed subnetwork of the top intramodular members (|bicor| > 0.6) positioned SLC13A5 adjacent to a densely connected nucleus including CYP46A1, ITM2B, NRGN, GABRD, FBXO2, CHCHD10, CYSTM1, and MFSD4A. Conclusions: Together, these results define a developmentally tuned, mitochondria-centered program that co-varies with SLC13A5 in the human brain across the lifespan. It may provide insights to interrogate age-dependent phenotypes and therapeutic avenues for disorders involving citrate metabolism. Full article

With accelerating urbanisation, extreme rainfall events have become increasingly frequent, leading to rising urban flooding risks that threaten city operation and infrastructure safety. The rapid expansion of impervious surfaces reduces infiltration capacity and accelerates runoff responses, making cities more vulnerable to short-duration, high-intensity storms. Although the SWMM is widely used for urban stormwater simulation, its application is often constrained by the lack of detailed drainage network data, such as pipe diameters, slopes, and node connectivity. To address this limitation, this study focuses on the main built-up area within the Second Ring Expressway of Chengdu, Sichuan Province, in southwestern China. As a regional core city, Chengdu frequently experiences intense short-duration rainfall during the rainy season, and the coexistence of rapid urbanisation with ageing drainage infrastructure further elevates flood risk. Accordingly, a technical framework of “open road data substitution–automated modelling–SWMM-based assessment” is proposed. Leveraging the spatial correspondence between road layouts and drainage pathways, open road data are used to construct a virtual drainage system. Combined with DEM and land-use data, Python-based automation enables sub-catchment delineation, parameter extraction, and network topology generation, achieving efficient large-scale modelling. Design storms of multiple return periods are generated based on Chengdu’s revised rainfall intensity formula, while socioeconomic indicators such as population density and infrastructure exposure are normalised and weighted using the entropy method to develop a comprehensive flood-risk assessment. Results indicate that the virtual drainage network effectively compensates for missing pipe data at the macro scale, and high-risk zones are mainly concentrated in densely populated and highly urbanised older districts. Overall, the proposed method successfully captures urban flood-risk patterns under data-scarce conditions and provides a practical approach for large-city flood-risk management. Full article

Prolonged tooth loss causes alveolar ridge atrophy, complicating implantation, especially in patients with impaired mineral metabolism. This study aimed to develop a personalized titanium mesh for guided bone regeneration and qualitatively evaluate its local tissue response in a vitamin D3-deficient rabbit model. A titanium mesh design has been developed in the form of a plate-shaped profile frame of a truncated pyramid with a solid upper base and perforated side faces. For testing in a rabbit model with vitamin D3 deficiency, a bone defect was created and repaired in the mandible using hydroxyapatite, an individual titanium mesh and a collagen membrane. Histological analysis was performed in the Laboratory of Digital Microscopic Analysis. The optimized geometry and parameters of the mesh openings contributed to effective vascularization and osteogenesis. In the postoperative period (3, 5 and 7 days), moderate edema and hyperemia were noted with their complete leveling by the 7th day (p < 0.05). According to the histological examination, 3 months after the installation of the titanium mesh, the formation of dense connective tissue with signs of active osteogenesis was observed in the defect area, including zones of mineralized bone trabeculae, osteocytes and osteon elements. The findings of this study indicate acceptable biocompatibility of the developed titanium structure and suggest osteoconductive potential, which, however, needs to be confirmed in controlled, quantitatively powered studies. Full article

We present a unified description of dense matter and neutron star structure based on simple but physically motivated models. Starting from the thermodynamics of degenerate Fermi gases, we construct an equation of state for cold, catalyzed matter by combining relativistic fermion statistics with the liquid drop model of nuclear binding. The internal stratification of matter in the outer crust is described by the $\beta$-equilibrium, neutron drip and a gradual transition to supranuclear matter. Short-range repulsive interactions inspired by Quantum Hadrodynamics are incorporated at high densities in order to ensure stability and causality. The resulting equation of state is used as input in the Tolman–Oppenheimer–Volkoff equations, yielding self-consistent neutron star models. We compute macroscopic stellar properties including the mass–radius relation, compactness and surface redshift that can be compared with recent observational data. Despite the simplicity of the underlying microphysics, the model produces neutron star masses and radii compatible with current observational constraints from X-ray timing and gravitational-wave measurements. This work demonstrates that physically transparent models can capture the essential features of neutron star structure and provide valuable insight into the connection between dense-matter physics and astrophysical observables; they can also be used as easy-to-handle models to test the impact of more complicated phenomena and variations in neutron stars. Full article

Background and Clinical Significance: Fibrolipoma is an uncommon histological variant of lipoma characterized by mature adipose tissue with a significant fibrous component. Intraoral lipomas are rare (only about 1–4% of all lipomas) and lipomas arising in the buccal fat pad (buccal space) are particularly uncommon. Case Presentation: A 47-year-old male presented with a painless, slowly enlarging swelling in the left cheek region. Physical examination revealed a soft, non-tender mass in the buccal space, causing mild bulging of the cheek. Contrast-enhanced computed tomography and magnetic resonance imaging demonstrated a well-circumscribed lesion within the left buccal fat pad suggestive of a lipoma. The tumor was excised entirely via an intraoral approach under general anesthesia. Histopathological examination showed lobules of mature adipocytes interspersed with dense fibrous connective septa consistent with a diagnosis of a fibrolipoma. The postoperative course was uneventful. Conclusions: This case highlights that fibrolipoma, while rare in the maxillofacial region, should be included in the differential diagnosis of buccal space tumors. Imaging studies can aid in identifying the fatty nature and extent of such lesions, but definitive diagnosis relies on histopathology. The buccal fat pad’s anatomy allows an intraoral surgical approach in appropriate cases, providing direct access and excellent cosmetic outcomes. Complete excision is curative in benign fibrolipomas, and careful surgical technique prevents injury to adjacent structures. Full article

Background: Type 2 diabetes mellitus (T2DM) and periodontitis are highly prevalent immune-inflammatory diseases that interact bidirectionally. However, how early-onset T2DM, periodontitis, and adverse lifestyle behaviors collectively remodel the gingival plaque microbiome at the ecological network level remains poorly understood in Indian populations. Methods: A cross-sectional 16S rRNA gene (V3–V4) sequencing study was conducted on supragingival and subgingival plaque from 60 adults (30–40 years) recruited in Mumbai. Participants were categorized as healthy (H, n = 10), periodontitis (P, n = 10), T2DM (n = 20), and T2DM with periodontitis (T2DM_P, n = 20). Comprehensive demographic, anthropometric, metabolic, periodontal, dietary, lifestyle, and oral hygiene data were collected. Sequence data were processed using QIIME2–DADA2, followed by diversity, differential abundance, and genus-level co-occurrence network analyses (Spearman |r| ≥ 0.6, FDR < 0.05; core prevalence ≥ 70%). Results: α-diversity showed no marked depletion across groups, whereas Bray–Curtis β-diversity revealed significant global separation, with maximal dissimilarity between H and T2DM_P. Healthy individuals with favorable lifestyle behaviors harbored scaffold-forming taxa such as Corynebacterium matruchotii, Lautropia mirabilis, and Capnocytophaga spp. In contrast, P and T2DM_P groups showed enrichment of proteolytic, inflammation-adapted genera including Porphyromonas, Tannerella, Treponema, Fretibacterium, Peptostreptococcus, and Selenomonas. Network analysis revealed a shift from commensal-rich modular networks to densely connected, keystone-centered disease modules. Conclusion: Early-onset T2DM and periodontitis, particularly under adverse lifestyle behaviors, reorganize plaque microbial composition and interaction architecture rather than depleting diversity, highlighting plaque-based keystone taxa and networks as targets for microbiome-informed risk stratification and integrated medical–dental–lifestyle interventions. Full article

Semantic segmentation of high-resolution remote sensing imagery is a critical technology for the intelligent interpretation of sensor data, supporting automated environmental monitoring and urban sensing systems. However, processing data from dense urban scenarios remains challenging due to sensor signal occlusions (e.g., shadows) and the complexity of parsing multi-scale targets from optical sensors. Existing approaches often exhibit a trade-off between the accuracy of global semantic modeling and the precision of complex boundary recognition. While the Segment Anything Model (SAM) offers powerful zero-shot structural priors, its direct application to remote sensing is hindered by domain gaps and the lack of inherent semantic categorization. To address these limitations, we propose a dual-branch cooperative network, PriorSAM-DBNet. The main branch employs a Densely Connected Swin (DC-Swin) Transformer to capture cross-scale global features via a hierarchical shifted window attention mechanism. The auxiliary branch leverages SAM’s zero-shot capability to exploit structural universality, generating object-boundary masks as robust signal priors while bypassing semantic domain shifts. Crucially, we introduce a parameter-efficient Scaled Subsampling Projection (SSP) module that employs a weight-sharing mechanism to align cross-modal features, freezing the massive SAM backbone to ensure computational viability for practical sensor applications. Furthermore, a novel Attentive Cross-Modal Fusion (ACMF) module is designed to dynamically resolve semantic ambiguities by calibrating the global context with local structural priors. Extensive experiments on the ISPRS Vaihingen, Potsdam, and LoveDA-Urban datasets demonstrate that PriorSAM-DBNet outperforms state-of-the-art approaches. By fine-tuning only 0.91 million parameters in the auxiliary branch, our method achieves mIoU scores of 82.50%, 85.59%, and 53.36%, respectively. The proposed framework offers a scalable, high-precision solution for remote sensing semantic segmentation, particularly effective for disaster emergency response where rapid feature recognition from sensor streams is paramount. Full article

Automated recognition of rock mass discontinuities in vegetated high-slope terrains remains a challenging task critical to geohazard assessment and slope stability analysis. This study presents an integrated framework combining close-range UAV photogrammetry with an Improved Superpoint Transformer (ISPT) for semantic segmentation and structural characterization. High-resolution UAV imagery was processed using an SfM–MVS photogrammetric workflow to generate dense point clouds, followed by a three-stage filtering workflow comprising cloth simulation filtering, volumetric density analysis, and VDVI-based vegetation discrimination. Feature augmentation using volumetric density and the Visible-Band Difference Vegetation Index (VDVI), together with connected-component segmentation, enhanced robustness under vegetation occlusion. Validation on four vegetated slopes in Buyun Mountain, China, achieved an overall classification accuracy of 89.5%, exceeding CANUPO (78.2%) and the baseline SPT (85.8%), with a 25-fold improvement in computational efficiency. In total, 4918 structural planes were extracted, and their orientations, dip angles, and trace lengths were automatically derived. The proposed ISPT-based framework provides an efficient and reliable approach for high-precision geotechnical characterization in complex, vegetation-covered rock mass environments. Full article

Population migration is an important indicator for measuring the interactions and connections between cities. Analyzing the spatiotemporal distribution pattern of the migration flows between cities is highly important to understanding urban development relationships and regional structures. From a spatiotemporal perspective, we conduct STFlowLISA (Space-Time Flow Local Indicator of Spatial Association) spatiotemporal autocorrelation analysis using population migration data from Hubei Province from 2018 to 2023 and, on this basis, calculate the spatiotemporal hub index and identify spatiotemporal clusters. The research aims to reveal the regional spatial structure shaped by migration flows and compare it with that of existing town system planning to evaluate deviations and provide a decision-making basis for the regional synergistic development of Hubei Province. The key findings include: (1) the population migration flows between Wuhan and its surrounding cities mostly exhibit a spatiotemporal distribution pattern of HH (high-value agglomeration), whereas the long-distance migration flows between eastern and western Hubei mostly follow a pattern of LL (low-value agglomeration), and these urban connections show improvement after the epidemic; (2) the spatiotemporal hubs of Hubei Province demonstrate a “core-periphery” structure with Wuhan as the absolute core, while Xiangyang’s role as a subcenter does not meet planning expectations; and (3) urban spatiotemporal clusters are dense in the east and sparse in the west, with Enshi and Shiyan showing disconnection from the main network, which deviates from the planned polycentric spatial pattern. By examining the spatiotemporal autocorrelation of migration flows, this study enriches the empirical understanding of regional spatial structure in Hubei Province within the framework of classical spatial theory and highlights the necessity of incorporating dynamic flow analysis into regional planning and policy-making. Full article

The advancement of hyperspectral image super-resolution (HSI-SR) has been significantly propelled by deep learning techniques. However, current methods predominantly rely on 2D or 3D convolutional networks, which are inherently local and thus limited in modeling long-range spectral–depth interactions. This work introduces a novel network architecture designed to address this gap through recursive deep feature learning. Our model initiates with 3D convolutions to extract preliminary spectral–spatial features, which are progressively refined via densely connected grouped convolutions. A core innovation is a recursively formulated generalized self-attention mechanism, which captures long-range dependencies across the spectral dimension with linear complexity. To reconstruct fine spatial details across multiple scales, a progressive upsampling strategy is further incorporated. Evaluations on several public benchmarks demonstrate that the proposed approach outperforms existing state-of-the-art methods in both quantitative metrics and visual quality. Full article