Search Results (6,792)

As unmanned aerial vehicles (UAVs) are increasingly deployed in mission-critical domains such as military operations, infrastructure inspection, and disaster response, the threat of GPS and network spoofing attacks has emerged as a fundamental challenge to operational continuity. Existing intrusion detection systems based on threshold rules or shallow machine learning models are inherently limited in their ability to identify the latent onset of sophisticated, gradually intensifying spoofing campaigns—a gap that motivates the present work. This study proposes a deep learning-based early detection and network resilience prediction framework that employs Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures operating on three spatio-temporal network features—Hop Count Spike Rate (HCS), Packet Drop Volatility (PDV), and Spatial Disconnect Density (SDD)—proposed in this study. To reflect realistic adversarial conditions, we design a Gradual Adaptive Attacker model in which the spoofing intensity escalates progressively across six operational phases, including a second-stage adaptive attack that modulates its gradient upon detecting initial countermeasures. Both models are trained on 1000 simulated runs using sliding-window time-series sequences and evaluated across 500 independent test runs with paired statistical testing. The GRU model achieves a mean ROC-AUC of 0.9915 (±0.0091) and a mean F1-Score of 0.9099 (±0.0462), outperforming LSTM across all metrics with statistical significance at p < 0.001 under both the paired t-test and the Wilcoxon signed-rank test. Critically, GRU detects spoofing onset with an average latency of 0.503 time steps—approximately 29.4% faster than LSTM (0.712 steps)—a difference confirmed as statistically significant (p < 0.001, Cohen’s d = 0.41). Network resilience simulations further demonstrate that integrating GRU-based autonomous evasion maintains a Connectivity Ratio (CR) above 80% even under severe attack phases, whereas passive networks experience total connectivity collapse (CR = 0%). These findings establish GRU as the superior architecture for real-time UAV edge deployment and affirm that the proposed pipeline extends beyond threat alerting to actively preserving mission continuity under adversarial spoofing conditions. Full article

Siamese tracking is widely used in object tracking due to its efficient dual-branch symmetric structure, deep feature matching mechanism, and flexible template strategy. Existing mainstream Siamese tracking algorithms typically employ static template matching or linear combination-based template updating to localize the target in the next frame. However, these mechanisms often struggle to ensure template accuracy in complex environments involving changes in target appearance, scale, occlusion, and motion blur, thereby compromising robustness and stability. To address these issues, this paper proposes a confidence-guided adaptive template update with a re-detection (CATUR) network. CATUR constructs a tracking confidence assessment module that uses average peak-to-correlation energy (APCE) and a dynamic threshold mechanism to determine the current tracking state, providing a basis for template updates and target re-detection. It also designs an adaptive template update network that effectively combines the initial, historical, and current-frame templates, enhancing adaptation to target appearance variations. By integrating a global search module and a re-detection module, CATUR achieves precise target re-localization, rapid template updating, and tracking recovery. Extensive experiments and ablation studies on LaSOT and TrackingNet demonstrate that CATUR improves AUC, PNorm, and P by 4.0%, 4.0%, and 3.2%, respectively, significantly enhancing tracking accuracy and robustness in complex environments. Full article

Background: Surveillance of non-muscle-invasive bladder cancer (NMIBC) relies on cystoscopy and urine cytology, both of which have well-recognised limitations. Molecular urine assays have been developed to reduce the burden of invasive surveillance, yet their real-world clinical utility remains uncertain. Uromonitor^® is a quantitative PCR-based assay targeting hotspot variants in the TERT promoter, FGFR3, and KRAS, which are frequently altered in urothelial carcinoma. We evaluated the performance of Uromonitor^® in routine clinical practice and assessed its technical reproducibility. Methods: Uromonitor^® diagnostic test accuracy was retrospectively calculated from samples from patients undergoing investigation for suspected bladder cancer (n = 64) or surveillance (n = 30) following a prior diagnosis at a tertiary referral centre between 2021 and 2023. Uromonitor^® results were compared with histology where available (n = 49, 52%), or with contemporaneous cystoscopy and urine cytology findings (n = 45, 48%). This pragmatic dual reference standard reflects routine clinical practice but may introduce some heterogeneity in diagnostic accuracy verification. A prospective in-house verification cohort was used to assess inter-laboratory reproducibility. Discordant cases underwent orthogonal next-generation sequencing (NGS) analysis. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy were calculated for the Uromonitor^® against the standard of care. Results: Ninety-four patients were included in the clinical performance analysis. Overall sensitivity, specificity, PPV, NPV and overall accuracy for Uromonitor^® were 38%, 88%, 63%, 72% and 70%, respectively. Sensitivity was higher in the diagnostic setting (47%; 95% CI 27.3–68.3%) than during surveillance (23%; 95% CI 8.2–50.2%). Several false-negative cases in the verification cohort harboured variants either detectable by NGS at variant allele frequencies below or slightly above the assay’s limit of detection or variants not covered by the assay hotspot design. Inter-laboratory reproducibility was excellent, with 100% concordance observed in the verification cohort. Conclusions: In a real-world clinical setting, Uromonitor^® demonstrated high specificity but limited sensitivity for detection of bladder cancer, particularly during surveillance. A negative result does not reliably exclude recurrence. Assay sensitivity thresholds and restricted variant coverage appear to be key contributors to false-negative results. These findings highlight the need for cautious clinical integration of Uromonitor^®. It is unclear whether this approach has sufficient sensitivity in surveillance to safely reduce cystoscopy frequency. This underscores the need for further refinement of urine-based molecular assays, including a need for enhanced sensitivity and broader mutational coverage before routine clinical adoption. Full article

In software engineering, detecting and managing code smells are pivotal for maintaining software quality and reducing the risk of defects. Code smells signify potential issues in code that, while not problematic in themselves, may indicate deeper design flaws or future complications. Traditional code smells detection methods, which compare code metrics against fixed or statistically derived thresholds, may not always yield the most accurate code smells relevant to specific software practices. Addressing this gap, this research introduces an innovative methodology that utilizes a neural threshold generator, trained via a cooperative critic, to dynamically generate threshold values for detecting code smells in software components. Although the critic is conceptually related to the discriminator in a Generative Adversarial Network (GAN), its training objective is aligned with rather than adversarial to that of the generator. By integrating relevant code metrics, the proposed model generates customized thresholds for each software component. Our current evaluation focuses on a set of 11 class-level code smells defined by single or AND-connected conditions. It then uses these thresholds to identify code smells, which serve as input features to train a defect prediction model. A key feature of our approach is a cooperative-critic feedback mechanism that continuously refines the thresholds based on the defect prediction outcomes, ensuring the model’s effectiveness in identifying potential software issues is consistently improved. This advanced approach has demonstrated superior defect prediction performance, as evidenced by improved metrics such as the F1-score, AUC-ROC, and AUC-PRC, compared with the results of a defect prediction model that uses the traditional thresholds. Our study underscores the effectiveness of generating context-specific thresholds through neural networks, suggesting a promising avenue for exploring related software practices. Full article

Co-channel interference (CCI) remains a critical factor affecting link reliability in narrowband wireless systems, especially in scenarios with intensive frequency reuse, overlapping coverage, and dense terminal access. Existing interference detection methods are either computationally simple but insufficiently sensitive to short-term spectral variations, or highly accurate but dependent on labeled data and nontrivial inference resources. To address this issue, this paper proposes a lightweight CCI detection method in the FFT domain based on spectrum-jump analysis. The proposed method does not rely on absolute power growth as the primary interference indicator. Instead, it tracks the temporal inconsistency of dominant spectral-bin indices across consecutive FFT frames and converts recurrent peak-bin migration into an interference decision through a short-window counting mechanism. The method is computationally efficient, interpretable, and suitable for real-time deployment without offline model training. SDR-based measurements are combined with controlled repeated experiments to assess detector performance under varying signal-to-noise ratio (SNR), interference-to-signal ratio (ISR), carrier-frequency offset (CFO), multi-peak ambiguity, and two-path Rayleigh fading conditions. On the measured SDR record, the proposed method captures all interference-positive windows after the marked onset, while the controlled SNR/ISR experiments yield an overall detection probability of 96.0% over 250 CCI trials with no false alarms over 250 normal trials. ROC and precision–recall analyses further show that the selected threshold lies within a broad validation plateau. The results also reveal clear applicability boundaries: when the CFO approaches zero, when the interference is very weak, or when multiple stationary peaks have nearly equal power, dominant-bin migration may be weak or ambiguous. Therefore, the proposed approach is a low-complexity online detector for CCI cases that induce observable FFT-bin instability, and it can also serve as a front-end trigger for more advanced interference analysis modules. Full article

Wind turbine blade defect detection requires accurate identification of small and irregular defects while maintaining low computational cost for practical inspection scenarios. However, lightweight detectors often suffer from insufficient local feature extraction, limited multiscale feature fusion, and weak responses to critical defect regions. To address these issues, this study proposes a Receptive-Field-Enhanced You Only Look Once model (RFE-YOLO), a lightweight defect detection model based on You Only Look Once version 10 nano (YOLOv10n).The proposed model introduces three task-oriented improvements. First, C2f-RFAConv is embedded into the backbone to enhance receptive field aware local feature representation for fine grained defects. Second, a Compact Cross-scale Feature Fusion Module, termed CCFM, is designed in the neck to improve the integration of low-level detail information and high-level semantic features with reduced computational complexity. Third, an Efficient Local Attention module is inserted before the detection head to strengthen defect-related spatial responses after feature fusion. Experiments were conducted on a wind turbine blade defect dataset containing three categories, namely Crack, Oil leakage, and Peel. The results show that RFE-YOLO achieves 89.9% mean Average Precision at an Intersection over Union threshold of 0.5, namely mAP@0.5, and 64.73% mAP@0.5:0.95. Compared with YOLOv10n, RFE-YOLO improves mAP@0.5 by 2.8 percentage points while reducing the number of parameters from 2.70M to 1.91M and giga floating point operations from 8.4 to 5.3. The inference speed reaches 88.8 frames per second on an NVIDIA GeForce RTX 3090 GPU. These results indicate that RFE-YOLO achieves a favorable balance between detection accuracy and model efficiency under the current experimental setting. Full article

Background: Burnout is a relevant occupational health concern in Emergency Medical Services (EMSs), with potential implications for workforce well-being, occupational health, and the sustainability of prehospital care. Although burnout has been widely studied among healthcare professionals, evidence concerning Emergency Medical Technician (EMT) students remains limited. This exploratory study aimed to estimate high burnout prevalence among EMT students and practising EMT professionals in Madrid, Spain, describe burnout dimensions in both groups, and examine sociodemographic correlates of high burnout status. Methods: A cross-sectional comparative study was conducted between March and June 2024 using a convenience sample of 85 participants: 43 EMT students and 42 practising EMT professionals. Burnout was assessed using validated Spanish versions of the Maslach Burnout Inventory: the MBI-SS for students and the MBI-HSS for professionals. Because these instruments are population-specific and rely on different norms and thresholds, between-group comparisons of raw scores were interpreted as exploratory. Descriptive analyses, between-group comparisons with effect sizes, correlation analyses, and an exploratory binary logistic regression model were performed. Results: High burnout was identified in 22 EMT students (51.2%) and 23 practising EMT professionals (54.8%), with no statistically significant between-group difference detected (p = 0.73; Cramer’s V = 0.04). Between-group comparisons of burnout dimensions showed small effect sizes for Emotional Exhaustion (Cohen’s d = 0.17), Depersonalisation (Cohen’s d = 0.24), and Personal Accomplishment (Cohen’s d = −0.26). Age was positively associated with Emotional Exhaustion (r = 0.29, p = 0.008) and Depersonalisation (r = 0.24, p = 0.028), and negatively associated with Personal Accomplishment (r = −0.26, p = 0.019). In the exploratory adjusted logistic regression model, age was associated with high burnout status (OR = 1.05; 95% CI 1.01–1.10; p = 0.017), whereas group and sex were not significant correlates. Conclusions: High burnout levels were observed in both EMT students and practising EMT professionals in this regional exploratory sample. However, the findings should be interpreted cautiously due to the cross-sectional design, convenience sampling, modest sample size, limited statistical power, and use of population-specific burnout instruments. These results suggest that burnout-related distress may be relevant across the EMT training-to-practice pathway and support the need for larger longitudinal and multicentre studies incorporating occupational, educational, and organisational variables. Full article

Intrusion detection system (IDS) research relies on accurately labeled network traffic datasets; however, label quality in IDS datasets is seldom audited prior to modeling. Many publicly available IDS datasets assign ground-truth labels based on capture filenames or temporal session windows rather than per-flow inspection, a practice referred to as file-level labeling. This study identifies and corrects a systematic mislabeling instance in SDN-MG25, a CICFlowMeter-based dataset for software-defined networking (SDN)-enabled microgrid intrusion detection. IP composition analysis, which cross-references each attack-labeled flow with the documented attacker IP address, reveals that the BackgroundAttackTraffic (BAT) class, comprising 3167 flows (79.5% of all attack labels), contains no attacker-originated traffic. All BAT flows involve legitimate microgrid hosts communicating with external services during the attack capture window. Correcting this labeling error increases binary detection F1 from 0.578 to $0.956\pm 0.005$, an improvement of $+0.378$ that is 4.2 times greater than the best single modeling improvement (threshold tuning, $+0.090$). Furthermore, Confident Learning, a state-of-the-art automated label-noise detector, recovers only 8.4% of mislabeled BAT flows (recall $=0.084$, precision $=0.247$), indicating that domain-knowledge audits are essential for detecting systematic, class-level mislabeling that statistical methods cannot identify. The end-to-end pipeline Macro F1 improves from 0.749 to 0.862 after label correction. IP composition analysis is proposed as a mandatory prerequisite for IDS dataset evaluation, and a reproducible two-stage pipeline with feature-tier ablation for session confound diagnosis is provided. Full article

Ship–bridge collisions in cross-sea bridge waterways are rare but potentially catastrophic events, making conventional accident-based risk assessment difficult to implement effectively. Existing AIS-based indicators capture vessel behaviors but insufficiently quantify bridge-passage safety margins, especially dynamic aspects such as crossing posture and readiness prior to bridge transit. To address this limitation, this study proposes a data-driven framework for detecting unsafe ship–bridge passages using two bridge-passage-oriented surrogate safety measures (SSMs) and extreme value theory (EVT). The Bridge-passage Lateral Clearance Margin (BLCM) quantifies the effective lateral safety margin retained during the realized bridge-crossing stage, while the Bridge-passage Readiness Lead Time (BRLT) measures how early a vessel becomes stably prepared for bridge passage before crossing. The Peaks Over Threshold (POT) model is first used to characterize the marginal extremes of the two indicators, and a bivariate threshold exceedance model (BTE) is then established to examine their joint risk behavior. Case studies of the Jintang Bridge and Zhoudai Bridge waterways demonstrate that the proposed framework can effectively screen and identify trajectories with unsafe or margin-deficient bridge-passage characteristics. The results show that unsafe passages are typically associated with both reduced lateral clearance and insufficient preparation time, and that joint modeling of the two indicators improves risk identification performance. The findings suggest that ship–bridge risk is better interpreted from the perspective of passage quality deficiency rather than simple geometric proximity. The proposed framework provides an interpretable tool for retrospective unsafe passage screening, traffic monitoring support, and post-event safety analysis in complex bridge waterways. Full article

Accurate and consistent forensic bruise assessment is critical in ensuring positive clinical and legal outcomes for victims of violence. In this study, a framework for automated bruise detection is presented that, for the first time, integrates narrowband alternate-light-source (ALS) forensic imaging and ambient white light imaging. This evaluation framework is designed to address long-standing issues with respect to equitable performance across skin tones and lighting scenarios via a combination of novel model diagnostic strategies. In particular, skin-tone balancing during training and testing, threshold-sensitivity analysis, and embedding-similarity partitioning are employed to quantify the model robustness and deployment trade-offs that arise in forensic image analysis. Models were implemented with ImageNet-pretrained backbones and trained on a unique, multi-annotator full-consensus dataset comprising both white-light and ALS (415 nm and 450 nm) images. The protocol emphasizes three axes of operational relevance: (1) illumination composition in training (W/ALS ratio); (2) subgroup fairness via targeted balancing; and (3) model operating-point selection (confidence and IoU thresholds) informed by confidence-stability metrics and bootstrapped uncertainty estimates. Systematic W/ALS ratio sweeps indicate peak accuracy under ALS-dominant training and declining performance as the proportion of white-light images increases within the training set. Skin-tone balancing reduced failure rates for darker skin tones but increased overprediction in some demographic subgroups. Embedding-similarity and seen/unseen injury analyses demonstrate inflated generalization under image-level partitioning. Ultimately, the findings suggest that future researchers and developers should employ injury-level data partitioning and ensure a weighted balance of ALS images during training. Full article

Object detection is a core component of industrial vision systems in manufacturing, infrastructure monitoring, and safety-critical sensing. While the mean average precision (mAP) averages the performance over all confidence thresholds, real-world deployment demands committing to a single operating threshold under score imprecision, distribution shifts, and asymmetric—often only approximately known—error costs. From a soft-computing perspective, deployment should explicitly manage this uncertainty rather than rely on a static validation optimum. We propose domain-specific and robust localization recall precision (DSR-LRP), a three-phase decision-support framework. The framework elicits soft domain preferences—such as asymmetric error costs, tolerable localization imprecision, and expected perturbations—from practitioner knowledge and encodes them as three quantitative parameters (k, ${\alpha }_{\mathrm{IoU}}$, $\beta$). A cost-sensitive, threshold-local objective aggregates the performance within a robustness band around each candidate threshold, jointly capturing the accuracy and local stability. Finally, it yields an interpretable recommendation package comprising the operating threshold, its DSR-LRP score, and visual evidence. Experiments on four practical datasets (blood cell screening, wildfire smoke monitoring, pothole detection, and semiconductor sensor inspection) showed that DSR-LRP consistently selected operating thresholds that were robust and cost-aligned. For example, in pothole detection, an LRP-optimal threshold degraded by 15.6% under simulated shifts, while the DSR-LRP recommendation changed by only 1.8%. DSR-LRP complements global metrics such as the mAP and provides a soft-computing-oriented tool for reliable, evidence-driven deployment of industrial object detectors. Full article

Background and Objectives: Spondylodiscitis is a severe spinal infection associated with substantial mortality. Standard diagnostic imaging is often limited to the symptomatic spinal segment, which may fail to detect infection foci in other spinal regions. The prevalence and prognostic significance of multifocal spondylodiscitis remain insufficiently characterized. Materials and Methods: A retrospective single-center cohort study was conducted at the University Medical Center Mannheim, Germany. All patients with a first diagnosis of imaging-confirmed infectious spondylodiscitis treated between 2008 and 2017 were included (n = 274). Disease distribution was classified as monosegmental, multisegmental unifocal, or multifocal. The study evaluated the detection rate of multifocal disease stratified by imaging modality (whole-spine MRI vs. segmental MRI) and assessed in-hospital mortality according to disease distribution, comorbidity burden, and pathogen type. Results: Among the 139 patients who underwent whole-spine MRI, multifocal spondylodiscitis was identified in 25 (18.0%) compared with 2 out of 116 patients (1.7%) who received segmental MRI. Overall in-hospital mortality was 16.9% (46/272). Mortality was substantially higher in patients with multifocal disease (40.0%) than in those with monosegmental (13.7%) or multisegmental unifocal involvement (15.6%, p = 0.002). Increasing comorbidity burden (7.5% with no comorbidities to 27.1% with three or more; p = 0.008) and Staphylococcus aureus infection (26.2% vs. 11.0%; p = 0.010) were also significantly associated with mortality. Conclusions: Multifocal spondylodiscitis was more frequently detected with whole-spine MRI and was associated with substantially increased in-hospital mortality. These findings support consideration of a low threshold for whole-spine MRI in the primary diagnostic workup of suspected spondylodiscitis. Further prospective studies are required to confirm these findings. Full article

Due to the complexity of recent power grids, any fault can dramatically affect the system’s quality, reliability, and stability. As a result, identifying faults becomes essential to maintaining the stability and reliability of power systems within acceptable thresholds. This article presents an innovative binary classification fault detection method in recent power grids. The proposed methodology primarily consists of two preliminary stages before the training phase: data preparation and pre-training, aimed at improving the performance of the classifier. During the data preparation phase, the synthetic minority over-sampling approach balances the raw data, and the pre-training phase identifies the optimal features and hyperparameters. A novel hybrid approach combines the Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) methods to optimize feature selection and adjust hyperparameters. Furthermore, four machine learning models are trained and evaluated using an actual fault dataset. In addition, several evaluation criteria and receiver operating characteristic curves are used to validate the strength and robustness of the suggested method. All experimental evaluations were performed in an Azure Machine Learning Studio (AMLS) environment. The experimental results are compared to previous studies to verify the superiority of the suggested technique. Full article

Brominated flame retardants (BFRs) are widely used in automotive polymers and electronic components, yet vehicles remain an under-characterized and potentially high-exposure microenvironment, particularly in hot climates. This study provides the first comprehensive assessment of BFR occurrence, sources, and exposure risks in vehicle dust from Saudi Arabia, addressing a critical regional data gap. This study systematically investigates the occurrence, compositional patterns, sources, and human exposure risks of polybrominated diphenyl ethers (PBDEs) and selected alternative BFRs in dust from 80 vehicles (domestic cars and taxis; model years 2015–2022) operating in Jeddah, Saudi Arabia. Dust samples were collected using a standardized vacuuming protocol, extracted and cleaned using solvent extraction and silica SPE, and analyzed via GC–NCI–MS. Both legacy PBDE congeners and emerging alternatives (including DBDPE and TBB) were consistently detected, with BDE-209 dominating the overall BFR burden with mean concentrations of 6560 ng/g in domestic vehicles and 5454 ng/g in taxis, with maximum values reaching 220,860 ng/g. Lower-brominated PBDEs occurred at substantially lower concentrations, reflecting the ongoing global transition away from Penta- and Octa-BDE formulations. Taxis exhibited generally higher concentrations than domestic vehicles, likely due to prolonged occupancy, increased usage intensity, and enhanced dust resuspension dynamics. Multivariate analysis (PCA and correlation) revealed two distinct source categories: (i) legacy Penta-BDE-related congeners associated with polyurethane foam and textile materials and (ii) high-brominated PBDEs and DBDPE linked to hard plastics and electronic components. Human exposure assessment demonstrated that dust ingestion is the dominant exposure pathway, while dermal and inhalation routes contribute minimally. Non-carcinogenic hazard indices (HI) were well below unity for all compounds (HI < 1.67 × 10⁻⁶), and incremental lifetime cancer risks (ILCR) for BDE-209 remained within or near accepted risk thresholds (7.52 × 10⁻⁶–1.04 × 10⁻⁵), although occupational exposure among taxi drivers was consistently higher. Overall, the results demonstrate that modern vehicle cabins act as significant microenvironments for chronic BFR exposure, particularly under high-temperature conditions. Despite generally low estimated risks, the combined effects of chemical persistence, bioaccumulation potential, and mixture toxicity—amplified by extreme in-cabin temperatures—highlight vehicles as overlooked yet significant exposure environments. These findings provide the first comprehensive dataset for the Arabian Peninsula and emphasize the need for climate-sensitive exposure assessment, safer material design, and targeted mitigation strategies in vehicle interiors. Full article

Spectral chest radiography with photon-counting detectors (PCDs) enables energy-resolved acquisition for bone/soft-tissue separation, but quantitative performance depends on detector cross-talk and the selected material decomposition algorithm. We performed a controlled simulation study comparing a conventional low-order polynomial decomposition model with two machine learning regressors (multilayer perceptron (MLP) and support vector regression (SVR)) for a cadmium telluride (CdTe) PCD. A Geant4-derived detector response model, coupled with a charge-transport model, was integrated into a physics-forward model including charge sharing and Poisson quantum noise. Digital LucAl/IEC 62220-2-1 phantoms with aluminum and polymethyl methacrylate inserts were used for quantitative bias/root mean square error (RMSE) evaluation, and task-based low-contrast detectability that was evaluated using an exponential transformation of the free-response operating characteristic (EFROC) method using a matched-filter template. Performance was evaluated over clinically relevant dose levels (0.07–7.5 mAs), calibration grid densities ($3\times 3$ to $8\times 8$), and numbers of energy thresholds ($M=2$–6). Polynomial decomposition was stable under sparse calibration, whereas ML methods benefited strongly from denser calibration and additional thresholds; SVR achieved the lowest RMSE under dense calibration, while MLP produced smoother maps and improved soft-tissue detectability at low-to-intermediate dose. At high dose, all methods approached near-ideal detection performance. These results quantify practical trade-offs between calibration requirements, quantitative accuracy, and low-contrast detectability for PCD-based spectral chest radiography. Full article