Search Results (2,161)

Background: Treatment monitoring in pulmonary tuberculosis increasingly requires assessment of residual inflammatory burden and structural lung damage beyond microbiologic response alone. High-resolution computed tomography (HRCT) can provide this information, but interpretation of serial examinations is time-consuming and partly subjective. This study did not aim to evaluate AI for the diagnosis of pulmonary tuberculosis. Instead, it explored whether artificial intelligence (AI)-assisted quantitative HRCT analysis could support longitudinal assessment of treatment-related imaging changes in patients with microbiologically confirmed pulmonary tuberculosis. Methods: We conducted a retrospective, single-center, exploratory longitudinal study of patients receiving treatment for pulmonary tuberculosis. HRCT examinations acquired at diagnosis and during follow-up were anonymized, reviewed by an expert thoracic radiologist, and processed using AVIEW Lung Texture (Coreline Soft v2.0). The software quantified total lung volume and six predefined parenchymal categories: normal lung, ground-glass opacity, consolidation, reticulation, honeycombing, and emphysema. Results: Ninety-six patients contributed 256 HRCT examinations. The most frequent software-detected abnormalities were ground-glass opacity, consolidation, and emphysema-labeled low-attenuation areas. Ground-glass opacity and consolidation showed the clearest decline across serial examinations, consistent with regression of active inflammatory disease during treatment. Reticulation showed a heterogeneous course, likely reflecting both inflammatory resolution and residual structural remodeling. Honeycombing was infrequent and quantitatively limited. Lung volume changed variably and did not consistently parallel visual improvement. A key methodological limitation was the absence of a dedicated cavity class. As a result, emphysema-labeled low-attenuation areas should not be interpreted as conventional emphysema alone, because tuberculous cavities and post-destructive abnormalities were frequently included in this category. Conclusions: AI-assisted HRCT quantification may support longitudinal assessment of pulmonary tuberculosis by providing structured and reproducible measures of interval change. However, tuberculosis-specific interpretation remains dependent on expert radiologic oversight, particularly in cavitary disease. Full article

For microbiological diagnostics, accurately counting and segmenting microbial colonies is extremely important. However, manual methods are labor-intensive and yield inconsistent results. We develop a hybrid model using swarm intelligence, combining a convolutional transformer with nested skip connections and global context with channel and spatial attention. Parameter tuning is supported by a variety of swarm optimization algorithms (e.g., Particle Swarm Optimization, Quantum-behaved Particle Swarm Optimization, and Differential Evolution Particle Swarm Optimization). Morphological refinement, including a further watershed transform, an attention graph, and post-processing, enhances colony boundaries by separating them. Grad-CAM++, Integrated Gradients, and temperature scaling provide a transparent and trustworthy model through explainability and post hoc calibration. The proposed model was extensively tested on the Microbial Colony Recognition and Circular Bacterial Colony Datasets, achieving a Dice score of 94.2%, an Intersection over the Union of 88.6%, and a mean absolute counting error of 2.7 colonies. These results significantly outperform several baseline models, including U-Net (88.1%), U-Net++ (89.7%), Attention U-Net (90.6%), and Swin-Unet (91.4%). Statistically significant improvements were confirmed (p < 0.01). A cross-dataset analysis demonstrates the framework’s robustness and cross-domain applicability, and positions it as a trustworthy, explainable automated model for assessing microbial colonies in laboratory and clinical settings. Full article

Potato sorting in post-harvest processing relies heavily on manual visual inspection, which is physically demanding, subjective, and insufficiently scalable for modern packing lines. This study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection. A controlled imaging platform was constructed using commodity hardware, and a dataset of 19,805 manually annotated instances across 1361 images was collected from two geographically distinct farm locations in Slovenia. A systematic benchmark of 25 model configurations spanning five YOLO architecture families—YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLO26—was conducted across three practical quality classes (Edible, Feed, Rotten) using a strict cross-location evaluation protocol in which models were trained on one location and tested on a completely unseen second location. All models achieved strong in-distribution performance (F1 ≥ 0.906), but showed considerable variation under cross-location conditions, with external F1 ranging from 0.792 to 0.918. The yolo26_l configuration achieved the best cross-location performance (F1 = 0.918, mAP@0.5:0.95 = 0.816, ΔF1 = 0.029), demonstrating that transferable representations are achievable under a standard supervised training protocol. Per-class analysis identified feed detection as the primary generalization bottleneck. The results confirm that affordable RGB-based sorting systems are technically feasible and highlight cross-location evaluation as an essential protocol for assessing real-world deployment readiness. Full article

Remote-sensing land surface deformation (LSD) is a powerful and effective approach for investigating regional alpine permafrost variations. However, alpine permafrost is often distributed in areas characterized by earthquakes, and the LSD of alpine permafrost is potentially contaminated or diminished by earthquake-related LSD. Therefore, this study aimed to derive the effective LSD in the alpine permafrost of the Source Area Yellow River (SAYR) by removing LSD originating from the M_w 7.4 Maduo earthquake in 2021-05-22 and analyzing the spatiotemporal variations in LSD during 2017–2024. Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) was used to obtain the initial LSD time series from Sentinel-1 images acquired during 2017–2024. The LSD of the M_w 7.4 Maduo earthquake, its aftershocks and the post-seismic relaxation in SAYR was simulated separately by considering its temporal process and removed from the LSD time series in SAYR. The final LSD was validated against in situ Global Navigation Satellite System (GNSS) measurements, and the spatiotemporal variations in LSD in SAYAR were subsequently analyzed. The study found the following: (1) the removal of the earthquake-related LSD was successful both spatially and temporally and the final LSD has mean absolute error (MAE) of 3.22 mm and root mean squared error (RMSE) of 3.92 mm; (2) during 2017–2024, the vertical LSD in SAYR was mostly −8–8 mm/y; (3) soil moisture determined the spatial distribution of the LSD direction in SAYR as a result of local drainage conditions, air temperature, precipitation and snow melt. This study demonstrated the necessity of removing the earthquake-related LSD when investigating the alpine permafrost LSD in tectonically active areas. The strategy adopted in this study serves as a technical reference for future investigations of this kind. The findings in this study provide insight for a thorough understanding of permafrost evolution on the Tibetan Plateau in the context of climate change. Full article

This study addresses the early-age brittleness and performance limitations of sustainable cement soil. While prior works optimized the baseline compressive strength using recycled sand and nanoclay, the multi-scale synergistic effects of fibers and nanomaterials on the post-peak deformation remain underexplored. To address this gap, a composite modification system incorporating recycled sand, nanoclay, polypropylene fibers, and graphene derivatives was developed. The experimental program comprised standard specimen fabrication, early-age curing, and unconfined compressive strength (UCS) testing, supplemented by RBF neural network curve fitting and quantitative ArcGIS digital image processing of scanning electron microscopy (SEM) micrographs. The results demonstrate that optimizing the fiber parameters (0.6% content with 6 mm length) successfully increases the early UCS to 2263.2 kPa, which is further elevated to a peak of 2755.0 kPa upon co-incorporation with 0.05% small-sized graphene oxide. Correspondingly, a newly introduced ductility index quantitatively confirms that the single-fiber reinforcement yields an index of 1.93, which is further enhanced to 2.02 by the graphene composite system. Microstructure tracking and digital image extraction revealed that the SEM-derived surface porosity decreased significantly, exhibiting a clear inverse relationship with the macroscopic mechanical strength. These quantitative microstructural shifts confirm that graphene effectively filled micropores and reinforced the fiber–matrix interface, establishing a dense matrix network with enhanced interfacial bonding. This multi-scale approach offers a sustainable strategy for green geotechnical applications. Full article

Carotid artery disease has traditionally been assessed according to luminal stenosis, although plaques with similar narrowing may differ substantially in biological activity and clinical risk. Intraplaque neovascularization is a key feature of plaque vulnerability, reflecting microvascular proliferation and its association with inflammation, hemorrhage, and structural destabilization. Dynamic contrast-enhanced ultrasound (DCE-US) offers a real-time, radiation-free method for evaluating intraplaque enhancement kinetics using strictly intravascular microbubble agents. However, its broader use in carotid plaque imaging remains limited by variability in acquisition protocols, contrast administration, signal processing, curve fitting, and parameter interpretation. This technical review clarifies the main analytical approaches used in carotid DCE-US, distinguishing bolus-based wash-in/wash-out analysis from destruction–replenishment modeling. Bolus analysis describes first-pass microbubble transit through the plaque microvasculature and commonly provides parameters such as peak intensity, wash-in slope, area under the curve, and time to peak. Destruction–replenishment analysis evaluates post-destruction refill under stable or quasi-stable contrast conditions and relies on model-based estimation of plateau intensity and the replenishment rate. Because these approaches interrogate different kinetic regimes, their outputs should not be considered interchangeable, even when similar terms are used across studies. Particular emphasis is placed on the operational meaning of quantitative and semi-quantitative parameters, the assumptions underlying curve modeling, and the methodological consequences of ROI placement, motion correction, acoustic settings, and fitting constraints. Rather than proposing a universal acquisition protocol, this article provides practical principles for acquisition, analysis, and reporting, helping radiologists, neuroradiologists, neurologists, and vascular imaging specialists understand the processing steps, algorithmic assumptions, and model-dependent choices underlying software-derived curves and parameters. By making this analytical layer more explicit, the review seeks to support a transparent, reproducible, and biologically coherent approach to quantitative carotid plaque characterization. Full article

Garlic, a significant global specialty economic crop, is currently facing severe challenges from labor shortages and escalating production costs. Achieving full-process mechanized production is the core approach to ensuring sustainable industrial development and enhancing international competitiveness. This paper systematically reviews the research progress and application status of mechanized equipment throughout the entire crop cycle of garlic production, including seeding, field management, harvesting, and post-harvest processing and sorting. The study reveals that garlic equipment is undergoing a profound transformation from traditional mechanization to “opto-electro-mechanical integration” and intelligence. In the seeding phase, breakthroughs have been made in pneumatic precision seed-metering and machine vision-based clove bud orientation technologies, significantly improving the quality of upright planting. In field management, precise variable-rate application and targeted weeding have been preliminary realized through plant protection Unmanned Aerial Vehicle (UAV) downwash airflow field simulation (CFD) and deep learning-based image segmentation. In the harvesting phase, relying on 3D Discrete Element Method (3D-DEM) soil-cutting simulation and adaptive profile root-trimming technology, the industry is accelerating the transition from inefficient segmented harvesting to low-damage combined harvesting. In the post-harvest phase, hyperspectral imaging (HSI) and multi-label convolutional neural networks (CNNs) have been utilized to achieve high-speed non-destructive detection of internal and external quality. However, industry still faces critical bottlenecks such as the insufficient integration of machinery and agronomy, poor robustness of intelligent perception algorithms in complex environments, and high damage rates of core soil-engaging components. Future research should focus on lightweight algorithm deployment, digital twin-driven virtual prototyping, and the construction of regional standardized machinery–agronomy systems, aiming to build an efficient and universal intelligent production closed-loop for garlic. Full article

Laser Powder Bed Fusion (LPBF) is a complex manufacturing process that depends on precise control of printing parameters and melt pool geometry, which directly influence defect formation and final part quality. This study evaluated the reliability of a simplified thermal conduction-based melt pool model by combining post-process metallographic analysis with in situ dual-wavelength infrared thermal imaging. Experimental data were obtained through single-track printing on 316L, IN625, and CoCr alloys across a wide range of parameters. The simulated melt pool length showed strong agreement with thermal camera measurements (R²_adj > 0.78), while the width showed moderate but consistent correlation (R²_adj > 0.52). For melt pool depth, the model systematically deviated due to its inability to capture keyhole melting, although a strong linear correlation was still observed (R²_adj > 0.86). Cross-validation between metallographic measurements and thermal imaging revealed only a 6–9% discrepancy, confirming the reliability of both methods and the potential of dual-wavelength cameras for industrial process monitoring. Overall, the model proves to be a reliable tool for predicting melt pool surface geometry specifically within the conduction melting regime, while its predictive capability degrades significantly in the keyhole regime, where simulated peak temperatures reach up to 7000 °C and melt pool depth errors escalate due to the disregard of recoil pressure, liquid and vapor dynamics. Full article

Objectives: This study evaluated the utility of adaptive complex signal average (ACSA) diffusion-weighted imaging (DWI) specifically in breath-hold (BH) liver imaging, with a focus on signal intensity (SI) improvement, intrahepatic signal homogeneity, and apparent diffusion coefficient (ADC) behavior, and compared these findings with conventional non-ACSA DWI and free-breathing (FB) ACSA DWI. Methods: This retrospective study included 62 patients (mean age, 67.8 ± 13.6 years; 27 women) who underwent liver MRI with both FB and BH DWI on a 3-T system. Non-ACSA images were generated using conventional magnitude reconstruction, and ACSA images were reconstructed from identical raw data. SI, signal-to-noise ratio (SNR) and ADC were measured in the left lateral segment and right hepatic lobe. The signal intensity difference ratio (SIDR) between ACSA and non-ACSA, signal intensity ratio (SIR) and ADC ratio between right lobe and lateral segment were calculated. Results: In both FB and BH imaging, SI and SNR in both liver regions were significantly higher on ACSA DWI than on non-ACSA DWI (p < 0.01). ADC values were significantly lower with ACSA. SIDR was significantly higher in the left lateral segment (p < 0.01), indicating greater SI improvement in motion-prone regions. SIR and ADC ratios between lobes were significantly smaller with ACSA in both respiratory conditions (p < 0.01). FB-ACSA showed smaller SIR than BH-ACSA, while ADC ratios did not differ. Conclusions: ACSA DWI significantly improves SI, intrahepatic uniformity, and ADC reliability even under BH liver imaging. BH ACSA DWI may represent a potentially useful application complementary to FB ACSA DWI, supporting its consideration as a post-processing strategy for improving qualitative and quantitative liver DWI in future investigations. Full article

Composed Image Retrieval (CIR) aims to search a target database for images that best align with a user’s intent, conditioned on a reference image paired with modification requirements. Existing CIR architectures typically treat the visual reference and the textual modification as symmetrical inputs, fusing their features into a shared latent embedding space. From a user-centric perspective, however, these multi-modal inputs serve fundamentally asymmetric roles: the reference image acts as a soft semantic anchor, whereas the modification text functions as an explicit requirement specifying precise visual changes. Because current models optimize composition predominantly at a global representation level, these non-negotiable logical constraints are frequently violated during inference, leading to retrieval results that fail to satisfy the user’s explicit instructions. To mitigate this limitation, we introduce a novel, training-free verification framework for fashion retrieval that enforces textual constraint adherence without sacrificing the expressive flexibility of open-vocabulary natural language. Our approach leverages schema-conditioned large language models to extract explicit, structured logical constraints from raw queries during post-processing. A downstream vision-language agent subsequently verifies these constraints against the top retrieved candidate pool to penalize non-compliant images and optimize candidate ordering. Extensive evaluations across standard fashion benchmarks demonstrate that our plug-in framework consistently and significantly enhances the recall metrics of state-of-the-art supervised and zero-shot CIR baselines. Full article

Surface deformation induced by underground coal mining shows a clear time-lag effect, with persistent residual deformation in old goafs under strip pillar mining conditions, drawing significant research attention. This study focuses on the Gucheng mining area, where 210 Sentinel-1A SAR images (May 2017–January 2025) were processed using SBAS-InSAR to derive 7.5 years of time-series surface deformation. Based on these results, five strip pillar mining panels with different cessation times were selected. Through comparative analysis, a time-progressive sequence was constructed to identify post-mining residual deformation and stage-wise stabilization characteristics, and to reveal long-term deformation responses occurring years after cessation, thereby reconstructing the long-term evolution of surface deformation in old goafs. Furthermore, a stacking ensemble prediction model was developed to predict subsidence trends at representative feature points. The results indicate that subsidence mainly ranges from −20 to −10 mm/a, with a maximum of approximately −64 mm/a and cumulative subsidence of about −515 mm. Surface deformation follows a stage-wise evolution pattern of “residual subsidence—stage-wise stabilization—secondary subsidence—deformation stabilization”, with durations of approximately 2, 2, and 14 years, respectively, and overall stabilization occurring after approximately 18 years. The predicted results from the stacking model are highly consistent with the SBAS-InSAR monitoring data and can reliably describe the evolution trend of surface subsidence. The findings provide important evidence for understanding long-term surface deformation in old goafs of strip pillar mining areas. Full article

Rare-disease diagnosis is difficult because clinicians must identify plausible conditions from a large, severely imbalanced disease space using evidence distributed across clinical narratives, structured findings, and image-linked descriptions. This paper presents a hybrid pipeline with caption-mediated multimodal fusion for ranked rare-disease diagnosis and grounded explanation, developed and evaluated on the ZebraMap multimodal case-report dataset (69,146 structured cases; 1727 diseases). Grouped train–validation–test splitting by source article was applied to prevent leakage, and a sequential pipeline was constructed combining BM25 lexical retrieval, a class-balanced TF–IDF classifier, MedCPT dense retrieval and cross-encoder reranking, caption-based image-aware late fusion, and post hoc grounded explanation generation. The final pipeline achieved test MRR 0.3905 and Recall@10 0.5507 (nDCG@10 0.4273), while the strongest individual component, the class-balanced TF–IDF classifier, reached MRR 0.4200 and Recall@10 0.6279; the hybrid pipeline therefore integrates ranking with grounded explanation rather than maximizing single-metric diagnostic accuracy. On 256 explained cases, the explanation module achieved citation coverage 0.7334 and usefulness 3.8734, exposing a tradeoff between diagnostic accuracy and explanation richness. These results indicate that a hybrid retrieval-and-classification approach can support ranked rare-disease differential diagnosis and that grounded explanation quality can be evaluated quantitatively, extending computational support for the prolonged rare-disease diagnostic process. Full article

Visible and long-wave infrared (LWIR) image fusion is essential for robust imaging, yet balancing natural color and thermal detail remains challenging. This study proposes a novel framework integrating a selective pre-enhancement module, an advanced fusion network, and a Palette Denoising Diffusion Probabilistic Model (DDPM) for high-quality synthesis in no-reference environments. The fusion network employs an encoder–decoder architecture with Residual-in-Residual Dense Blocks (RRDBs) and a Convolutional Block Attention Module (CBAM) to extract discriminative multi-level features. Spatially Adaptive Normalization (SPADE) and a Visibility Deficiency Mask (VDF) are incorporated to adaptively compensate for information-poor regions while preserving modality-specific characteristics. The fused output is subsequently refined by a conditional DDPM to restore fine-grained textures and suppress noise. Finally, post-processing enhances global contrast and color naturalness while mitigating thermal artifacts. Experimental results demonstrate that the proposed method effectively reduces over-brightness and improves detail preservation in diverse nighttime scenarios. Full article

Electron beam powder bed fusion (E-PBF) requires reliable in situ process monitoring, and electron emission signals offer a promising avenue for this purpose. Most prior studies have relied on dedicated beam scans performed before or after melting, leaving open the question of whether the signal acquired during the melt itself can directly indicate geometric and topographical features of the fabricated part. In this work, the in-operando electron emission signal was recorded during spot-melting of a Ti-6Al-4V spur gear and evaluated for its ability to reconstruct geometric features and surface topography, with optical microscopy and profilometry serving as ground truth. A melt-pool dilation correction was applied to compensate for the geometric expansion of individual melt spots. After correction, the in-operando reconstruction reached agreement deviation values below 2.2% across the tooth tips, tooth bases, and chord widths, which are comparable to or better than those obtained from post-melt ELO imaging. Comparison with profilometer height profiles confirmed strong correlation with surface topography (Pearson 0.67–0.87 across all four profiles, p < 0.05 for all), indicating that the signal captures meaningful surface-topography variation in addition to geometric boundaries. The results demonstrate that the in-operando electron emission signal shows strong potential for in situ geometric and topographical assessment of complex parts in E-PBF, supporting its future integration into closed-loop process monitoring. Full article

Developing and evaluating visual perception systems for autonomous vehicles requires data across diverse and adverse driving conditions, yet collecting and annotating such real-world data is costly and often impractical. To address this challenge, we propose a modular, scenario-driven framework for generating synthetic datasets tailored to the evaluation of visual perception functions. The framework aligns with the operational boundaries and detection–response requirements of automated driving functions and comprises three stages: (1) configuring use-case-driven scenarios, (2) generating sensor data and ground truth via simulation, and (3) post-processing to ensure dataset usability. Designed to be generic and flexible, the framework is instantiated and demonstrated through its integration with specific platforms and tools, namely Pro-SiVIC and RTMaps. We evaluate the generated dataset from two perspectives, image fidelity and perception performance under synthetic weather conditions, in comparison to real-world conditions. Furthermore, we train multiple perception models under different learning paradigms, including baseline, transfer-learning, and mixed-training strategies, to examine the influence of synthetic data on robustness. Experimental results demonstrate not only the high quality of the generated data but also its effectiveness in evaluating visual perception functions, as well as its benefit to model robustness and generalization. Full article