Search Results (660)

The formation, development, and spatial distribution of CUHIs are influenced by urban spatial heterogeneity, yet the scale and seasonal dependencies of the effects of urban morphology modulation on CUHIs have not been fully explored, needing further study. Based on multi-source data for the Yangtze-Huaihe River Valley (YHRV), this study employs the XGBoost model to systematically investigate the effects of two-dimensional (2D)/three-dimensional (3D) urban morphological indicators on CUHIs and their inherent scale–seasonal dependencies. Results show significant provincial heterogeneity in YHRV’s CUHIs: Shanghai exhibits the highest CUHI intensity (CUHII) across all seasons, with a peak of 1.55 °C in winter, followed by Zhejiang and Jiangsu. Seasonally, winter CUHII averages 0.6–0.8 °C (the highest), followed by autumn, while spring and summer have lower values. The effect of the modulation of urban morphology on CUHIs exhibits distinct spatiotemporal dependence: in winter and autumn, CUHII is mainly dominated by the percentage of landscape (PLAND) and largest patch index (LPI) at the 4 km buffer scale (correlation coefficients r = 0.475 and 0.406 for winter); in spring and summer, the 2 km buffer scale shows a more balanced regulatory role of multiple urban morphological indicators. Notably, 2D indicators of urban morphology are consistently more influential in regulating CUHIs than 3D indicators. The Hefei station case effectively validates the model’s sensitivity to changes in urban morphology. This study provides a quantitative basis for season–scale collaborative regulation of urban thermal environments in the YHRV. Future research will integrate climatic factors into XGBoost via screening, reconstruction, and interaction quantification to enhance its predictability for transient heat island processes. Full article

Background: Colon capsule endoscopy (CCE) has seen increased adoption since the COVID-19 pandemic, offering a non-invasive alternative for lower gastrointestinal investigations. However, inadequate bowel preparation remains a key limitation, often leading to higher conversion rates to colonoscopy. Manual assessment of bowel cleanliness is inherently subjective and marked by high interobserver variability. Recent advances in artificial intelligence (AI) have enabled automated cleansing scores that not only standardise assessment and reduce variability but also align with the emerging semi-automated AI reading workflow, which highlights only clinically significant frames. As full video review becomes less routine, reliable, and consistent, cleansing evaluation is essential, positioning bowel preparation AI as a critical enabler of diagnostic accuracy and scalable CCE deployment. Objective: This CESCAIL sub-study aimed to (1) evaluate interobserver agreement in CCE bowel cleansing assessment using two established scoring systems, and (2) determine the impact of AI-assisted scoring, specifically a TransUNet-based segmentation model with a custom Patch Loss function, on both interobserver and intraobserver agreement compared to manual assessment. Methods: As part of the CESCAIL study, twenty-five CCE videos were randomly selected from 673 participants. Nine readers with varying CCE experience scored bowel cleanliness using the Leighton–Rex and CC-CLEAR scales. After a minimum 8-week washout, the same readers reassessed the videos using AI-assisted CC-CLEAR scores. Interobserver variability was evaluated using bootstrapped intraclass correlation coefficients (ICC) and Fleiss’ Kappa; intraobserver variability was assessed with weighted Cohen’s Kappa, paired t-tests, and Two One-Sided Tests (TOSTs). Results: Leighton–Rex showed poor to fair agreement (Fleiss = 0.14; ICC = 0.55), while CC-CLEAR demonstrated fair to excellent agreement (Fleiss = 0.27; ICC = 0.90). AI-assisted CC-CLEAR achieved only moderate agreement overall (Fleiss = 0.27; ICC = 0.69), with weaker performance among less experienced readers (Fleiss = 0.15; ICC = 0.56). Intraobserver agreement was excellent (ICC > 0.75) for experienced readers but variable in others (ICC 0.03–0.80). AI-assisted scores were significantly lower than manual reads by 1.46 points (p < 0.001), potentially increasing conversion to colonoscopy. Conclusions: AI-assisted scoring did not improve interobserver agreement and may even reduce consistency amongst less experienced readers. The maintained agreement observed in experienced readers highlights its current value in experienced hands only. Further refinement, including spatial analysis integration, is needed for robust overall AI implementation in CCE. Full article

In the Ultra-High-Definition (UHD) domain, blind image quality assessment remains challenging due to the high dimensionality of UHD images, which exceeds the input capacity of deep learning networks. Motivated by the visual discrepancies observed between high- and low-quality images after down-sampling and Super-Resolution (SR) reconstruction, we propose a SUper-Resolved Pseudo References In Dual-branch Embedding (SURPRIDE) framework tailored for UHD image quality prediction. SURPRIDE employs one branch to capture intrinsic quality features from the original patch input and the other to encode comparative perceptual cues from the SR-reconstructed pseudo-reference. The fusion of the complementary representation, guided by a novel hybrid loss function, enhances the network’s ability to model both absolute and relational quality cues. Key components of the framework are optimized through extensive ablation studies. Experimental results demonstrate that the SURPRIDE framework achieves competitive performance on two UHD benchmarks (AIM 2024 Challenge, PLCC = 0.7755, SRCC = 0.8133, on the testing set; HRIQ, PLCC = 0.882, SRCC = 0.873). Meanwhile, its effectiveness is verified on high- and standard-definition image datasets across diverse resolutions. Future work may explore positional encoding, advanced representation learning, and adaptive multi-branch fusion to align model predictions with human perceptual judgment in real-world scenarios. Full article

Advancements in bioinks and three-dimensional (3D) printing and bioprinting have significantly advanced cardiovascular tissue engineering by enabling the fabrication of biomimetic cardiac and vascular constructs. Traditional 3D printing has contributed to the development of acellular scaffolds, vascular grafts, and patient-specific cardiovascular models that support surgical planning and biomedical applications. In contrast, 3D bioprinting has emerged as a transformative biofabrication technology that allows for the spatially controlled deposition of living cells and biomaterials to construct functional tissues in vitro. Bioinks—derived from natural biomaterials such as collagen and decellularized matrix, synthetic polymers such as polyethylene glycol (PEG) and polycaprolactone (PCL), or hybrid combinations—have been engineered to replicate extracellular environments while offering tunable mechanical properties. These formulations ensure biocompatibility, appropriate mechanical strength, and high printing fidelity, thereby maintaining cell viability, structural integrity, and precise architectural resolution in the printed constructs. Advanced bioprinting modalities, including extrusion-based bioprinting (such as the FRESH technique), droplet/inkjet bioprinting, digital light processing (DLP), two-photon polymerization (TPP), and melt electrowriting (MEW), enable the fabrication of complex cardiovascular structures such as vascular patches, ventricle-like heart pumps, and perfusable vascular networks, demonstrating the feasibility of constructing functional cardiac tissues in vitro. This review highlights the respective strengths of these technologies—for example, extrusion’s ability to print high-cell-density bioinks and MEW’s ultrafine fiber resolution—as well as their limitations, including shear-induced cell stress in extrusion and limited throughput in TPP. The integration of optimized bioink formulations with appropriate printing and bioprinting platforms has significantly enhanced the replication of native cardiac and vascular architectures, thereby advancing the functional maturation of engineered cardiovascular constructs. Full article

Despite the remarkable success of Deep Neural Networks (DNNs) in Remote Sensing Image (RSI) object detection, they remain vulnerable to adversarial attacks. Numerous adversarial attack methods have been proposed for RSI; however, adding a single large-scale adversarial patch to certain high-value targets, which are typically large in physical scale and irregular in shape, is both costly and inflexible. To address this issue, we propose a strategy of using multiple compact patches. This approach introduces two fundamental challenges: (1) how to optimize patch placement for a synergistic attack effect, and (2) how to retain strong adversarial potency within size-constrained mini-patches. To overcome these challenges, we introduce the Spatially Adaptive and Distillation-Enhanced Mini-Patch Attack (SDMPA) framework, which consists of two key modules: (1) an Adaptive Sensitivity-Aware Positioning (ASAP) module, which resolves the placement challenge by fusing the model’s attention maps from both an explainable and an adversarial perspective to identify optimal patch locations, and (2) a Distillation-based Mini-Patch Generation (DMPG) module, which tackles the potency challenge by leveraging knowledge distillation to transfer adversarial information from large teacher patches to small student patches. Extensive experiments on the RSOD and MAR20 datasets demonstrate that SDMPA significantly outperforms existing patch-based attack methods. For example, against YOLOv5n on the RSOD dataset, SDMPA achieves an Attack Success Rate (ASR) of 88.3% using only three small patches, surpassing other patch attack methods. Full article

Accurately estimating aboveground carbon storage (AGC) of urban vegetation remains a major challenge, due to the heterogeneity and vertical complexity of urban environments, where traditional forest-based remote sensing models often perform poorly. This study integrates multimodal remote sensing data and incorporates two three-dimensional structural features—mean tree height ($H_{mean}$) and canopy cover ratio (CCR)—in addition to conventional spectral and textural variables. To minimize redundancy, the Boruta algorithm was applied for feature selection, and four machine learning models (SVR, RF, XGBoost, and CatBoost) were evaluated. Results demonstrate that under multimodal data fusion, three-dimensional features emerge as the dominant predictors, with XGBoost using Boruta-selected variables achieving the highest accuracy (R² = 0.701, RMSE = 0.894 tC/400 m²). Spatial mapping of AGC revealed a “high-aggregation, low-dispersion” pattern, with the model performing best in large, continuous green spaces, while accuracy declined in fragmented or small-scale vegetation patches. Overall, this study highlights the potential of machine learning with multi-source variable inputs for fine-scale urban AGC estimation, emphasizes the importance of three-dimensional vegetation indicators, and provides practical insights for urban carbon assessment and green infrastructure planning. Full article

Dominant species form species-specific fine-scale vegetation matrices in grasslands that regulate community dynamics, diversity and ecosystem functioning. The structure of these dynamic microscale landscapes was analyzed and compared between primary and secondary plant communities. We explored fine-scale monitoring data along permanent transects over seven consecutive years. Spatial and temporal patterns of dominant grass species (Festuca valesiaca, Alopecurus pratensis and Poa angustifolia) were analyzed using information theory models. These matrix-forming species showed high spatiotemporal variability in all grasslands. However, consistent differences were found between primary and secondary grasslands in the spatial and temporal organization of the vegetation matrix. Alopecurus pratensis and Poa angustifolia had coarse-scale patchiness with stronger aggregation in secondary grasslands. The spatial patterns of Festuca valesiaca were nearly random in both types of grasslands. Strong associations were observed among the spatial patterns of each species across years, with a stronger dependence in secondary grasslands. In contrast, the rate of fine-scale dynamics was higher in primary grasslands. The complexity of microhabitats within the matrix was higher in primary grasslands, often involving two to three dominant species, while, in secondary grasslands, patches formed by a single dominant species were more frequent. In the spatial variability of small-scale subordinate species richness, significant, temporally consistent differences were found. Higher variability in secondary grasslands suggests stronger and more spatially variable microhabitat filtering. We recommend that grassland management and restoration practices be guided by preliminary information on the spatial organization of primary grasslands. Enhancing the complexity of the matrix formed by dominant species can further improve the condition of secondary grasslands. Full article

Voltage-gated Na⁺ channels (Nav) are the molecular determinants of action potential initiation and propagation. Among the nine voltage-gated Na⁺ channel isoforms (Nav1.1–Nav1.9), Nav1.2 and Nav1.6 are of particular interest because of their developmental expression profile throughout the central nervous system (CNS) and their association with channelopathies. Although the α-subunit coded by each of the nine isoforms can sufficiently confer transient Na⁺ currents (I_Na), in vivo these channels are modulated by auxiliary proteins like intracellular fibroblast growth factor (iFGFs) through protein–protein interaction (PPI), and probes developed from iFGF/Nav PPI complexes have been shown to precisely modulate Nav channels. Previous studies identified ZL0177, a peptidomimetic derived from a short peptide sequence at the FGF14/Nav1.6 PPI interface, as a functional modulator of Nav1.6-mediated I_Na⁺. However, the isoform specificity, binding sites, and putative physiological impact of ZL0177 on neuronal excitability remain unexplored. Here, we used automated planar patch-clamp electrophysiology to assess ZL0177’s functional activity in cells stably expressing Nav1.2 or Nav1.6. While ZL0177 was found to suppress I_Na in both Nav1.2- and Nav1.6-expressing cells, ZL0177 elicited functionally divergent effects on channel kinetics that were isoform-specific and supported by differential docking of the compound to AlphaFold structures of the two channel isoforms. Computational modeling predicts that ZL0177 modulates Nav1.2 and Nav1.6 in an isoform-specific manner, eliciting phenotypically divergent effects on action potential discharge. Taken together, these results highlight the potential of PPI derivatives for isoform-specific regulation of Nav channels and the development of therapeutics for channelopathies. Full article

Background/Objectives: Human epidermal growth factor 2 (HER2) scoring is critical for modern breast cancer therapies, especially with emerging indications of antibody–drug conjugates for HER2-low tumors. However, inter-observer agreement remains limited in borderline cases. Automatic artificial intelligence-based scoring has the potential to improve diagnostic consistency and scalability. This study aimed to develop two transformer-based models for HER2 scoring of breast cancer whole-slide images (WSIs) and compare their performance. Methods: We adapted a large-scale foundation model (Virchow) and a lightweight model (TinyViT). Both were trained using patch-level annotations and integrated into a WSI scoring pipeline. Performance was evaluated on a clinical test set (n = 66), including clinical decision tasks and inference efficiency. Results: Both models achieved substantial agreement with pathologist reports (linear weighted kappa: 0.860 for Virchow, 0.825 for TinyViT). Virchow showed slightly higher WSI-level accuracy than TinyViT, whereas TinyViT reduced inference times by 60%. In three binary clinical tasks, both models demonstrated a diagnostic performance comparable to pathologists, particularly in identifying HER2-low tumors for antibody–drug conjugate (ADC) therapy. A continuous scoring framework demonstrated a strong correlation between the two models (Pearson’s r = 0.995) and aligned with human assessments. Conclusions: Both transformer-based artificial intelligence models achieved human-level accuracy for automated HER2 scoring with interpretable outputs. While the foundation model offers marginally higher accuracy, the lightweight model provides practical advantages for clinical deployment. In addition, continuous scoring may provide a more granular HER2 quantification, especially in borderline cases. This could support a new interpretive paradigm for HER2 assessment aligned with the evolving indications of ADC. Full article

The Amur tiger (Panthera tigris altaica) is a flagship and umbrella species of forest ecosystems in northeastern Asia. Climate change is profoundly and irreversibly affecting wildlife habitat suitability, especially for large mammals. To effectively protect the Amur tiger, it is necessary to understand the impact of climate change on the quality and the connectivity of its habitat. We used the species distribution models combined with the latest Shared Socioeconomic Pathway (SSP) climate scenarios to predict current and future changes in habitats and corridors. We found the following: (1) The total area of the Amur tiger’s suitable habitat currently amounts to approximately 4941.94 km², accounting for 27.64% of the study area represented by two adjacent national parks. Among these habitats, the highly suitable areas are mainly located on the both sides of the Sino-Russian border. The landscape connectivity remains relatively stable, and the degree of fragmentation in highly suitable habitats is low. (2) Although the suitable habitat of the Amur tiger shows an expansion trend under most climate scenarios (excluding SSP3-7.0), the area of suitable habitat within the entire study region does not increase significantly. Therefore, we should implement conservation measures to facilitate the continued expansion of suitable habitat for the Amur tiger. The quantity and length of landscape connectivity corridors are expected to vary in response to changes in core habitat patches, while the centroid of highly suitable habitats is also expected to shift to different extents. In such circumstances, new ecological corridors need to be constructed, while existing natural ecological corridors should be preserved. Full article

The axle-box bearing is a critical load-bearing component in high-speed trains and is prone to failure under long-term heavy-duty operation, affecting both operational efficiency and safety. Current deep-learning-based fault diagnosis methods face two key challenges: difficulty in capturing temporal features across multiple scales simultaneously, and limited capability in modeling local sequential patterns. To address these issues, we propose P2IFormer, a fault diagnosis model based on multi-granularity patch-to-image embedding. The raw vibration sequence is divided into equal-length patch sequences under multiple granularities, each defined by a fixed window size. Each patch is then transformed into a Gramian Angular Field (GAF) image to extract spatial features and generate granularity-specific embedding. A multi-granularity self-attention mechanism is used to model both intra- and inter-granularity dependencies. The resulting multi-granularity features are fused and fed into a softmax classifier for final fault prediction. Experiments conducted under four constant-speed conditions and one variable-speed condition demonstrate that P2IFormer achieves over 99.5% accuracy across all scenarios, significantly outperforming existing CNN- and Transformer-based methods. Full article

Mangrove forests are among the world’s most vital coastal ecosystems. Mapping mangrove cover from local to global scales using spectral data and machine learning models is a well-established method. While non-spectral contextual datasets (spatial features) have also been incorporated into such models, the contribution of these additional features to improving mangrove mapping remains underexplored. Using the Mesoamerican Reef Region as a case study, we evaluate the effectiveness of incorporating spatial features in binary mangrove classification to enhance mapping accuracy. We compared an aspatial model that includes only spectral data with three spatial models: two included features such as geographic coordinates, elevation, and proximity to coastlines and streams, while the third integrated a geostatistical approach using Inverse Distance Weighted (IDW) interpolation. Spectral inputs included bands and indices derived from Sentinel-1 and Sentinel-2, and all models were implemented using the Random Forest algorithm in Google Earth Engine. Results show that spatial features reduced omission errors without increasing commission errors, enhancing the model’s ability to capture spatial variability. Models using geographic coordinates and elevation performed comparably to those with additional environmental variables, with storm frequency and distance to streams emerging as important predictors in the Mesoamerican Reef region. In contrast, the IDW-based model underperformed, likely due to overfitting and limited representation of local spectral variation. Spatial analyses show that models incorporating spatial features produced more continuous mangrove patches and removed some false positives in non-mangrove areas. These findings highlight the value of spatial features in improving classification accuracy, especially in regions with ecologically diverse mangroves across varied environments. By integrating spatial context, these models support more accurate, locally relevant mangrove maps that are essential for effective conservation and management. Full article

Robust perception of road surface conditions is a critical challenge for the safe deployment of autonomous vehicles and the efficient management of transportation infrastructure. This paper introduces a synthetic data-driven deep learning framework designed to address this challenge. We present a large-scale, procedurally generated 3D synthetic dataset created in Blender, featuring a diverse range of road defects—including cracks, potholes, and puddles—alongside crucial road features like manhole covers and patches. Crucially, our dataset provides dense, pixel-perfect annotations for segmentation masks, depth maps, and camera parameters (intrinsic and extrinsic). Our proposed model leverages these rich annotations in a multi-task learning framework that jointly performs road defect segmentation and depth estimation, enabling a comprehensive geometric and semantic understanding of the road environment. A core contribution is a two-stage domain adaptation strategy to bridge the synthetic-to-real gap. First, we employ a modified CycleGAN with a segmentation-aware loss to translate synthetic images into a realistic domain while preserving defect fidelity. Second, during model training, we utilize a dual-discriminator adversarial approach, applying alignment at both the feature and output levels to minimize domain shift. Benchmarking experiments validate our approach, demonstrating high accuracy and computational efficiency. Our model excels in detecting subtle or occluded defects, attributed to an occlusion-aware loss formulation. The proposed system shows significant promise for real-time deployment in autonomous navigation, automated infrastructure assessment and Advanced Driver-Assistance Systems (ADAS). Full article

Small water bodies are widely spread and play crucial roles in supporting regional agricultural and aquaculture activities. PlanetScope imagery has a high resolution (3 m) with daily global coverage and has obviously enhanced small water body mapping. Recent studies have demonstrated the effectiveness of deep learning for mapping small water bodies using PlanetScope; however, a persistent challenge remains in the scarcity of high-quality, manually annotated water masks used for model training, which limits the generalization capability of data-driven deep learning models. In this study, we propose a transfer learning framework that leverages Sentinel-2 data to improve PlanetScope-based small water body mapping, capitalizing on the spectral interoperability between PlanetScope and Sentinel-2 bands and the abundance of open-source Sentinel-2 water masks. Eight state-of-the-art segmentation models have been explored. Additionally, this paper presents the first assessment of the VMamba model for small water body mapping, building on its demonstrated success in segmentation tasks. The models were pre-trained using Sentinel-2-derived water masks and subsequently fine-tuned with a limited set (1292 image patches, 256 × 256 pixels in each patch) of manually annotated PlanetScope labels. Experiments were conducted using 5648 image patches and two areas of 9636 km² and 2745 km², respectively. Among the evaluated methods, VMamba achieved higher accuracy compared with both CNN- and Transformer-based models. This study highlights the efficacy of combining global Sentinel-2 datasets for pre-training with localized fine-tuning, which not only enhances mapping accuracy but also reduces reliance on labor-intensive manual annotation in regional small water body mapping. Full article

Plant disease classification is critical for effective crop management. Recent advances in deep learning, especially Vision Transformers (ViTs), have shown promise due to their strong global feature modeling capabilities. However, ViTs often overlook local features and suffer from feature extraction degradation during patch merging as channels increase. To address these issues, we propose PLTransformer, a hybrid model designed to symmetrically capture both global and local features. We design a symmetric multi-scale convolutional module that combines two different-scale receptive fields to simultaneously extract global and local features so that the model can better perceive multi-scale disease morphologies. Additionally, we propose an overlap-attentive channel downsampler that utilizes inter-channel attention mechanisms during spatial downsampling, effectively preserving local structural information and mitigating semantic loss caused by feature compression. On the PlantVillage dataset, PLTransformer achieves 99.95% accuracy, outperforming DeiT (96.33%), Twins (98.92%), and DilateFormer (98.84%). These results demonstrate its superiority in handling multi-scale disease features. Full article