Search Results (3,549)

Liquid biopsy and multi-omic biomarker integration are transforming precision oncology in breast cancer, providing real-time, minimally invasive insights into tumor biology. By analyzing circulating tumor DNA, circulating tumor cells, exosomal non-coding RNAs, and proteomic or metabolomic profiles, clinicians can monitor clonal evolution, therapeutic response, and recurrence risk in real time. Recent advances in sequencing technologies, methylation profiling, and artificial intelligence–driven data integration have markedly improved diagnostic sensitivity and predictive accuracy. Multi-omic frameworks combining genomic, transcriptomic, and proteomic data enable early detection of resistance, molecular stratification, and identification of actionable targets, while machine learning models enhance outcome prediction and therapy optimization. Despite these advances, key challenges persist. Pre-analytical variability, lack of standardized protocols, and disparities in access continue to limit reproducibility and clinical adoption. High costs, incomplete regulatory validation, and the absence of definitive evidence for mortality reduction underscore the need for larger, prospective trials. Integrating multi-omic assays into clinical workflows will require robust bioinformatics pipelines, clinician-friendly reporting systems, and interdisciplinary collaboration among molecular scientists, data engineers, and oncologists. In the near future, liquid biopsy is expected to complement, not replace, traditional tissue analysis, serving as a cornerstone of adaptive cancer management. As sequencing becomes faster and more affordable, multi-omic and AI-driven analyses will allow earlier detection, more precise treatment adjustments, and continuous monitoring across the disease course. Ultimately, these innovations herald a shift toward real-time, data-driven oncology that personalizes breast cancer care and improves patient outcomes. Full article

Accurate prediction of the internal corrosion rate is crucial for the safety management and maintenance planning of oil and gas pipelines. However, this task is challenging due to the complex, multi-factor nature of corrosion and the scarcity of available inspection data. To address this, we propose a novel hybrid prediction model, GM-Markov-PSO, which integrates a gray prediction model with a Markov chain and a particle swarm optimization algorithm. A key innovation of our approach is the systematic incorporation of symmetry principles—observed in the spatial distribution of corrosion factors, the temporal evolution of the corrosion process, and the statistical fluctuations of monitoring data—to enhance model stability and accuracy. The proposed model effectively overcomes the limitations of individual components, providing superior handling of small-sample, non-linear datasets and demonstrating strong robustness against stochastic disturbances. In a case study, the GM-Markov-PSO model achieved prediction accuracy improvements ranging from 0.93% to 13.34%, with an average improvement of 4.51% over benchmark models, confirming its practical value for informing pipeline maintenance strategies. This work not only presents a reliable predictive tool but also enriches the application of symmetry theory in engineering forecasting by elucidating the inherent order within complex corrosion systems. Full article

Industrial environments still rely heavily on analog instruments for process supervision, as their robustness and low cost make them suitable for harsh conditions. However, these devices require manual readings, which limit automation and digital integration within Industry 4.0 frameworks. To address this gap, this study proposes an intelligent and cost-effective system for non-invasive acquisition of measurement data from analog industrial instruments, leveraging machine vision and Artificial Neural Networks (ANNs). The proposed framework exploits the geometric symmetry inherent in circular and linear scales to interpret pointer positions under varying lighting and perspective conditions. A dedicated image-processing pipeline is combined with lightweight ANN architectures optimized for embedded platforms, ensuring real-time inference without the need for high-end hardware. The processed data are wirelessly transmitted to a Human–Machine Interface (HMI) and web-based dashboard for real-time visualization. Experimental validation on pressure and flow instruments demonstrated an average Mean Absolute Error (MAE) of 0.589 PSI and 0.085 GPM, Root Mean Square Error (RMSE) values of 0.731 PSI and 0.097 GPM, and coefficients of determination (R²) of 0.985 and 0.978, respectively. The system achieved an average processing time of 3.74 ms per cycle on a Raspberry Pi 3 platform, outperforming Optical Character Recognition (OCR) and Convolutional Neural Network (CNN)-based methods in terms of computational efficiency and latency. The results confirm the feasibility of a symmetry-driven vision framework for real-time industrial supervision, providing a practical pathway to digitalize legacy analog instruments and promote low-cost, intelligent Industry 4.0 implementations. Full article

Accurate sky–obstacle segmentation in hemispherical fisheye imagery is essential for solar irradiance forecasting, photovoltaic system design, and environmental monitoring. However, existing methods often rely on expensive all-sky imagers and region-specific training data, produce coarse sky–obstacle boundaries, and ignore the optical properties of fisheye lenses. We propose a low-cost segmentation framework designed for fisheye imagery that combines synthetic data generation, lens-aware augmentation, and a hybrid deep-learning pipeline. Synthetic fisheye training images are created from publicly available street-view panoramas to cover diverse environments without dedicated hardware, and lens-aware augmentations model fisheye projection and photometric effects to improve robustness across devices. On this dataset, we train a convolutional neural network (CNN) and refine its output with gradient-boosted decision trees (GBDT) to sharpen sky–obstacle boundaries. The method is evaluated on real fisheye images captured with smartphones and low-cost clip-on lenses across multiple sites, achieving an Intersection over Union (IoU) of 96.63% and an F1 score of 98.29%, along with high boundary accuracy. An additional evaluation on an external panoramic baseline dataset confirms strong cross-dataset generalization. Together, these results show that the proposed framework enables accurate, low-cost, and widely deployable hemispherical sky segmentation for practical solar and environmental imaging applications. Full article

Electrocardiography (ECG) is widely recognized as the gold standard for measuring heart rate (HR) and heart rate variability (HRV). However, photoplethysmography (PPG) presents notable advantages in terms of wearability, affordability, and ease of integration into consumer devices, despite its susceptibility to motion artifacts and the absence of standardized processing protocols. In this study, we review current ECG and PPG signal processing methods and propose a signal quality assessment and reconstruction pipeline tailored for dynamic, in-vehicle environments. This pipeline was evaluated using data gathered from participants riding in an automated vehicle. Our findings demonstrate that while blood volume pulse (BVP) derived from PPG can provide reliable heart rate estimates and support extraction of certain HRV features, its utility in accurately capturing high-frequency HRV components remains constrained due to motion-induced noise and signal distortion. These results underscore the need for caution in interpreting PPG-derived HRV, particularly in mobile or ecologically valid contexts, and highlight the importance of establishing best practices and robust preprocessing methods to enhance the reliability of PPG sensing for field-based physiological monitoring. Full article

Oil and gas fields in subsidence-prone regions face multiple hazards that threaten the resilience of their infrastructure. This study presents an integrated risk mapping framework for the Yibal field in the Sultanate of Oman, utilizing remote sensing and geophysical data. Multi-temporal PS-InSAR analysis from 2010 to 2023 revealed cumulative surface deformation and tilt anomalies. Micro-seismic and fault proximity data assessed subsurface stress, while a flood risk map-based surface deformation-adjusted elevation captured hydrological susceptibility. All datasets were standardized into five risk zones (ranging from very low to very high) and combined through a weighted overlay analysis, with an emphasis on surface deformation and micro seismic factors. The resulting risk map highlights a central corridor of high vulnerability where subsidence, seismic activity, and drainage pathways converge, overlapping critical infrastructure. The results demonstrate that integrating geomechanical and hydrological factors yields a more accurate assessment of infrastructure risk than single-hazard approaches. This framework is adaptable to other petroleum fields, enhancing infrastructure protection (e.g., pipelines, flowlines, wells, and other oil and gas facilities), and supporting sustainable field management. Full article

Eosinophilic esophagitis (EoE) has emerged as a major cause of dysphagia and food impaction worldwide. This narrative review traces the evolving therapeutic pipeline for EoE, highlighting agents spanning from late-stage clinical development to final approval. We summarize mechanistic insights that have driven a shift from broad immunosuppression to precise inhibition of type-2 inflammatory pathways, including blockade of key interleukin pathways. Randomized trials have demonstrated histologic and symptomatic gains, yet regulatory approvals and optimal positioning within treatment algorithms are pending. Parallel innovations in drug delivery aim to maximize mucosal exposure while minimizing systemic burden. Key challenges include heterogeneity in disease phenotype, paucity of long-term safety data, and the need for non-invasive biomarkers to guide precision prescribing. Cost considerations and patient preferences will shape adoption. By integrating advances across immunology, formulation science and clinical trial design, the therapeutic pipeline for EoE holds promise to transform care from empirical suppression to mechanism-based disease modification. Full article

Fruit detection and counting is a key component of data-driven resource management and yield estimation in greenhouses. This work presents a novel infrared-based approach to capsicum counting in greenhouses that takes advantage of the light penetration of infrared (IR) imaging to enhance detection under challenging lighting conditions. The proposed capsicum counting pipeline integrates the YOLO11 detection model for capsicum identification and the BoT-SORT multi-object tracker to track detections across a video stream, enabling accurate fruit counting. The detector model is trained on a dataset of 1000 images, with 11,916 labeled capsicums, captured with an OAK-D pro camera mounted on a mobile robot inside a capsicum greenhouse. On the IR test set, the YOLO11m model achieved an F1-score of 0.82, while the tracker obtained a multiple object tracking accuracy (MOTA) of 0.85, correctly counting 67 of 70 capsicums in a representative greenhouse row. The results demonstrate the effectiveness of this IR-based approach in automating fruit counting in greenhouse environments, offering potential applications in yield estimation. Full article

We study statistical dependence in the frequency domain using the integral probability metric (IPM) framework. We propose the uniform Fourier dependence measure (UFDM) defined as the uniform norm of the difference between the joint and product-marginal characteristic functions. We provide a theoretical analysis, highlighting key properties, such as invariances, monotonicity in linear dimension reduction, and a concentration bound. For the estimation of the UFDM, we propose a gradient-based algorithm with singular value decomposition (SVD) warm-up and show that this warm-up is essential for stable performance. The empirical estimator of UFDM is differentiable, and it can be integrated into modern machine learning pipelines. In experiments with synthetic and real-world data, we compare UFDM with distance correlation (DCOR), Hilbert–Schmidt independence criterion (HSIC), and matrix-based Rényi’s $\alpha$-entropy functional (MEF) in permutation-based statistical independence testing and supervised feature extraction. Independence test experiments showed the effectiveness of UFDM at detecting some sparse geometric dependencies in a diverse set of patterns that span different linear and nonlinear interactions, including copulas and geometric structures. In feature extraction experiments across 16 OpenML datasets, we conducted 160 pairwise comparisons: UFDM statistically significantly outperformed other baselines in 20 cases and was outperformed in 13. Full article

Fetal ventriculomegaly (VM) is a condition characterized by abnormal enlargement of the cerebral ventricles of the fetus brain that often causes developmental disorders in children. Manual segmentation and classification of ventricular structures from brain MRI scans are time-consuming and require clinical expertise. To address this challenge, we develop an automated pipeline for ventricle segmentation, ventricular width estimation, and VM severity classification using a publicly available dataset. An adaptive slice selection strategy converts 3D MRI volumes into the most informative 2D slices, which are then segmented to isolate the lateral ventricles and deep gray matter. Ventricular width is automatically estimated to assign severity levels based on clinical thresholds, generating labeled data for training a deep learning classifier. Finally, an explainability module using a large language model integrates the MRI slices, segmentation masks, and predicted severity to provide interpretable clinical reasoning. Experimental results demonstrate that the proposed decision support system delivers robust performance, achieving dice scores of 89% and 87.5% for the 2D and 3D segmentation models, respectively. Also, the classification network attains an accuracy of 86% and an F1-score of 0.84 in VM analysis. Full article

L360QS pipeline steel, due to its high toughness, high strength, resistance to sulfide stress cracking, and resistance to hydrogen-induced cracking, is increasingly being used in pipeline network construction. Its fracture behavior is a critical factor for safe operation in mountainous steep-slope environments, but it has not yet been widely studied. Therefore, this paper conducts extensive experiments on the ductile fracture of L360QS pipeline steel. The tests employed standard tensile, notched tensile, shear, and compression specimens, covering a stress triaxiality range from approximately −0.33 to 0.92. The study combined Ling’s iterative method to establish an elastoplastic constitutive model considering post-necking behavior, and incorporated it into finite element models to extract the average stress triaxiality and equivalent plastic strain at the moment of fracture initiation for each type of specimen. Based on the extracted data, a piecewise ductile fracture model was established: a simplified Johnson–Cook criterion is used in the high triaxiality range, while an empirical function is used to describe fracture behavior in the medium, low, and negative triaxiality ranges. The model was validated using a train–test split approach, predicting fracture displacements for an independent test set of specimens. The results showed all prediction errors were within 5%, demonstrating the model’s high accuracy. Furthermore, a Spearman correlation analysis quantified the influence of geometric factors, revealing that notch curvature has the strongest monotonic relationship in controlling average stress triaxiality and fracture strain. The fracture model established in this paper can accurately predict the fracture behavior of L360QS pipeline steel and provides a reliable basis for failure prediction and safety assessment under complex service conditions (such as mountainous steep slopes). Full article

This study presents SpineCheck, a fully integrated deep-learning-based clinical decision support platform for automatic vertebra segmentation and Cobb angle (CA) measurement from scoliosis X-ray images. The system unifies end-to-end preprocessing, U-Net-based segmentation, geometry-driven angle computation, and a web-based clinical interface within a single deployable architecture. For secure clinical use, SpineCheck adopts a stateless “process-and-delete” design, ensuring that no radiographic data or Protected Health Information (PHI) are permanently stored. Five U-Net family models (U-Net, optimized U-Net-2, Attention U-Net, nnU-Net, and UNet3++) are systematically evaluated under identical conditions using Dice similarity, inference speed, GPU memory usage, and deployment stability, enabling deployment-oriented model selection. A robust CA estimation pipeline is developed by combining minimum-area rectangle analysis with Theil–Sen regression and spline-based anatomical modeling to suppress outliers and improve numerical stability. The system is validated on a large-scale dataset of 20,000 scoliosis X-ray images, demonstrating strong agreement with expert measurements based on Mean Absolute Error, Pearson correlation, and Intraclass Correlation Coefficient metrics. These findings confirm the reliability and clinical robustness of SpineCheck. By integrating large-scale validation, robust geometric modeling, secure stateless processing, and real-time deployment capabilities, SpineCheck provides a scalable and clinically reliable framework for automated scoliosis assessment. Full article

Hydrogen pipeline compression is essential for H${}_2$ transportation, with low molecular mass limiting achievable pressure ratios. Existing meanline-based studies offer little guidance on 3D-geometry generation, while existing CFD analyses provide limited insight into secondary flows, loss mechanisms, and off-design behavior. An in-house tool combining meanline, streamline-curvature, and genetic algorithms generates CAD-ready geometries, analyzed with steady 3D CFD from surge to choke. In the absence of H${}_2$ experimental data, validation on an air compressor showed CFD errors of 1% in pressure ratio and 2% in isentropic efficiency. Simulations of the H${}_2$ compressor reveal that tip-leakage vortices dominate rotor-exit nonuniformity and mixing losses. Two potential stall triggers are identified: (1) incidence-induced separation at the leading-edge hub corner; (2) vaneless diffuser rotating stall, as hub separation tendencies seem connected to reduced static-pressure recovery. However, a deeper characterization would require advanced unsteady schemes. At choke onset, the incidence reaches −10°, and the relative Mach number at the leading-edge tip is 0.63, indicating a subsonic negative-incidence stall rather than sonic choking. A meanline loss breakdown analysis corroborates CFD by showing that mixing losses and skin friction prevail. Design-improvement areas have been identified to enhance the performance of hydrogen compressors for future energy systems. Full article

Pedestrian accessibility is a critical dimension of sustainable and inclusive transportation systems, yet many cities lack reliable data on infrastructure features that support visually impaired users. Among these, podotactile paving plays a vital role in guiding movement and ensuring safety at intersections and transit nodes. However, tactile paving networks remain largely absent from digital transport inventories and automated mapping pipelines, limiting the ability of cities to systematically assess accessibility conditions. This paper presents a scalable approach for identifying and mapping podotactile areas from mobile and handheld laser scanning data, broadening the scope of data-driven urban modelling to include infrastructure elements critical for visually impaired pedestrians. The framework is evaluated across multiple sensing modalities and geographic contexts, demonstrating robust generalization to diverse transport environments. Across four dataset configurations from Madrid and Mantova, the proposed DeepLabV3+ model achieved podotactile F1-scores ranging from 0.83 to 0.91, with corresponding IoUs between 0.71 and 0.83. The combined Madrid–Mantova dataset reached an F1-score of 0.86 and an IoU of 0.75, highlighting strong cross-city generalization. By addressing a long-standing gap in transportation accessibility research, this study demonstrates that podotactile paving can be systematically extracted and integrated into transport datasets. The proposed approach supports scalable accessibility auditing, enhances digital transport models, and provides planners with actionable data to advance inclusive and equitable mobility. Full article

Marine risers, critical structures connecting underwater production systems and surface floating platforms, stand freely in water and endure extremely complex marine environmental loads. To meet the multi-parameter observation demand for their overall state, a fiber-optic sensing-based marine riser buoy observation system was developed. Unlike traditional point-type and offline monitoring systems, it integrates marine buoys with sensing submarine cables to achieve long-term real-time online monitoring of risers’ overall state via fiber-optic sensing technology. Comprising two main modules (buoy monitoring module and fiber-optic sensing module), the buoy’s stability was verified through theoretical derivation, simulation, and stability curve plotting. Frequency domain analysis of buoy loads and motion responses, along with calculation of motion response amplitude operators (RAOs) at various incident angles, showed the system avoids wave periods in the South China Sea (no resonance), ensuring structural safety for offshore operations. A 7-day marine test of the prototype was conducted in Yazhou Bay, Hainan Province, to monitor real-time temperature and strain data of the riser in the test sea area. The sensing submarine cable accurately responded to temperature changes at different depths with high stability and precision; using the Frenet-based 3D curve reconstruction algorithm, pipeline shape was inverted from the monitored strain data, enabling real-time pipeline monitoring. During the test, the buoy and fiber-optic sensing module operated stably. This marine test confirms the buoy observation system’s reasonable design parameters and feasible scheme, applicable to temperature and deformation monitoring of marine risers. Full article