Search Results (5,037)

Spaceborne microwave imagers are vital for monitoring global precipitation due to their wide swath and high sensitivity. This study proposes a deep learning approach that integrates a U-Net with a multi-task learning (MTL) framework. The model was separately trained over land and ocean using GPM Microwave Imager (GMI) brightness temperatures, with collocated precipitation rates and types from the Dual-frequency Precipitation Radar (DPR) as labels. This combines the accuracy of radars with the coverage of imagers to produce high-precision, wide-swath precipitation estimates. In the MTL setup, near-surface precipitation rate retrieval is the main task, and precipitation type classification is the auxiliary task. A composite loss (weighted MSE and quantile regression) is used for the main task, and weighted cross-entropy for the auxiliary task. Residual blocks and an attention mechanism are incorporated to improve physical representation and generalization, thereby significantly enhancing the model’s capability to retrieve heavy precipitation. The model was trained on 2015–2024 GPM data and evaluated on an independent six-month 2025 GMI dataset. Compared to a standard U-Net, the MTL model achieved significant gains: Pearson Correlation Coefficient (PCC) increased by 9.7% (ocean) and 13.7% (land), and Critical Success Index (CSI) by 10.7% (ocean) and 10.8% (land). The method was also applied to the FY-3G Microwave Radiation Imager (MWRI-RM). In case studies, it outperformed the official product, achieving average increases of 20.1% in PCC and 15.7% in CSI, respectively. Validation against FY-3G Precipitation Measurement Radar (June–August 2024) yielded over ocean PCC = 0.757, RMSE = 1.588 mm h⁻¹, MAE = 0.355 mm h⁻¹; over land PCC = 0.691, RMSE = 2.007 mm h⁻¹, MAE = 0.692 mm h⁻¹. The study demonstrates that the MTL-enhanced U-Net significantly improves the accuracy of spaceborne microwave imager rainfall retrieval and shows robust practical applicability. Full article

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) remains challenging due to heterogeneous tumor morphology, intensity variability, and multi-scale structural complexity. This study proposes a DeepLabV3+-based segmentation framework integrating a VGG19-UNet encoder, Atrous Spatial Pyramid Pooling (ASPP), and low-level feature refinement to simultaneously capture hierarchical semantics and boundary-sensitive spatial details. The architecture enhances receptive field coverage without additional downsampling while preserving fine-grained contour information during reconstruction. Extensive evaluation was conducted on the Figshare Brain Tumor Segmentation (FBTS) dataset and the BraTS 2021 and BraTS 2018 benchmarks, focusing on Whole Tumor segmentation across multiple MRI modalities and tumor grades. Under five-fold cross-validation, the proposed model achieved a mean Dice Similarity Coefficient of 0.9717 and Jaccard Index of 0.9456 on FBTS, with stable and competitive performance across FLAIR, T1, T2, and T1CE modalities in both HGG and LGG cases. Boundary-level analysis further confirmed controlled Hausdorff Distance and low Average Symmetric Surface Distance. Statistical validation and ablation analysis demonstrate consistent improvements over baseline U-Net configurations. The proposed framework provides a robust and computationally efficient solution for automated brain tumor segmentation across heterogeneous datasets. Full article

Rapid urbanization and agricultural expansion in arid regions have profoundly altered carbon cycles and landscape stability. Focusing on the Hexi Corridor, China, this study integrates multi-source geospatial data (1990–2020) to analyze the spatiotemporal evolution and driving factors of land-use carbon emissions (LUCE) and landscape ecological risks (LER). By integrating carbon accounting, LER assessment, bivariate spatial autocorrelation, and the Optimal Parameter Geographic Detector (OPGD), we quantify the intricate relationship between carbon dynamics and landscape integrity. Results indicate a transformative pattern of anthropogenic expansion and natural contraction, with a 2315.49 km² net loss of unused land. Net carbon emissions surged 4.6-fold, while forest and grassland sinks exhibited a significant “lock-in effect” due to fragile ecological foundations. Simultaneously, LER followed an “inverted U-shaped” trajectory; the refined 5 × 5 km grid scale revealed a significant drop in high-risk areas from 44.65% to 10.96% following ecological restoration. Spatial analysis reveals a significant “spatial mismatch” between LUCE and LER, with oases manifesting “high carbon–low risk” clustering. Driver detection confirms a driving asymmetry. LUCE is dominated by anthropogenic factors (nighttime light, q > 0.90), whereas LER is profoundly constrained by natural backgrounds. Future governance must shift toward a collaborative system centered on source-based emission control and precise regional management to synergize low-carbon transition with landscape security. Full article

Accurate delineation of tumor margins is critical for complete resection and minimizing recurrence, yet existing imaging modalities such as MRI, CT, and fluorescence imaging suffer from limitations including high cost, limited accessibility, and intraoperative constraints. In this study, we propose a low-cost, non-invasive approach for subsurface imaging based on near-infrared (NIR) illumination combined with deep learning. A controlled experimental setup was developed in which structured patterns displayed on an electronic paper screen were concealed beneath a tissue-mimicking chicken phantom and imaged using a NIR-sensitive camera under halogen illumination. A convolutional autoencoder based on a U-Net architecture was trained on approximately 10,000 paired samples to reconstruct hidden structures from highly scattered surface images. The proposed method achieved strong reconstruction performance, with the best model reaching a peak signal-to-noise ratio (PSNR) of 20.14 dB, structural similarity index (SSIM) of 0.92, and feature similarity index (FSIM) of 0.94, significantly outperforming conventional Wiener filtering. Qualitative results demonstrated accurate recovery of subsurface shapes with minor smoothing artifacts. While generalization to out-of-distribution samples remains limited, the findings highlight the potential of combining NIR imaging and deep learning for safe, rapid, and cost-effective subsurface visualization. This work establishes a foundation for future development toward clinically relevant tumor margin detection. Full article

Accurate detection of prostate cancer suspicious areas in biparametric MRI (bpMRI) remains challenging because of severe lesion-to-background imbalance, limited lesion contrast, and inter-reader variability in lesion delineation. Unlike prior approaches that collapse inter-reader disagreement into a single consensus label, this study makes three contributions: (1) an adapted nnU-Net framework with prostate-centered preprocessing to reduce voxel-level class imbalance; (2) a class-imbalance-aware composite loss combining Dice, binary cross-entropy, and tailored focal loss to improve sensitivity to small and low-contrast lesions; and (3) a multi-expert learning strategy that preserves reader-specific annotations as separate supervision targets and aggregates predictions at the ensemble level. The method was developed on a single-center dataset of 378 bpMRI studies independently annotated by three board-certified radiologists. Of these, 323 studies were used for model development with patient-level 5-fold cross-validation, and 55 studies were reserved as a fixed independent test set. Compared with our previously published U-Net baseline, the proposed consensus-based nnU-Net improved Average Precision (AP) from 0.69 to 0.75, AUROC from 0.92 to 0.96, and the PI-CAI score from 0.81 to 0.85 on the independent test set. In addition, the multi-expert approach further improved AP to 0.81 versus 0.76 (+6.6%, p < 0.01), AUROC to 0.99 versus 0.95 (+4.2%, p < 0.01), and the PI-CAI score to 0.90 versus 0.86 (+4.7%). These findings demonstrate that explicitly preserving expert disagreement as a training signal, combined with anatomically targeted preprocessing and tailored loss design, substantially improves prostate lesion detection in bpMRI, providing a strong basis for future multi center external validation. Full article

Radial distribution feeders are especially sensitive to reactive-power deficits, which increase technical losses, deteriorate voltage profiles, reduce energy efficiency, and indirectly raise the emissions associated with the energy required to supply those losses. In this context, this paper proposes a sustainability-oriented planning methodology for the location and sizing of capacitor banks in radial distribution feeders, aimed at jointly improving technical performance, economic viability, and sustainability-related energy benefits. The problem is formulated as a discrete multi-objective model and solved through a constructive Greedy heuristic combined with backward/forward sweep load-flow evaluation, considering commercially available capacitor sizes. The methodology is validated on the IEEE 34-bus feeder, a demanding benchmark that remains less frequently used than the IEEE 33- and 69-bus systems in recent capacitor-planning studies. Seven scenarios are analyzed, from the uncompensated base case to configurations with up to six capacitor banks. The results show that all compensated scenarios improve feeder performance, reducing active losses from 25.3327 kW to a minimum of 20.1468 kW, equivalent to a maximum reduction of 20.47%, and increasing the minimum nodal voltage from 0.95528 p.u. to 0.97038 p.u. From a purely financial perspective, the one-bank scenario yields the highest net present value (USD 16,358.86), whereas the two-bank scenario emerges as the most balanced solution within the evaluated set, with annual savings of USD 5432.29 and a net present value of USD 11,497.58. Overall, the results confirm that capacitor-bank planning should be addressed as a trade-off among electrical efficiency, voltage support, profitability, and sustainability-oriented benefits. The proposed framework provides a simple, reproducible, and interpretable planning tool for radial distribution feeders. Full article

Background/Objectives: This study proposes CMT-BUSNet, a hybrid architecture integrating CNN, Mamba, and Transformer branches for breast ultrasound tumor segmentation with built-in explainability. Methods: CMT-BUSNet employs a CNN-anchored hierarchical parallel encoder where Mamba and Transformer branches process CNN-derived features in parallel, fused through an Adaptive Feature Fusion Module (AFFM) with Dense Nested Decoder and Boundary-Aware Composite Loss. Five-fold cross-validation on BUS-BRA (N = 1875) compared nine architectures under identical protocols, plus nnU-Net v2 trained with its default self-configuring protocol as a benchmark. External evaluation used the BUSI dataset (N = 647). Results: CMT-BUSNet achieved DSC = 0.9037 ± 0.0047 on BUS-BRA with higher boundary delineation metrics than nnU-Net v2, which was trained under a different self-configuring protocol (B-IoU: 0.611 vs. 0.557; HD95: 10.07 vs. 13.54 pixels), despite nnU-Net’s marginally higher DSC (0.9108). On BUSI, CMT-BUSNet (DSC = 0.6709) yielded higher scores than nnU-Net (0.5579) across all metrics under zero-shot transfer, though the two methods were trained under different protocols. Training-based ablation confirmed each component’s contribution, and quantitative XAI validation demonstrated attribution faithfulness (nEAR = 2.82×) and uncertainty–error correlation (r = 0.39). Conclusions: CMT-BUSNet achieves competitive accuracy with higher boundary metrics, preliminary cross-dataset transferability, and built-in interpretability relative to nnU-Net (noting different training protocols). Internal validation folds are image-disjoint but not guaranteed to be patient-disjoint, which should be considered when interpreting the reported metrics. Multicenter validation is required before clinical deployment. Full article

The rapid expansion of seaweed aquaculture has profound impacts on coastal ecosystems, yet the lack of long-term, high-precision spatiotemporal monitoring methods has constrained systematic understanding of aquaculture dynamics and their environmental effects. This study integrated Landsat (1984–2025) and Sentinel-2 (2015–2025) imagery with an attention-enhanced U-Net deep learning model to achieve 41 years of continuous monitoring of seaweed aquaculture in the Dongtou Archipelago, Zhejiang Province, China. The model achieved high extraction accuracy for both Landsat and Sentinel-2 aquaculture areas (F1 scores of 0.972 and 0.979, respectively). On this basis, the cultivation zones were further classified into Porphyra sp. and Sargassum fusiforme cultivation areas by incorporating local aquaculture planning and field survey data. Results showed that the aquaculture area underwent three developmental stages: slow initiation (1984–2000, <3 km²), rapid expansion (2001–2015, 3–8 km²), and high-level fluctuation (post-2015, typically 8–20 km²), reaching a peak of ~30 km² during 2018–2019. Long-term retrieval of water quality parameters revealed that the decline in total suspended matter (from ~80 to 60 mg/L) and chlorophyll (from ~3 to 2 μg/L) within aquaculture zones was significantly greater than that in non-aquaculture areas, providing direct observational evidence for local water quality improvement by appropriately scaled aquaculture. Meanwhile, sea surface temperature showed a sustained increasing trend, with extremely high-temperature days (≥25 °C) exhibiting strong interannual variability, posing potential thermal stress risks to cold-preferring seaweed species. The NDVI (Normalized Difference Vegetation Index) and FAI (Floating Algae Index) indices effectively captured aquaculture phenology (seeding, growth, maturation, harvest), with their interannual peaks exhibiting an inverted U-shaped correlation with corresponding yields (R = 0.82 and 0.79, respectively, based on quadratic regression fitting), preliminarily demonstrating the potential of remote sensing in indicating density-dependent effects. This study systematically demonstrates the comprehensive capability of multi-source satellite remote sensing in long-term dynamic monitoring, environmental effect assessment, and yield relationship analysis of seaweed aquaculture, providing key technical support and scientific basis for aquaculture carrying capacity management and ecological risk prevention in island waters. Full article

Lung nodule detection remains a critical challenge in clinical diagnostics due to the small size, weak contrast, and high background interference of nodules in CT scans. To address these issues, a novel deep neural network architecture, termed Daisy-Net, is proposed. This model incorporates dual attention mechanisms and inter-scale feature perception, consisting of two primary components: the Parallelized Patch and Spatial Context Aware (PPSCA) module and the Omni-domain Multistage Fusion (OMF) module. The PPSCA module enhances the extraction of fine-grained textures and boundary information through multi-branch patch perception and spatial attention. The OMF module employs omni-domain feature fusion and progressive stage-wise supervision to improve robustness and discrimination under complex conditions. The lung nodule detection task is formulated as a two-dimensional segmentation problem and evaluated on the LUNA16 dataset. In the post-binarization comparative evaluation, Daisy-Net achieves the best overall performance among all compared methods, with an Intersection over Union (IoU) of 81.41, a Dice coefficient of 89.75, a precision of 95.34, a sensitivity of 84.78, and a specificity of 99.9974. These findings indicate the model’s strong capability in detecting small pulmonary nodules accurately and reliably. Full article

Early detection of dental caries in children is critical to prevent irreversible tooth damage and guarantee optimal oral health outcomes. However, interpreting pediatric panoramic radiographs throughout the mixed dentition stage remains a very challenging task due to overlap in anatomical structures and developmental variability. This complexity underscores the need for well curated, representative datasets that enable the development of reliable computer-aided diagnostic models. Herein, this study introduces the Mixed Dentition Orthopantomogram Dataset, a newly developed, publicly available dataset of children that was carefully labeled by dental specialists to identify proximal and occlusal caries regions in the range of 3–12 years. To evaluate the dataset’s applicability for artificial intelligence research, we benchmarked it using both classification and segmentation models. A patch-based classifier achieved an average AUC of 0.89 and Recall 0.85 in distinguishing healthy and carious regions. For segmentation, we evaluated U-Net and Attention U-Net with multiple loss functions, and the Attention U-Net trained with Focal loss achieved the best Dice score of 0.94. Collectively, these findings support the dataset’s utility for pediatric caries analysis and demonstrate the viability of deep learning approaches for mixed dentition panoramic imaging. Full article

Synthetic Aperture Radar (SAR) imagery is inherently degraded by multiplicative speckle noise, rendering traditional superpixel methods—which rely on hard assignment and uniform initialization—suboptimal for boundary preservation. This study proposes a complexity-aware superpixel generation framework featuring differentiable soft-assignment optimization. The approach employs an F-LGRP (Fusion of Local Gradient Pattern Representation) feature descriptor that fuses regional gradient statistics via Gaussian filtering to suppress speckle, coupled with a complexity-driven recursive quadtree initialization strategy yielding non-uniform seed density. A U-Net architecture predicts soft pixel–superpixel association maps within a 9-neighborhood constraint, supervised by a multi-objective loss integrating edge information reconstruction and boundary feature reconstruction. Comprehensive evaluations on simulated and real SAR images (WHU-OPT-SAR and Munich) demonstrate that the proposed method achieves state-of-the-art performance across Boundary Recall, Undersegmentation Error, Compactness, and Achievable Segmentation Accuracy compared to SLIC, SNIC, Mean-Shift, PILS, and SSN. Validation on downstream segmentation tasks further confirms superior accuracy and computational efficiency, establishing the framework as an effective solution for end-to-end SAR image analysis. Full article

Timely and accurate monitoring of surface water dynamics via remote sensing is critical, given water resources’ importance. However, accurate water body delineation based on high-resolution remotely sensed imagery is still challenging due to the complexity of water bodies’ boundaries and the diversity of their shapes and sizes, which can lead to boundary ambiguity and varying degrees of confusion with near-water vegetation in water body maps. To address this challenge, we introduce an uncertainty-aware hybrid CNN–Transformer model for delineating water bodies using remotely sensed imagery. In our designed network, a multi-scale transformer (MST) module is first designed to effectively model and refine the multi-scale global semantic dependencies of water bodies. Subsequently, an uncertainty-guided multi-scale information fusion (MSIF) module is constructed to extract water body mapping information from these multi-scale features output from the MST module and fuse them adaptively. Across different scales, the extracted features differ in their ability to distinguish water bodies from non-water bodies and in their levels of uncertainty. Consequently, during the adaptive fusion of multi-scale water body information in the MSIF module, the mapping uncertainty is quantified and suppressed to minimize its impact, thus yielding enhanced precision in water body delineation. Ultimately, a comprehensive loss function is designed for model optimization to generate the final water body map. Furthermore, to promote water body segmentation models’ development, this study also presents the HBD_Water water body sample dataset, which contains 44 multispectral, 5000 × 5000-pixel images at 2 m spatial resolution, and will be released on the LuojiaSET platform soon. Finally, to verify the proposed model and its constituent MST and MSIF modules, extensive water mapping experiments were performed on three datasets. The experimental results substantiate their effectiveness. Furthermore, comparative experiment results demonstrate that the proposed model performs better at water body extraction than advanced networks including TransUNet, DeeplabV3+, and ADCNN. Full article

Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes, obscuring critical anatomical structures and compromising diagnostic precision. To address this, an unsupervised deep learning framework has been proposed for Metal Artifact Reduction (MAR) utilizing a Cycle-Consistent Adversarial Network (CycleGAN) optimized for high-fidelity restoration. Unlike supervised methods that rely on unattainable voxel-aligned paired datasets, the proposed approach leverages an unpaired dataset of approximately 4000 images, curated from the public ToothFairy dataset. The architecture integrates U-Net-based generators and PatchGAN discriminators, specifically tuned to mitigate generative hallucinations and preserve morphological integrity. Quantitative benchmarking on a held-out test set demonstrates a 34.6% improvement in the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score, a substantial reduction in Fréchet Inception Distance (FID) from 207.03 to 157.04, and a superior Structural Similarity Index Measure (SSIM) of 0.9105. The framework achieves real-time efficiency with a 3.03 ms inference time per slice, effectively suppressing artifacts while preserving anatomical detail. Expert validation confirms high fidelity; however, to ensure reliability in extreme cases, the architecture is recommended as a clinical decision-support tool under human-in-the-loop oversight. By enhancing diagnostic clarity via a scalable software pipeline, this study provides a robust solution for high-fidelity dental implant imaging. Full article

Generative AI has advanced rapidly in architectural design; however, existing building footprint generation models tend to emphasize stylistic exploration while insufficiently integrating site context as a fundamental physical constraint that facilitates alignment with the surrounding urban fabric. To address this limitation, this study proposes a context-responsive methodology for generating building footprints using a multi-layered four-channel representation of site conditions—including roads, sidewalks, adjacent buildings, and site boundaries—within a Latent Diffusion Model framework. The proposed approach encodes these physical conditions into a structured tensor and concatenates them directly to the U-Net input, enabling site context to function as an explicit spatial control variable during generation. An ablation study evaluated the effectiveness of the proposed contextual configuration. Compared with a single-channel model, the four-channel model achieved an 18.08% reduction in average pixel-wise information entropy, indicating a measurable decrease in generative uncertainty. Qualitative analyses further demonstrated that the enriched contextual input promotes geometrically coherent footprint configurations, such as context-responsive setbacks and spatial alignment with surrounding built forms. These findings suggest that structured multi-channel site information enhances contextual grounding in generative design processes and may contribute to more environmentally integrated and spatially coherent architectural outcomes. Full article

Conventional spatial frequency domain imaging (SFDI) based optical property inversion is inefficient, while deep learning methods suffer from heavy reliance on large-scale real datasets. To address this contradiction, a simulation-driven approach for subsurface fruit bruise discrimination was proposed. An SFDI simulation environment was built with Blender to generate 800 paired datasets of diffuse reflectance images and optical transport coefficients, overcoming the high cost and long cycle of real dataset acquisition. We designed the CBAM-GAN-U-Net model and adopted surface profile correction in the prediction method to eliminate curved surface-induced non-planar distortion, with the whole method validated on liquid phantoms, green apples and crown pears. This prediction method achieved high accuracy in predicting the reduced scattering coefficient μ_s′, with NMAE of 0.021 ± 0.007 (phantoms), 0.039 ± 0.012 (severely bruised green apples) and 0.044 ± 0.015 (severely bruised crown pears), outperforming U-Net and GANPOP. Based on the predicted μ_s′, a discrimination strategy combining coefficient of variation, mean ratio and receiver operating characteristic (ROC) curve analysis was adopted, attaining 100% accuracy for non-bruised/bruised fruit discrimination, with misclassification rates of 6% (green apples) and 8% (crown pears) for mild/severe bruise differentiation. This method enables accurate subsurface fruit bruise detection, providing a reliable technical solution for the fruit and vegetable industry and helping reduce postharvest supply chain losses. Full article