Search Results (2,804)

To address the application requirements of Visual Simultaneous Localization and Mapping (VSLAM) in intracavitary environments and the scarcity of gold-standard datasets for deep learning methods, this study proposes a hybrid attention mechanism combined with U-Net for vascular branch point extraction in endoluminal images (SuperVessel). The network is initialized via transfer learning with pre-trained SuperRetina model parameters and integrated with a vascular feature detection and matching method based on dual branch fusion and structure enhancement, generating a pseudo-gold-standard vascular branch point dataset. The framework employs a dual-decoder architecture, incorporates a dynamic up-sampling module (CBAM-Dysample) to refine local vessel features through hybrid attention mechanisms, designs a Dice-Det loss function weighted by branching features to prioritize vessel junctions, and introduces a dynamically weighted Triplet-Des loss function optimized for descriptor discrimination. Experiments on the Vivo test set demonstrate that the proposed method achieves an average Area Under Curve (AUC) of 0.760, with mean feature points, accuracy, and repeatability scores of 42,795, 0.5294, and 0.46, respectively. Compared to SuperRetina, the method maintains matching stability while exhibiting superior repeatability, feature point density, and robustness in low-texture/deformation scenarios. Ablation studies confirm the CBAM-Dysample module’s efficacy in enhancing feature expression and convergence speed, offering a robust solution for intracavitary SLAM systems. Full article

To address challenges such as small target size, high density, severe occlusion, complex background interference, and edge device computational constraints, a lightweight model, GAFNet, is proposed based on YOLO11n, optimized for rice pest detection in field environments. To improve feature perception, we propose the Global Attention Fusion and Spatial Pyramid Pooling (GAM-SPP) module, which captures global context and aggregates multi-scale features. Building on this, we introduce the C3-Efficient Feature Selection Attention (C3-EFSA) module, which refines feature representation by combining depthwise separable convolutions (DWConv) with lightweight channel attention to enhance background discrimination. The model’s detection head, Enhanced Ghost Detect (EGDetect), integrates Enhanced Ghost Convolution (EGConv), Squeeze-and-Excitation (SE), and Sigmoid-Weighted Linear Unit (SiLU) activation, which reduces redundancy. Additionally, we propose the Focal-Enhanced Complete-IoU (FECIoU) loss function, incorporating stability and hard-sample weighting for improved localization. Compared to YOLO11n, GAFNet improves Precision, Recall, and mean Average Precision (mAP) by 3.5%, 4.2%, and 1.6%, respectively, while reducing parameters and computation by 5% and 21%. GAFNet can deploy on edge devices, providing farmers with instant pest alerts. Further, GAFNet is evaluated on the AgroPest-12 dataset, demonstrating enhanced generalization and robustness across diverse pest detection scenarios. Overall, GAFNet provides an efficient, reliable, and sustainable solution for early pest detection, precision pesticide application, and eco-friendly pest control, advancing the future of smart agriculture. Full article

Accurate plant leaf image segmentation plays a crucial role in species recognition, phenotypic analysis, and disease detection. However, most segmentation models perform poorly in complex field environments due to challenges such as overlapping leaves and uneven sunlight. This research proposes an Edge-Aware High-Frequency Preservation Network (EHPNet) for leaf segmentation in complex field environments. Specifically, a High-Frequency Edge Fusion Module (HEFM) is introduced into the skip connections to preserve high-frequency edge information during feature extraction and enhance boundary localization. In addition, a Structural Recalibration Attention Module (SRAM) is incorporated into the decoder to refine edge structural features across multiple scales and retain spatial continuity, which leads to more accurate reconstruction of leaf boundaries. Experimental results on a composite dataset constructed from Pl@ntLeaves and ATLDSD show that EHPNet achieves 98.25%, 99.25%, 99.03%, 98.51%, and 98.77% in mean Intersection over Union (mIoU), accuracy, precision, recall, and F1 score, respectively. Compared with state-of-the-art methods, EHPNet achieves superior overall performance, which demonstrates its effectiveness for leaf segmentation in complex field environments. Full article

In the field management of maize, phenomena such as missed sowing and empty seedlings directly affect the final yield. By implementing seedling replenishment activities and promptly evaluating seedling growth, maize output can be increased by improving seedling survival rates. To address the challenges posed by complex field environments (including varying light conditions, weeds, and foreign objects), as well as the performance limitations of model deployment on resource-constrained devices, this study proposes a Lightweight Real-Time You Only Look Once (LRT-YOLO) model. This model builds upon the You Only Look Once version 11n (YOLOv11n) framework by designing a lightweight, optimized feature architecture (OF) that enables the model to focus on the characteristics of small to medium-sized maize seedlings. The feature fusion network incorporates two key modules: the Feature Complementary Mapping Module (FCM) and the Multi-Kernel Perception Module (MKP). The FCM captures global features of maize seedlings through multi-scale interactive learning, while the MKP enhances the network’s ability to learn multi-scale features by combining different convolution kernels with pointwise convolution. In the detection head component, the introduction of an NMS-free design philosophy has significantly enhanced the model’s detection performance while simultaneously reducing its inference time. The experiments show that the $mA{P}_{50}$ and $mA{P}_{50:95}$ of the LRT-YOLO model reached 95.9% and 63.6%, respectively. The model has only 0.86M parameters and a size of just 2.35 M, representing reductions of 66.67% and 54.89% in the number of parameters and model size compared to YOLOv11n. To enable mobile deployment in field environments, this study integrates the LRT-YOLO model with the ByteTrack multi-object tracking algorithm and deploys it on the NVIDIA Jetson AGX Orin platform, utilizing OpenCV tools to achieve real-time visualization of maize seedling tracking and counting. Experiments demonstrate that the frame rate (FPS) achieved with TensorRT acceleration reached 23.49, while the inference time decreased by 38.93%. Regarding counting performance, when tested using static image data, the coefficient of determination ($R^2$) and root mean square error (RMSE) were 0.988 and 5.874, respectively. The cross-line counting method was applied to test the video data, resulting in an $R^2$ of 0.971 and an RMSE of 16.912, respectively. Experimental results show that the proposed method demonstrates efficient performance on edge devices, providing robust technical support for the rapid, non-destructive counting of maize seedlings in field environments. Full article

Traditional fusion methods for integrating multi-source gravity data rely on predefined mathematical models that inadequately capture complex nonlinear relationships, particularly at wavelengths shorter than 10 km. We developed a convolutional neural network incorporating differential marine geodetic data (DMGD-CNN) to enhance marine gravity anomaly recovery from HY-2A satellite altimetry. The DMGD-CNN framework encodes spatial gradient information by computing differences between target points and their surrounding neighborhoods, enabling the model to explicitly capture local gravity field variations. This approach transforms absolute parameter values into spatial gradient representations, functioning as a spatial high-pass filter that enhances local gradient information critical for short-wavelength gravity signal recovery while reducing the influence of long-wavelength components. Through systematic ablation studies with eight parameter configurations, we demonstrate that incorporating first- and second-order seabed topography derivatives significantly enhances model performance, reducing the root mean square error (RMSE) from 2.26 mGal to 0.93 mGal, with further reduction to 0.85 mGal achieved by the differential learning strategy. Comprehensive benchmarking against international gravity models (SIO V32.1, DTU17, and SDUST2022) demonstrates that DMGD-CNN achieves 2–10% accuracy improvement over direct CNN predictions in complex topographic regions. Power spectral density analysis reveals enhanced predictive capabilities at wavelengths below 10 km for the direct CNN approach, with DMGD-CNN achieving further precision enhancement at wavelengths below 5 km. Cross-validation with independent shipborne surveys confirms the method’s robustness, showing 47–63% RMSE reduction in shallow water regions (<2000 m depth) compared to HY-2A altimeter-derived results. These findings demonstrate that deep learning with differential marine geodetic features substantially improves marine gravity field modeling accuracy, particularly for capturing fine-scale gravitational features in challenging environments. Full article

Modern port operations face increasing challenges from rapidly changing weather and environmental conditions, requiring accurate short-term forecasting to support safe and efficient maritime activities. This study presents a sensor fusion-based machine learning framework for real-time multi-target nowcasting of wind gust speed, sustained wind speed, and wind direction using heterogeneous data collected at the Port of Livorno from February to November 2025. Using an IoT architecture compliant with the oneM2M standard and deployed at the Port of Livorno, CNIT integrated heterogeneous data from environmental sensors (meteorological stations, anemometers) and vessel-mounted LiDAR systems through feature-level fusion to enhance situational awareness, with gust speed treated as the primary safety-critical variable due to its substantial impact on berthing and crane operations. In addition, a comparative performance analysis of Random Forest, XGBoost, LSTM, Temporal Convolutional Network, Ensemble Neural Network, Transformer models, and a Kalman filter was performed. The results show that XGBoost consistently achieved the highest accuracy across all targets, with near-perfect performance in both single-split testing (R² ≈ 0.999) and five-fold cross-validation (mean R² = 0.9976). Ensemble models exhibited greater robustness than deep learning approaches. The proposed multi-target fusion framework demonstrates strong potential for real-time deployment in Maritime Autonomous Surface Ship (MASS) systems and port decision-support platforms, enabling safer manoeuvring and operational continuity under rapidly varying environmental conditions. Full article

Background: Advances in molecular pathology have transformed NSCLC (Non-Small Cell Lung Cancer) diagnosis, prognosis, and treatment by enabling precise tumor characterization and targeted therapeutic strategies. We review key genomic alterations in NSCLC, including EGFR (epidermal growth factor receptor) mutations, ALK (anaplastic lymphoma kinase) and ROS1 (ROS proto-oncogene 1) rearrangements, BRAF (B-Raf proto-oncogene serine/threonine kinase) mutations, MET (mesenchymal–epithelial transition factor) alterations, KRAS (Kirsten rat sarcoma) mutations, HER2 (human epidermal growth factor receptor 2) alterations and emerging NTRK (neurotrophic receptor tyrosine kinase) fusions and AXL-related pathways. Methods: A total of 48 patients with NSCLC was analyzed, including 22 women and 26 men (mean age 70 years, range 44–86). Tumor specimens were classified histologically as adenocarcinomas (n = 81%) or squamous cell carcinomas (n = 19%). Smoking history, PD-L1 (programmed death-ligand 1) expression, and genetic alterations were assessed. NGS (Next-generation sequencing) identified genomic variants, which were classified according to ACMG (American College of Medical Genetics and Genomics) guidelines. Results: The cohort consisted of 29 former smokers, 13 current smokers, and 5 non-smokers (12%), with a mean smoking burden of 33 pack years. PD-L1 TPS (tumor proportion score) was ≥50% in 10 patients, ≥1–<50% in 22, and <1% in 15 patients. In total, 120 genomic variants were detected (allele frequency ≥ 5%). Of these, 52 (43%) were classified as likely pathogenic or pathogenic, 48 (40%) as variants of unknown significance, and 20 (17%) as benign or likely benign. The most frequently altered genes were TP53 (tumor protein p53) (31%), KRAS and EGFR (15% each), and STK11 (serine/threonine kinase 11) (12%). Adenocarcinomas accounted for 89% of all alterations, with TP53 (21%) and KRAS (15%) being most common, while squamous cell carcinomas predominantly harbored TP53 (38%) and MET (15%) mutations. In patients with PD-L1 TPS ≥ 50%, KRAS mutations were enriched (50%), particularly KRAS G12C and G12D, with frequent co-occurrence of TP53 mutations (20%). No pathogenic EGFR mutations were detected in this subgroup. Conclusions: Comprehensive genomic profiling in NSCLC revealed a high prevalence of clinically relevant mutations, with TP53, KRAS and EGFR as the dominant drivers. The strong association of KRAS mutations with high PD-L1 expression, irrespective of smoking history, highlights the interplay between genetic and immunological pathways in NSCLC. These findings support the routine implementation of broad molecular testing to guide precision oncology approaches in both adenocarcinoma and squamous cell carcinoma patients. Full article

Coronary artery disease (CAD) remains a leading cause of mortality worldwide, and accurate coronary artery segmentation in X-ray coronary angiography (XCA) is challenged by low contrast, structural ambiguity, and anisotropic vessel trajectories, which hinder quantitative coronary angiography. We propose HR-UMamba++, a U-Mamba-based framework centered on a rotation-aligned multi-directional state-space scan for modeling long-range vessel continuity across multiple orientations. To preserve thin distal branches, the framework is equipped with (i) a persistent high-resolution bypass that injects undownsampled structural details and (ii) a UNet++-style dense decoder topology for cross-scale topological fusion. On an in-house dataset of 739 XCA images from 374 patients, HR-UMamba++ is evaluated using eight segmentation metrics, fractal-geometry descriptors, and multi-view expert scoring. Compared with U-Net, Attention U-Net, HRNet, U-Mamba, DeepLabv3+, and YOLO11-seg, HR-UMamba++ achieves the best performance (Dice 0.8706, IoU 0.7794, HD95 16.99), yielding a relative Dice improvement of 6.0% over U-Mamba and reducing the deviation in fractal dimension by up to 57% relative to U-Net. Expert evaluation across eight angiographic views yields a mean score of 4.24 ± 0.49/5 with high inter-rater agreement. These results indicate that HR-UMamba++ produces anatomically faithful coronary trees and clinically useful segmentations that can serve as robust structural priors for downstream quantitative coronary analysis. Full article

High-resolution remote sensing images are gradually playing an important role in land cover mapping, urban planning, and environmental monitoring tasks. However, current segmentation approaches frequently encounter challenges such as loss of detail and blurred boundaries when processing high-resolution remote sensing imagery, owing to their complex backgrounds and dense semantic content. In response to the aforementioned limitations, this study introduces HMA-UNet, a novel segmentation network built upon the UNet framework and enhanced through a hybrid attention strategy. The architecture’s innovation centers on a composite attention block, where a lightweight split fusion attention (LSFA) mechanism and a lightweight channel-spatial attention (LCSA) mechanism are synergistically integrated within a residual learning structure to replace the stacked convolutional structure in UNet, which can improve the utilization of important shallow features and eliminate redundant information interference. Comprehensive experiments on the WHDLD dataset and the DeepGlobe road extraction dataset show that our proposed method achieves effective segmentation in remote sensing images by fully utilizing shallow features and eliminating redundant information interference. The quantitative evaluation results demonstrate the performance of the proposed method across two benchmark datasets. On the WHDLD dataset, the model attains a mean accuracy, IoU, precision, and recall of 72.40%, 60.71%, 75.46%, and 72.41%, respectively. Correspondingly, on the DeepGlobe road extraction dataset, it achieves a mean accuracy of 57.87%, an mIoU of 49.82%, a mean precision of 78.18%, and a mean recall of 57.87%. Full article

Underwater images frequently suffer from color casts, low illumination, and blur due to wavelength-dependent absorption and scattering. We present a practical two-stage, modular, and degradation-aware framework designed for real-time enhancement, prioritizing deployability on edge devices. Stage I employs a lightweight CNN to classify inputs into three dominant degradation classes (color cast, low light, blur) with 91.85% accuracy on an EUVP subset. Stage II applies three scene-specific lightweight enhancement pipelines and fuses their outputs using two alternative learnable modules: a global Linear Fusion and a LiteUNetFusion (spatially adaptive weighting with optional residual correction). Compared to the three single-scene optimizers (average PSNR = 19.0 dB; mean UCIQE ≈ 0.597; mean UIQM ≈ 2.07), the Linear Fusion improves PSNR by +2.6 dB on average and yields roughly +20.7% in UCIQE and +21.0% in UIQM, while maintaining low latency (~90 ms per 640 × 480 frame on an Intel i5-13400F (Intel Corporation, Santa Clara, CA, USA). The LiteUNetFusion further refines results: it raises PSNR by +1.5 dB over the Linear model (23.1 vs. 21.6 dB), brings modest perceptual gains (UCIQE from 0.72 to 0.74, UIQM 2.5 to 2.8) at a runtime of ≈125 ms per 640 × 480 frame, and better preserves local texture and color consistency in mixed-degradation scenes. We release implementation details for reproducibility and discuss limitations (e.g., occasional blur/noise amplification and domain generalization) together with future directions. Full article

High-resolution satellite precipitation products are key inputs for basin-scale rainfall estimation, but they still exhibit substantial biases in complex terrain and during heavy rainfall. Recent multi-source fusion studies have shown that simply stacking multiple same-type microwave satellite products yields only limited additional gains for high-quality precipitation estimates and may even introduce local degradation, suggesting that targeted correction of a single, widely validated high-quality microwave product (such as IMERG) is a more rational strategy. Focusing on the mountainous, gauge-sparse Lüshui River basin with pronounced relief and frequent heavy rainfall, we use GPM IMERG V07 as the primary microwave product and incorporate CHIRPS, ERA5 evaporation, and a digital elevation model as auxiliary inputs to build a daily attention-enhanced CNN–LSTM (A-CNN–LSTM) bias-correction framework. Under a unified IMERG-based setting, we compare three network architectures—LSTM, CNN–LSTM, and A-CNN–LSTM—and test three input configurations (single-source IMERG, single-source CHIRPS, and combined IMERG + CHIRPS) to jointly evaluate impacts on corrected precipitation and SWAT runoff simulations. The IMERG-driven A-CNN–LSTM markedly reduces daily root-mean-square error and improves the intensity and timing of 10–50 mm·d⁻¹ rainfall events; the single-source IMERG configuration also outperforms CHIRPS-including multi-source setups in terms of correlation, RMSE, and performance across rainfall-intensity classes. When the corrected IMERG product is used to force SWAT, daily Nash-Sutcliffe Efficiency increases from about 0.71/0.70 to 0.85/0.79 in the calibration/validation periods, and RMSE decreases from 87.92 to 60.98 m³ s⁻¹, while flood peaks and timing closely match simulations driven by gauge-interpolated precipitation. Overall, the results demonstrate that, in gauge-sparse mountainous basins, correcting a single high-quality, widely validated microwave product with a small set of heterogeneous covariates is more effective for improving precipitation inputs and their hydrological utility than simply aggregating multiple same-type satellite products. Full article

Gait recognition using wearable sensor data is crucial for healthcare, rehabilitation, and monitoring neurological and musculoskeletal disorders. This study proposes a deep learning framework for gait classification using inertial measurements from four body-mounted IMU sensors (head, lower back, and both feet). The data were collected from a publicly available, clinically annotated dataset comprising 1356 gait trials from 260 individuals with diverse pathologies. The framework, G-MASA-TCN (Gait Multi-Anchor, Space-Aware Temporal Convolutional Network), integrates multi-scale temporal fusion, graph-informed spatial modeling, and residual dilated convolutions to extract discriminative gait signatures. To ensure both high performance and interpretability, Integrated Gradients is incorporated as an explainable AI (XAI) method, providing sensor-level and temporal attributes that reveal the features driving model decisions. The framework is evaluated via repeated cross-validation experiments, reporting detailed metrics with cross-run statistical analysis (mean ± standard deviation) to assess robustness. Results show that G-MASA-TCN achieves 98% classification accuracy for neurological, orthopedic, and healthy cohorts, demonstrating superior stability and resilience compared to baseline architectures, including Gated Recurrent Unit (GRU), Transformer neural networks, and standard TCNs, and 98.4% accuracy in identifying individual subjects based on gait. Furthermore, the model offers clinically meaningful insights into which sensors and gait phases contribute most to its predictions. This work presents an accurate, interpretable, and reliable tool for gait pathology recognition, with potential for translation to real-world clinical settings. Full article

Background: Reconstruction of limbs with extensive bone loss often requires complex surgical procedures, which can be technically demanding, time-consuming, and physically and psychologically burdensome for patients. Historically, the lack of alternatives for large bone defects often led to primary amputation. Modern musculoskeletal practice allows for reconstruction using autologous or allogeneic bone grafts, or through more complex procedures such as the Masquelet technique or distraction osteogenesis. However, these methods share a common challenge: the need for a docking site procedure in cases of insufficient bony fusion of the transport segment. The aim of this study was to identify predictive factors for the need for a docking site procedure. Methods: A retrospective analysis was conducted on 93 patients treated for lower extremity bone defects between January 2013 and June 2023. Of these, 39 patients (41.9%) underwent segmental bone transport and formed the study cohort for the predictive model analysis. Patients of all ages and both genders were included, regardless of the etiology and size of the defect. The need for a docking site procedure was analyzed using logistic regression, ROC analysis, and ANOVA. Results: The study included 93 patients (73 male, 19 female) aged 7 to 83 years. The mean defect size was 76.46 mm (range: 12.1 to 225.1 mm). The mean transport duration was 149.97 days, with a mean transport speed of 0.61 mm/day. Among the 39 segmental transport patients, a docking site procedure was performed in 64.1% (n = 25). Logistic regression and ROC analysis were performed on this subgroup (n = 39, with 25 events). Significant predictors for the need for a docking site procedure were age (p = 0.024), vascular injury (p = 0.009), transport duration (p = 0.001), and transport speed (p < 0.001). ROC analysis demonstrated that transport speed (AUC = 0.931) and transport duration (AUC = 0.911) showed strong discriminative ability for predicting docking site procedure necessity, suggesting potential utility as clinical decision-support parameters. Conclusions: The study identified transport duration and speed as potentially valuable predictive factors in this retrospective cohort for the need of a docking site procedure, though prospective validation is required. A transport duration exceeding 290.5 days significantly increased the likelihood of requiring a docking site procedure. These findings can help optimize treatment planning and improve long-term limb preservation. Full article

To address the issue of insufficient trajectory tracking accuracy and the stability of distributed drive mining dump trucks under complex working conditions, this paper proposes a model predictive control (MPC) strategy based on genetic-particle swarm optimization (GAPSO). This strategy overcomes the limitations of traditional MPC controllers—where the weight matrix is fixed—by constructing a hierarchical optimization architecture that enables adaptive weight adjustment. An MPC-based trajectory tracking controller is developed using a three-degree-of-freedom vehicle dynamics model. Furthermore, to address the challenge of tuning MPC weight parameters, a GAPSO-based fusion optimization algorithm is introduced. This algorithm integrates the global search capability of genetic algorithms with the local convergence advantages of particle swarm optimization, enabling joint optimization of the state and control weight matrices. Simulation results demonstrate that under complex scenarios such as double lane change maneuvers, varying vehicle speeds, and different road adhesion coefficients, the proposed GAPSO-MPC controller significantly outperforms conventional MPC and PSO-MPC approaches in terms of lateral position tracking root mean square error. The method effectively enhances the robustness of trajectory tracking for distributed drive mining vehicles under disturbance conditions, offering a viable technical solution for high-precision control in autonomous mining systems. Full article

Background: Durvalumab consolidation following radiochemotherapy is now the standard treatment for unresectable stage III non-small cell lung cancer (NSCLC). [¹⁸F]FDG PET/CT offers valuable insights not just for staging but also for tumor characterization via radiomics, which can potentially predict histology, immunophenotype, and prognosis. Methods: We conducted a retrospective analysis of [¹⁸F]FDG PET/CT scans from stage IIIA–IIIB NSCLC patients treated at the Clinical Centre, University of Pécs. All biopsy samples were classified histologically (squamous vs. adenocarcinoma) and tested for PD-L1. Lung tumors were segmented using MEDISO InterViewTM FUSION software (version 3.12.002.0000). with an SUVmax threshold of four. Imaging features were extracted and compared based on histology, PD-L1 status, and neutrophil-to-lymphocyte ratio (NLR)-based prognosis groups. Statistical analyses were performed with Jamovi (v2.6.44), using Shapiro–Wilk, t-test/ANOVA, Mann–Whitney/Kruskal–Wallis, or Chi-square tests as appropriate. Results: Fifty-six patients were included (38 PD-L1-positive, 18 -negative). Among PD-L1-positive cases, poor versus good NLR prognosis groups differed in maximum diameter (p = 0.046), short-zone emphasis (p = 0.026), and zone-length non-uniformity (p = 0.027). Focusing on PD-L1-positive squamous carcinoma, maximum diameter, metabolic tumor volume, busyness, and coarseness showed significant differences (all p < 0.05). SUVmax, mean SUV, SUVpeak, and complexity were higher in squamous than in adenocarcinoma subtypes. PD-L1-positive and -negative squamous tumors differed in zone percentage (p = 0.039) and long-zone high gray-level emphasis (p = 0.024), while no significant differences were observed among adenocarcinomas. Conclusions: [¹⁸F]FDG PET/CT radiomics showed potential for differentiating NSCLC histological subtypes and for identifying PD-L1-associated imaging patterns in squamous cell carcinoma. In addition, certain metabolic features were associated with NLR-based prognostic groups in PD-L1-positive patients. Full article