Search Results (7,914)

Background/Objectives: This review explores the role of artificial intelligence (AI), particularly with deep learning and machine learning, in the detection and classification of papilledema using retinal fundus imaging. Methods: The study synthesizes historical, technical, and clinical insights, comparing AI-based diagnostic accuracy with conventional methods. Results: Our findings demonstrate that AI systems, especially convolutional neural networks (CNNs), offer sensitivity and specificity comparable to, or even surpassing, expert-level fundoscopy. Conclusions: These results suggest significant implications for early diagnosis, triage, and telemedicine integration in ophthalmic care. Full article

With the development of deep Earth engineering, the stability of surrounding rocks subjected to high temperatures from fire hazards has become an increasingly prominent issue. Therefore, studying the physical and mechanical properties of rocks under different thermal treatment modes is of great significance for the design of underground engineering. Taking red sandstone as the research object, this paper conducts physical parameter tests, uniaxial compression tests, and X-ray diffraction (XRD) on specimens under real-time high temperatures and natural cooling in the range of 600–1000 °C, to analyze the variations in specimen composition, the correlation between physical and mechanical properties and temperature, and to explore the underlying mechanisms. The results show that under both real-time high temperatures and natural cooling, the volume of sandstone increases while the mass decreases with rising temperature. At 1000 °C, the volume expansion rates are 3.30% and 3.80%, and the mass loss rates are 6.30% and 5.60%, respectively. Mechanical parameters, including peak strength, elastic modulus, and peak strain under the two treatments, all deteriorate significantly compared with those at room temperature. At 1000 °C, peak strength decreases by 54.83% and 36.26%, elastic modulus decreases by 74.55% and 67.96%, and peak strain increases by 65.63% and 43.75%, respectively. High-temperature-induced changes in the internal mineral structure and composition of sandstone are the main causes of rock mechanical property deterioration. During the cooling process, thermal shrinkage and recrystallization of mineral particles densify the rock structure; therefore, the compressive strength of naturally cooled sandstone is higher than that under real-time high temperatures. This study can provide theoretical guidance for the repair and reinforcement of rock engineering after high-temperature action. Full article

Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model’s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies. Full article

Deep unconventional oil and gas reservoirs are critical to hydrocarbon exploration and development in China. However, their complex geological and petrophysical features, including high temperature, high pressure, high salinity, multiple pressure systems, and intricate pore–fracture structures, make them highly susceptible to formation damage during drilling, completion, stimulation, and production. Effective reservoir protection is therefore essential for minimizing damage and improving development efficiency. This paper systematically reviews recent advances in reservoir protection for deep unconventional reservoirs, with a focus on evaluation methods and protective materials. Laboratory evaluation methods, including permeability recovery, nuclear magnetic resonance, pressure decay, and spontaneous imbibition, together with field-based approaches such as well testing and production decline analysis, are summarized and assessed for their applicability to complex damage characterization. Major damage mechanisms, including liquid-phase trapping, solid invasion, sensitivity damage, stress sensitivity, and wettability alteration, are analyzed with emphasis on working fluid–reservoir interactions under multi-field coupling conditions. Recent progress in protective materials is also reviewed, covering polymer-based materials such as gel sealing agents, delayed-swelling hydrogels, water-/oil-soluble temporary plugging agents, and film-forming polymers, as well as ultrafine CaCO₃ and fiber-based materials. In addition, related protection technologies, including temporary plugging, film-forming fluid-loss control, underbalanced drilling, and low-damage completion fluids, are discussed. Existing models developed for conventional sandstone reservoirs are insufficient for deep unconventional systems. Future research should prioritize integrated evaluation and protection methods tailored to deep tight, shale, and fractured–vuggy carbonate reservoirs. This review provides a basis for understanding complex damage mechanisms, developing functional protective materials, and advancing integrated reservoir protection technologies for the efficient development of deep unconventional resources. Full article

Early rectal cancer represents a challenging setting in which accurate locoregional staging is essential to guide appropriate treatment. Current diagnostic strategies primarily include magnetic resonance imaging (MRI) and endoscopic ultrasound (EUS). However, both modalities show significant limitations in early-stage disease, particularly in T staging. This diagnostic gap impacts therapeutic decision-making, particularly in patients with lesions suggestive of deep submucosal invasion. In these cases, endoscopic submucosal dissection (ESD) may be insufficient to achieve adequate vertical negative margins, whereas radical surgery is associated with considerable morbidity and potential impairment of quality of life. In this gray zone, endoscopic intermuscular dissection (EID) has recently emerged as a novel therapeutic approach designed to overcome the limitations of standard endoscopic resection. By enabling dissection within the deeper intermuscular plane, it can achieve curative resections while preserving rectal wall integrity. This narrative review aims to explore the current diagnostic gaps in early rectal cancer and to define the potential role of EID within the current therapeutic algorithm. Full article

Incomplete spatio-temporal (ST) data from sensor networks in precision agriculture often limits environmental modeling and decision-making accuracy. To address this, we propose the Spatio-Temporal Conditional Diffusion Framework (ST-CDF), a generative approach for high-fidelity data reconstruction. The framework’s core is a deep denoising network that integrates a Graph Attention Network (GAT) to explicitly model non-Euclidean spatial correlations, a Differential Attention Transformer to capture abrupt temporal dynamics, and an Inverse Discrete Wavelet Transform (IDWT) module to preserve multi-scale signal details. The generative process is constrained by a physics-informed training objective, which injects known physical laws (i.e., the Penman–Monteith equation for reference evapotranspiration, $E{T}_0$) as an inductive bias, ensuring the imputed data maintains physical consistency. For privacy-preserving deployment on resource-constrained IoT devices, we extend the framework with a Federated Cluster-Guided Distillation (Fed-CGD) strategy. We conducted extensive experiments against established methods on two real-world agricultural datasets. ST-CDF demonstrated improved imputation accuracy across evaluated metrics. Its efficacy was most pronounced in the physically-demanding $E{T}_0$ calculation task, where data imputed by ST-CDF at an 80% missing rate achieved a Root Mean Square Error (RMSE) of 0.3485 and a Coefficient of Determination ($R^2$) of 0.7558, outperforming the baseline models. Furthermore, we explore ST-CDF as an explainable (XAI) framework for active agricultural decision support, demonstrating its utility in performing counterfactual simulations of “what-if” interventions, such as irrigation. The findings highlight ST-CDF as an effective, physically-grounded, and interpretable tool for data-driven scientific computation and precision agriculture. Full article

Deep-water gravity flow deposits constitute a critical frontier in global hydrocarbon exploration, and characterizing flows controlled by complex topography remains a significant challenge. Focusing on the Cretaceous Pointe Indienne Formation in the Lower Congo Basin, West Africa, this study systematically investigates the depositional characteristics, flow types, vertical sedimentary sequences, and depositional models of lacustrine gravity flows, based on newly acquired drill core data, analytical test results, and three-dimensional seismic interpretation from the study area. Three major gravity flow types are identified in this study: sandy debris flows, muddy debris flows and turbidity currents. Meanwhile, we highlight the critical roles of slide–slump deposits and contour currents in deep-water depositional evolution, which further clarifies the sedimentary characteristics, vertical facies association patterns and spatial distribution of the Pointe Indienne Formation. Based on these results, we construct a stepped-slope depositional model for lacustrine rift basins. This “stepped-slope-controlled gravity flow” model describes the evolution of sediment transport from high-density, block-based processes (slides/debris flows) to low-density turbulent processes (turbidity currents). Beyond explaining the geological features of sub-salt gravity flow deposits in the Lower Congo Basin, this model improves the accuracy of predicting deep-water gravity flow sand body distribution in lacustrine basins with analogous structural and topographic settings, providing robust geological and theoretical support for hydrocarbon exploration in similar regions. Full article

The mineral system model formalizes the critical geological processes and mappable parameters that control ore formation, which can then be translated into spatial predictors used as input features in machine learning (ML)-based mineral prospectivity mapping (MPM). In most MPM studies, exploration evidence features are indeed derived from the mineral system model of the targeted deposit type. However, not all features produced in this way are necessarily informative or favorable for prospectivity analysis. This challenge can be addressed by using feature selection frameworks to identify the most relevant features before applying ML and deep learning (DL) algorithms for mathematical integration. To address this need, this study employs an unsupervised variational autoencoder (VAE) framework to evaluate and rank exploration evidence layers. The VAE quantifies feature importance through a systematic strategy that measures the sensitivity of reconstruction-error components, mean squared error (MSE), mean absolute error (MAE), and Kullback–Leibler (KL) divergence, to individual feature variations. In this way, the VAE ranks the exploration features and helps to identify those that are the most useful for prospectivity mapping. The proposed approach was applied to a real geo-dataset from a porphyry copper district in Iran. Based on the conceptual model of porphyry copper mineralization, 15 evidence layers were generated, including proximity to phyllic, argillic, propylitic, iron oxide, and silicification alteration zones; proximity to intrusive rocks, faults, and fault intersections; and geochemical maps of Cu, Mo, Sb, Pb, Zn, As, and W. The VAE-based ranking indicated that evidence layers related to hydrothermal alterations, intrusive rocks, and faults were the most influential exploration features, whereas geochemical evidence layers showed lower relative importance. Based on this evaluation, two modeling scenarios were considered: in the first, all available features were used, and in the second, only the features selected by the VAE framework were included. In both cases, the final prospectivity model was produced by an autoencoder (AE). For comparison, the prediction-area (P–A) plots of the two prospectivity models were generated using 14 known mineral occurrences as positive ground-truth labels, indicating that the model based on the selected features achieved a higher prediction rate (80%) than the model based on all features (72%). These results demonstrate that the evidence layers derived from the mineral system approach can benefit from unsupervised VAE-based evaluation, leading to improved performance of the prospectivity modeling. Full article

Extremely low overlap leads to severely scarce local geometric correspondences across frame pairs. Pure geometric descriptors—encoding merely low-level shape signatures—inherently fail to impose sufficient constraints for reliable transformation estimation when matches become critically sparse, rendering registration fundamentally fragile. While recent red-green-blue-depth (RGB-D) attempts have explored visual augmentation, they predominantly rely on low-level chromatic statistics or shallow convolutional neural network (CNN) features, underutilizing the rich hierarchical semantics inherent in RGB imagery. We present V3Reg, a robust registration framework that pioneers the integration of large-scale vision foundation models (DINOv3) with adaptive cross-modal fusion. Specifically, we extract mid-to-deep semantic features (Layer 11) from DINOv3 to transcend low-level texture limitations, and propose a Task-Aware Channel-Wise Gated Adaptive Fusion (TACGAF) module that dynamically calibrates geometric-visual contributions via registration-error-guided channel-wise gating. To rigorously evaluate ultra-low-overlap robustness, we reconstruct RGBD-ZeroMatch, a benchmark with controllable overlap ratios ranging from 1% to 20%. Extensive experiments demonstrate that V3Reg achieves 99.6% Feature Matching Recall and 96.3% Registration Recall on standard benchmarks. Notably, it maintains 50.2% Registration Recall at merely 5% overlap, outperforming prior methods by over 18 percentage points. Full article

The Nuri deposit is currently the only Cu-W-Mo deposit in the Gangdese metallogenic belt, Tibet, China, that contains large-scale tonnages for both Cu and WO₃ resources, accompanied by a medium-scale Mo resources. Previous studies have suggested the potential presence of concealed porphyry-type orebodies at depth, yet effective exploration tools for verifying this hypothesis remain lacking. In this study, microscopic identification, electron probe microanalysis (EPMA), and laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) were integrated to investigate the mineral chemical characteristics of chlorite from the Nuri deposit. The aim was to evaluate the effectiveness of chlorite geochemistry as an exploration vector for predicting deep concealed porphyry orebodies and to establish corresponding exploration indicators. Chlorite in the deposit can be genetically classified into metasomatic (Chl-I) and hydrothermal (Chl-II) types. Both types are Mg-rich varieties, indicating formation under conditions of low oxygen fugacity and low pH. With decreasing vertical distance to the orebody and toward the southeast direction of the exploration section, the contents of Ti (10–950 ppm) and V (50–820 ppm), as well as the Ti/Sr, Ti/Mn, Ti/Li, and V/Li ratios, progressively increase. In contrast, the concentrations of Li (36–390 ppm), Mn (1270–6730 ppm), Sr (1–510 ppm), and Zn (110–1100 ppm) systematically decrease. These systematic compositional variations demonstrate that chlorite geochemistry is an effective exploration tool in the Nuri mining area and suggest the presence of a concealed mineralization center or porphyry orebody beneath the interval from ZK4501 to ZK4502. Full article

Permeable concrete bricks incorporating waste tire rubber particles were prepared to improve sustainability and optimize the balance between mechanical performance and hydraulic behavior. Orthogonal experiments and response surface methodology were used to investigate the effects of aggregate-to-binder ratio (A/B), water-to-binder ratio (W/B), rubber content, and rubber particle size on compressive strength and permeability coefficient. Results showed that rubber content dominated compressive strength, while A/B ratio had the greatest influence on permeability. Compressive strength decreased continuously with increasing rubber content and A/B ratio, whereas permeability increased with A/B ratio and showed non-monotonic responses to rubber content and particle size. Response surface optimization identified an optimum mixture: A/B = 3.006, W/B = 0.45, rubber content = 0.103, and rubber particle size = 0.525 mm, yielding a compressive strength of 18.97 MPa and a permeability coefficient of 1.82 mm/s. Validation tests showed relative errors of 1.32% for compressive strength and 3.85% for the permeability coefficient, respectively. SEM and CT analyses revealed that the performance of the permeable concrete bricks was governed by the balance among skeleton integrity, interfacial bonding, and pore connectivity. These findings support the valorization of waste tire rubber in sustainable permeable paving materials. Full article

Industrial quality control is a critical component of modern manufacturing, as defects can lead to significant economic losses and safety risks. Traditional inspection methods, largely reliant on human operators or rule-based systems, often suffer from inconsistency, limited scalability, and reduced accuracy in complex environments. Recent advances in artificial intelligence (AI), particularly in deep learning and computer vision, have enabled automated defect detection and classification with unprecedented performance. This paper provides a comprehensive review of AI-based image processing techniques for industrial quality control, covering classification, detection, and segmentation approaches. Key applications across manufacturing sectors are discussed, alongside current challenges such as data scarcity, real-time implementation, and model generalisation. Furthermore, this paper explores emerging trends toward autonomous inspection systems, integrating real-time analytics, edge computing, and intelligent decision making. The insights presented aim to guide future research toward robust, scalable, and fully automated quality control solutions in smart manufacturing environments. Full article

Background: Tongue diagnosis is a fundamental diagnostic method in traditional medicine. Studies restricted to single ethnic groups may introduce bias and limit the clinical applicability of digital tongue diagnosis across diverse populations. Objectives: This study examined differences in tongue image features between Japanese and Brazilian (Caucasian ancestry) participants using digital tongue diagnosis technology and explored potential influencing factors. Methods: Tongue images were collected from 143 Japanese and 116 Brazilian participants attending traditional medicine clinics in Japan and Brazil. An independently developed tongue image analysis system (TIAS) was employed to extract shape, texture (gray level co-occurrence matrix), color (L*a*b color space), and deep-learning derived features (crack, prickle, tooth-mark, peel, greasy coating, stasis). Statistical analyses and machine learning models with SHAP explainability were used to compare features and identify key classification parameters. Results: Significant inter-group differences were observed in tongue shape, texture parameters (particularly at the root and tip), color parameters (especially middle-a-mean, middle-b-mean, tip-a-mean, and tip-b-mean), and deep features. The Japanese group showed a markedly higher prevalence of greasy coating (72.03% vs. 41.38%, p < 0.001) and stasis. Machine learning analysis revealed that the b value in the middle region of the tongue (middle-b-mean) contributed most strongly to the classification of greasy coating. Conclusions: The digital tongue image analysis system enables accurate and objective quantification of tongue features. Pronounced ethnic differences exist, particularly in the distribution of greasy coating. The middle-b-mean has the greatest impact on greasy coating classification. These findings underscore the importance of considering ethnic background when developing digital tongue diagnosis systems. Full article

With the increasing complexity of unmanned aerial vehicle (UAV) missions in complex obstacle environments, cooperative hunting of maneuvering ground targets by UAV swarms has become an important problem for multi-agent autonomous decision-making. This paper focuses on a simulated three-UAV hunting scenario in a two-dimensional obstructed environment, where UAVs must search for, approach, encircle, and continuously track a target while avoiding static obstacles under local observation. To address the problem of multi-UAV cooperative hunting of dynamic targets in complex obstacle environments, this paper proposes a curriculum learning (CL)-based Multi-Agent Proximal Policy Optimization algorithm, termed CL-MAPPO. Specifically, a three-stage progressive training curriculum is designed to overcome the challenges of low exploration efficiency, slow environmental adaptation, and difficult convergence of cooperative hunting policies faced by multi-agent deep reinforcement learning in hunting tasks, thereby gradually enhancing the cooperative hunting capability of UAVs in complex environments. Curriculum I employs fixed obstacles and a stationary target position to train the UAVs’ basic obstacle avoidance and target search abilities. Curriculum II introduces randomly generated obstacles and target positions to improve the UAVs’ adaptability to varying environments. Curriculum III further incorporates a dynamic target, prompting the UAVs to learn effective hunting strategies against maneuvering targets. The simulation experiment includes ablation experiments against MAPPO without curriculum learning and comparative simulations against MADDPG and MADQN, using reward convergence curves and trajectory visualizations to evaluate the training results. The results show that, under the same training episodes in the ablation experiment, CL-MAPPO reaches a higher and more stable reward level than vanilla MAPPO, indicating improved learning efficiency without increasing model complexity. In the comparative experiment, the CL-MAPPO algorithm achieved a higher success rate in cooperative hunting. These simulation experiments verify the effectiveness and superiority of the CL-MAPPO algorithm in multi-agent cooperative hunting tasks. Full article

Tremella fuciformis polysaccharides (TFPS) exhibit anti-inflammatory and gut-microbiota-modulating activities, but conventional extraction methods often show limited efficiency and may affect polysaccharide structural integrity. This study optimized a deep eutectic solvent (DES)-based extraction method with potential environmental advantages for TFPS, characterized the major purified fraction, and evaluated its effects in a dextran sulfate sodium (DSS)-induced experimental colitis model. Extraction parameters for the choline chloride–lactic acid DES system were refined through single-factor testing combined with response surface methodology. The purified fraction TFPS-1 was characterized by chromatographic, spectroscopic, methylation, and NMR analyses, and its biological effects were assessed in DSS-treated mice. Under the optimized conditions, the TFPS yield reached 33.09 ± 1.52%, representing a 77.6% increase compared with hot-water extraction. TFPS-1 was identified as a low-molecular-weight glucan mainly containing α-(1→4)- and β-(1→6)-linked glucose residues. In experimental colitis mice, TFPS-1 alleviated body weight loss, colon shortening, and histopathological injury; increased mucus secretion and barrier-related gene expression; reduced pro-inflammatory cytokines; increased IL-10; and partially adjusted gut microbiota composition. These results indicate that DES-based extraction is an efficient strategy for preparing TFPS and provide evidence that TFPS-1 may be further explored as a food-derived polysaccharide ingredient for intestinal protection in experimental colitis-related contexts. Full article