Search Results (1,179)

Objective: Existing deep learning (DL) studies on brain metastasis have largely focused on algorithm or reader performance in controlled settings, whereas its role in routine teleradiology quality support remains unestablished. We evaluated the report-level impact of DL assistance on brain metastasis interpretation in a real-world teleradiology workflow using dual-sequence MRI. Materials and Methods: In this retrospective study, 600 patients who underwent contrast-enhanced dual-sequence brain MRI during two consecutive 3-month periods before (pre-DL, n = 286) and after (post-DL, n = 314) DL integration into teleradiology workflow were analyzed. Ten board-certified teleradiologists interpreted all the cases with or without DL-generated overlays. Report-level diagnostic metrics were assessed against a consensus reference standard established by faculty neuroradiologists. Subsequently, exploratory case-level stratified sensitivity analyses were performed for metastasis-positive examinations based on lesion multiplicity and the largest lesion size. Teleradiologists’ perceptions were assessed using a post-interpretation survey. Results: Compared with the pre-DL group, the post-DL group showed higher sensitivity (77.7% vs. 90.8%, p < 0.001), specificity (82.3% vs. 90.8%, p = 0.002), accuracy (80.8% vs. 90.8%, p < 0.001), positive predictive value (68.2% vs. 85.7%, p < 0.001), and negative predictive value (88.3% vs. 94.2%, p = 0.011). False-positive and false-negative rates were lower after DL implementation (11.9% vs. 5.7%, p = 0.009; 7.3% vs. 3.5%, p = 0.045). Sensitivity gains were most pronounced for cases with single metastasis (74.6% vs. 91.2%, p = 0.007) and with the largest lesion ≤ 5 mm (74.3% vs. 92.0%, p = 0.004), whereas sensitivity was similar for multiple metastases and for cases with a largest lesion > 5 mm. Survey responses suggested favorable usability and diagnostic support. Conclusions: In this real-world teleradiology workflow, DL implementation was associated with higher report-level diagnostic metrics and fewer false interpretations. DL assistance may help support quality control for brain metastasis interpretation, particularly in more subtle and diagnostically challenging cases, although radiologist judgment remains essential for subtle or borderline lesions. Full article

Falls are a leading cause of paediatric injuries, yet school-based prevention relies heavily on subjective observation rather than objective biomechanical assessment. This paper introduces the Safe Fall framework, integrating a judo-inspired educational programme with an occlusion-robust computer vision pipeline to quantify safe falling strategies. We analysed video recordings of 285 schoolchildren using a multi-stage architecture combining YOLOv8 for detection, SAM 2 for segmentation, and MMPose for skeletal tracking. The intervention yielded significant improvements in 60% of kinematic metrics ($p<0.05$), most notably a $+61.4\%$ increase in descent rate and expanded rolling ranges, indicating a shift from hazardous “freezing” behaviours to controlled energy dissipation. Unsupervised clustering confirmed a migration of students towards safe motor profiles, while a Random Forest classifier achieved an accuracy of 98.3% and an AUC of 0.998 in distinguishing fall quality. These findings demonstrate that integrating pedagogical training with automated vision modelling provides a scalable and evidence-based approach for reducing injury risk in real-world school environments. Full article

Background/Objectives: To evaluate and compare the qualitative and quantitative image performance of multiplexed sensitivity-encoding diffusion-weighted imaging (MUSE-DWI) against conventional single-shot (ss-DWI) and high-resolution single-shot (HR-ssDWI) sequences in patients with esophageal cancer. Methods: Twenty patients who underwent esophagus MRI, including ss-DWI, HR-ssDWI and MUSE-DWI, were retrospectively enrolled. Image quality, esophageal contour, lesion conspicuity and image distortion were independently graded by two radiologists using a five-point scale and compared between the three sequences. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of esophageal tissue were measured and compared between the three sequences. Results: After Bonferroni correction (p < 0.017), MUSE-DWI had significantly higher scores than HR-ssDWI in image quality, esophageal contour delineation and lesion conspicuity, and all three sequences had statistically significant differences in image distortion scores with MUSE-DWI performing the best. Quantitative analysis revealed that MUSE-DWI had the highest SNR and CNR values; significant differences were found in SNR between ss-DWI and HR-ssDWI (p < 0.001), and in both SNR and CNR between HR-ssDWI and MUSE-DWI (p < 0.001), while no significant differences were observed in SNR and CNR between ss-DWI and MUSE-DWI (p > 0.017). Conclusions: MUSE-DWI outperforms ss-DWI and HR-ssDWI in reducing image distortion, with comparable quantitative image quality metrics to ss-DWI. It represents a valuable optimized DWI technique for esophageal clinical imaging. Full article

In the realm of intelligent transportation systems (ITS), achieving optimal system performance relies heavily on the acquisition of comprehensive and high-quality spatio-temporal traffic data. In practical data-gathering processes, factors such as sensor malfunctions or communication interruptions often lead to incomplete or missing data records, which in turn substantially hinder the advancement of ITS applications. To address missing spatio-temporal data, a widely adopted paradigm involves the Latent Factorization of Tensors (LFT) model. Traditional LFT frameworks often employ the standard L₂ metric in their learning objective, making them easily affected by abnormal data points. Moreover, impulse noise frequently arises in sensors and communication scenarios. To address these limitations, this paper develops an Adaptive L${}_{p,ϵ}$-norm-incorporated Latent Factorization of Tensors (L${}_{p,ϵ}$LFT) model founded on two-fold concepts: (a) constructing a generalized objective function grounded in the L${}_{p,ϵ}$-norm distance to enhance robustness against outliers; (b) realizing the self-adaptation of model hyper-parameters through a fuzzy controller to enhance model practicality. Experimental evaluations on six traffic speed datasets derived from multiple metropolitan traffic networks demonstrate that the proposed L${}_{p,ϵ}$LFT model yields significantly higher imputation accuracy and superior computational efficiency compared with seven state-of-the-art approaches. Full article

Background/Objectives: We aim to evaluate whether digital imaging and communications in medicine (DICOM)-level deep learning-based iodine-boosting applied to dual-source dual-energy computed tomography (DECT) source DICOM improves image quality in low-iodine-dose abdominal DECT in adults undergoing post-procedure follow-up computed tomography (CT). Methods: This retrospective study included 43 adults (April–September 2025) who underwent dynamic dual-source DECT using a low-iodine protocol. Three CT reconstructions were compared: mixed images, conventional 50-keV virtual monoenergetic images (VMIs), and 50-keV VMIs generated after applying DICOM-based deep learning iodine-boosting/denoising to the tube-specific dual-energy source DICOM series prior to VMI/iodine-map reconstruction (deep learning-based reconstruction [DLR]-VMI). Iodine material density (IMD) images were compared between the conventional and DLR-processed datasets. Quantitative attenuation and signal-to-noise ratio (SNR) were assessed using paired and repeated-measures tests. Image quality was scored by two readers using a five-point Likert scale. Results: Attenuation varied across CT reconstructions for all regions of interest in both phases (all overall p < 0.001). Liver attenuation increased from 94.9 ± 22.0 Hounsfield units (HU) (VMI) to 114.5 ± 34.6 HU (DLR-VMI) during the arterial phase and from 127.6 ± 25.6 HU to 166.6 ± 39.9 HU during the portal venous phase (both p < 0.001). Liver SNR improved with DLR-VMI compared to VMI (arterial: 9.11 ± 3.62 vs. 6.06 ± 1.90; portal: 12.74 ± 3.56 vs. 7.90 ± 1.82; both p < 0.001). On IMD images, DLR increased HU-equivalent values and liver SNR (arterial: 5.20 ± 2.89 vs. 2.61 ± 1.39; portal: 9.22 ± 2.81 vs. 4.48 ± 1.28; both p < 0.001). Qualitatively, DLR-VMI yielded the highest overall image-quality scores for both reviewers in both phases (Reviewer 1, arterial/portal: 4 (4–5)/5 (4–5); Reviewer 2, arterial/portal: 4 (3–4)/4 (4–4)). DLR also improved the overall image quality of IMD images for both reviewers (all p < 0.001). Conclusions: Raw DICOM-level iodine-boosting DLR applied to dual-source DECT-source DICOM enabled enhanced image quality and improved quantitative and qualitative metrics in low-iodine-dose abdominal DECT. Full article

Selecting the best multi-objective algorithms for photovoltaic energy storage system (PV-ESS) design remains challenging due to limited benchmarking across renewable energy studies. This study addresses this gap through a systematic evaluation of four widely used multi-objective optimization algorithms: NSGA-II, Multi-Objective Particle Swarm Optimization (MOPSO), weighted-sum scalarization, and ε-constraint methods. Performance assessment utilized three Pareto front quality metrics: Inverted Generational Distance (IGD) for convergence quality, hypervolume (HV) for objective-space coverage, and spacing for solution distribution uniformity. The algorithms were tested on PV-ESS design problems in three developing economies (Nigeria, South Africa, India) under identical problem formulations and computational resources. NSGA-II achieved superior performance across all metrics in all three case studies. For convergence quality, NSGA-II attained a mean IGD of 0.0083, outperforming MOPSO by 29%, ε-constraint by 64%, and weighted-sum by 131%. For objective-space coverage, NSGA-II achieved a mean HV of 0. 700, representing 10–16% better coverage than other methods. For solution distribution, NSGA-II showed a mean spacing of 0.076, indicating 30–117% more uniform Pareto fronts. Computational efficiency analysis revealed that NSGA-II’s runtime is between 5.5 and 7.8 h per case, providing better quality–time ratios compared to ε-constraint methods (which are 18 times slower), while avoiding MOPSO’s premature convergence. Statistical validation confirmed NSGA-II’s superiority, with p < 0.01 across all quality metrics. These results establish NSGA-II as the best algorithm for lifecycle-aware PV-ESS optimization, offering quantitative, evidence-based guidance for practitioners selecting optimization tools for renewable energy system design. The demonstrated performance leads to $ 45,000–$ 60,000 lifecycle cost savings per MW/MWh of system capacity through improved Pareto front identification. Full article

Urban water distribution systems (WDSs) face increasing threats from accidental or intentional contaminant intrusion events. While contamination warning systems using water quality sensors enable early detection and rapid response to contamination events, traditional sensor placement approaches often rely on a single or limited performance metric, overlooking the multidimensional nature of system resilience. This study presents a multidimensional resilience-based framework for the optimal placement of water quality sensors in urban WDSs, integrating hydraulic and water quality simulations using the EPANET-MATLAB toolkit with a genetic algorithm (GA) optimization process. For Anytown Water Distribution Network, four distinct functionalities were formulated to capture different aspects of system performance during contamination events, and an integrated-multidimensional resilience metric was proposed as a collective measure. Results demonstrated that the optimal sensor configurations varied significantly depending on the selected functionality. However, the integrated multidimensional resilience-based approach yielded more balanced and effective sensor placements, simultaneously enhancing resilience levels for all individual functionalities. Furthermore, the findings indicated that adding more sensors beyond a certain number offers marginal improvements in system resilience, suggesting that sensor deployment should be guided by monitoring objectives (e.g., resilience) rather than simply increasing sensor numbers. The findings and discussion suggest practical insights for utilities to enhance water supply services with safe quality and system security against contamination threats in urban WDSs. Full article

Obtaining multiple MRI contrasts for each patient prolongs scan acquisition time, increases healthcare costs, and may not always be feasible due to patient specific constraints. Deep learning-based MRI contrast synthesis offers a potential solution, yet most existing approaches are evaluated on preprocessed public benchmarks that do not reflect real-world clinical variability. In this study, we propose a fusion U-Net transformer framework for bidirectional T1-weighted ↔ T2-weighted brain MRI synthesis trained and evaluated exclusively on retrospectively acquired clinical data. The proposed architecture integrates multiscale convolutional feature extraction with axial attention mechanisms and a transformer bottleneck for efficient global context modeling. A fusion refinement block is incorporated to mitigate skip connection artifacts. An adversarial training strategy with the least squares GAN objective and a hybrid loss combining L1 reconstruction and structural similarity (SSIM) is employed to promote both pixel-level accuracy and perceptual fidelity. The model is evaluated using SSIM and PSNR metrics alongside qualitative expert assessment conducted by two board-certified radiologists. For both synthesis directions, the framework achieves competitive quantitative performance against baseline models under the challenging conditions of clinical data. Expert evaluation confirms high anatomical fidelity and clinically acceptable image quality across both synthesis directions. These results indicate that the proposed framework represents a promising approach for multi-contrast MRI synthesis in clinically heterogeneous data environments. Full article

Objective: To investigate the integrated relationship between Cerebral Small Vessel Disease (CSVD) markers and quantitative facial soft-tissue measurements in Alzheimer’s disease (AD) continuum, utilizing peripheral muscle health as a potential biomarker for systemic frailty and neurodegeneration. Methods: Retrospective analysis of 3T brain MRI data from 67 patients (AD, N = 45; Mild Cognitive Impairment [MCI], N = 22). CSVD markers were assessed using STRIVE and standardized scales (Fazekas, Potter). Facial soft-tissue metrics, including masseter and tongue volume, temporal muscle thickness (TMT), and fat infiltration (Mercuri Scale), were quantified via semi-automatic segmentation on T1-weighted sequences. Group comparisons (AD vs. MCI) used regression models adjusted for age and sex. The overall central–peripheral relationship was explored via Canonical Correlation Analysis (CCA). Results: The AD group showed a highly significant cognitive decline (MMSE: 23.2 ± 4.1 vs. 28.2 ± 1.4, p < 0.0001). Centrally, the presence of PVSs in the mesencephalic region was the most robust predictor for AD (p = 0.003). Peripherally, average masseter muscle volume was significantly lower in the AD group (p = 0.0273), and masseter fat infiltration was significantly higher (p = 0.025), supporting localized sarcopenia. The CCA demonstrated a statistically significant positive multivariate relationship (r = 0.51, Roy’s Largest Root p = 0.015) between a higher combined CSVD burden and a worse soft tissue profile across the cohort. Conclusions: Quantitative indices of facial soft tissues, particularly masseter muscle volume and quality, reflect systemic frailty and cognitive deterioration along the AD continuum. The strong central–peripheral correlation suggests that sarcopenia and CSVD are interconnected manifestations of a shared pathobiological process. These easily measurable facial markers could serve as valuable, non-invasive peripheral biomarkers, complementing traditional neuroimaging risk stratification in AD. Full article

Background/Objectives: Frailty is common among rural Chinese older adults despite relatively high daily physical activity, a phenomenon known as the “rural frailty paradox.” Conventional moderate-to-vigorous physical activity (MVPA) metrics rely on absolute cut-points and are often highly correlated with activity volume, limiting their ability to distinguish the roles of activity volume and activity intensity distribution. We therefore applied a cut-point-free accelerometer approach using average acceleration (AvAcc) and intensity gradient (IG) to distinguish activity volume from activity intensity distribution and to examine whether activity intensity distribution, together with diet quality, could help explain the rural frailty paradox beyond total activity volume alone. Methods: In this cross-sectional analysis of the Healthy Aging and Lifestyle Enhancement study, 1203 rural older adults were included. Physical activity (PA) was objectively measured using triaxial accelerometers to derive AvAcc and the IG. Diet quality was assessed using the China Prime Diet Quality Score (CPDQS), and frailty was assessed using the Fried frailty phenotype adapted for rural Chinese older adults. Multiple linear regression, joint effect models, and restricted cubic spline analyses were conducted after adjustment for age, sex, chronic disease status, total energy intake, and related covariates. Results: In mutually adjusted models, higher IG and CPDQS were independently associated with lower frailty scores, whereas AvAcc was not. In the fully adjusted model, IG (β = −0.14, p < 0.001) and CPDQS (β = −0.10, p < 0.001) were inversely associated with frailty score, while AvAcc showed no significant association (p = 0.665). In joint analyses, compared with the low-IG/low-CPDQS group, participants with high IG/high CPDQS had the lowest frailty scores (β = −0.28, p < 0.001), followed by those with low IG/high CPDQS (β = −0.20, p = 0.002). Restricted cubic spline analyses indicated a non-linear association between IG and frailty and an approximately linear inverse association for CPDQS. Conclusions: These findings suggest that, among rural older adults, frailty may be more strongly associated with activity intensity distribution than with total activity volume alone. Together with diet quality, this may help explain the rural frailty paradox. Full article

Daytime detection of space targets is challenging due to the strong skylight background and the limited resolution of conventional polarization imaging systems. In this work, we present a semiconductor-based polarization detection method that integrates a CMOS polarization imaging sensor with a Schmidt–Cassegrain telescope. To compensate for the spatial resolution loss inherent in division-of-focal-plane semiconductor polarization detectors, a bicubic interpolation algorithm is applied to reconstruct the degree and angle of polarization images. Furthermore, a spectral filtering strategy is introduced to suppress skylight-induced stray radiation, improving image contrast and reducing the risk of detector saturation. The developed system combines semiconductor optoelectronic detection, optical filtering, and computational reconstruction into a compact experimental platform. Validation experiments on Polaris and low-Earth-orbit space targets under daytime conditions demonstrate that the proposed approach achieves clearer and sharper polarization images compared with traditional intensity-based methods. Objective evaluation metrics, including gradient, contrast, brightness, and spatial frequency, confirm significant improvements in image quality. These results highlight the potential of semiconductor optoelectronic devices for polarization-based imaging and provide an effective framework for enhancing daytime space target detection. Full article

Injection molding process optimization has predominantly relied on simulation-generated data, which cannot capture machine-specific variability and stochastic process noise inherent in real manufacturing environments. This paper presents an experiment-driven machine learning framework for multi-objective optimization of injection molding process parameters targeting volumetric shrinkage, warpage, cycle time, and part weight. Physical experiments were conducted on an industrial injection molding machine using high-density polyethylene with a face-centered central composite design. Systematic benchmarking of four machine learning algorithms under identical cross-validation protocols identified Gaussian process regression as the best-performing surrogate model for the majority of quality metrics, while warpage prediction remained challenging across all algorithms due to its complex thermo-mechanical origins. Permutation-based feature importance analysis established a clear parameter hierarchy, identifying holding time as the dominant factor governing multiple quality responses. Constrained Bayesian optimization with progressive constraint tightening was employed to identify optimal parameter sets and fundamental process capability boundaries. The resulting parameter configurations were validated against a held-out test set. This work demonstrates that rigorous, data-driven optimization using exclusively experimental data provides a viable and practically achievable alternative to simulation-based approaches, contributing to experiment-centric smart manufacturing in polymer processing. Full article

Background/Objectives: Young women with breast cancer (aged ≤ 40 years) have distinct prognostic characteristics, yet little is known about how modifiable body composition factors influence outcomes in this age group. This study examined whether CT-derived body composition measures could identify thresholds that predict overall survival (OS). Methods: This was a single-center, 10-year, matched case–control study nested within a cohort, utilizing retrospectively collected data. Using an institutional database (2009–2018) and the initial cohort of 112 patients, we performed a subset analysis of patients with stage I–III breast cancer at diagnosis who had available pretreatment CT scans to estimate associations with body composition metrics and OS. The final analytic dataset included 89 individuals (49 survivors and 40 deceased). CT scans at the L3 level were analyzed using Slice-O-Matic software to quantify visceral (VAT), subcutaneous (SAT), intermuscular (IMAT), total adipose tissue (TAT), skeletal muscle density (SMD), skeletal muscle gauge (SMG), and skeletal muscle index (SMI). Cox proportional hazard models determined optimal cutpoints for OS. Multivariable models included adjustments for disease stage and hormone receptor status. Results: The median age was 35 (IQR, 32–38); 47% were White and 37% were Black. The majority (78%) were not Hispanic or Latina. Most (67%) were overweight/obese. Specific thresholds for IMAT index (>2.57), VAT (>31.38), and SMG (<2419.89) were associated with worse survival (all p < 0.05), while no cutpoints were identified for other variables. Conclusions: These findings show that muscle fat infiltration and reduced muscle quality have important prognostic value in young women with breast cancer. Exploratory cutpoints derived from routine staging CT scans may help inform risk stratification and generate hypotheses for targeted nutritional or exercise interventions, but require validation in larger, independent cohorts before clinical application. Full article

Background/Objectives: Poor bone quality is strongly associated with adverse surgical events. Although dual-energy X-ray absorptiometry (DXA) remains the gold standard for bone mineral density (BMD) assessment, logistical barriers may limit its preoperative application. The Endplate Bone Quality (EBQ) score is an MRI-derived metric quantifying subchondral bone quality at the vertebral endplate with demonstrated predictive value for cage subsidence following lumbar interbody fusion. However, EBQ has been measured exclusively at the operative level in surgical cohorts. This study aimed to assess level-specific EBQ scores across the entire lumbar spine and compare distributions across age, sex and osteoporosis subgroups. Methods: A single-institution retrospective review of T1-weighted lumbar MRI studies from patients evaluated for lower back pain from 2020 to 2025 was performed. EBQ was independently scored by two blinded raters at each disc space from L1–L2 to L5–S1 using 3 mm endplate ROIs normalized to a CSF ROI at L3. Interrater reliability was assessed via ICC, Pearson correlation, and RMSE. Patients were stratified by age (≤60 vs. >60 years), sex, and osteoporosis status, and subgroup comparisons were performed for overall and level-specific EBQ score. Results: A total of 96 patients with an average age of 61.0 ± 9.42 years were included in this study. The majority of patients included were female (87.5%), and 18.8% had been diagnosed with osteoporosis. EBQ scores demonstrated a progressive caudal increase across all subgroups from L2–L3 to L5–S1. Overall interrater reliability was acceptable (ICC = 0.76), with level-specific ICCs ranging from 0.70 to 0.83. No significant differences were observed between age or sex subgroups. Osteoporotic patients demonstrated significantly higher EBQ at L1–L2, L2–L3, and overall (all p < 0.05), with no significant differences at L3–L4 through L5–S1. Conclusions: This study provides normative, level-specific EBQ reference data throughout all levels of the lumbar spine. The increase in EBQ scores seen among caudal levels and reduced osteoporotic discriminatory power support the importance of level-specific context when interpreting EBQ thresholds. These findings may support future studies evaluating threshold development for EBQ. Full article

Background/Objectives: To evaluate the relationships between meibomian gland dysfunction (MGD), ocular surface parameters, and matrix metalloproteinase-9 (MMP-9)-mediated inflammation in glaucoma patients, we specifically assessed the impact of prostaglandin analogue use, preservative exposure, and number of medications. Methods: This retrospective cross-sectional study included patients treated with topical antiglaucoma medications for at least six months. Meibomian gland expressibility, meibum quality, and MGD grade were assessed along with tear film break-up time (TBUT), Schirmer I test, and Oxford staining score. Tear MMP-9 levels were measured using a Point-of-Care immunoassay (InflammaDry^®) and graded on a 0 to 4 scale. Results: Elevated MMP-9 grades were significantly correlated with worsening meibum expressibility, meibum quality, and MGD grade (all p < 0.001), whereas no significant associations were found with traditional parameters such as TBUT and Schirmer I test. Prostaglandin analogue use was associated with worse meibomian gland parameters and higher MMP-9 levels compared to non-use. Patients receiving preservative-containing medications exhibited poorer meibomian gland parameters and MMP-9 levels, as well as worse corneal staining scores. An increased number of medications was associated with a stepwise deterioration in meibomian gland function and elevated MMP-9 levels. Conclusions: Prostaglandin analogue use, preservative exposure, and increased number of medications are significant factors associated with the exacerbation of MGD and ocular surface inflammation. Semi-quantitative grading of tear MMP-9 revealed a stepwise association with meibomian gland dysfunction severity that was not detected by conventional dry eye metrics, indicating that MMP-9 may be considered a potential indicator of subclinical ocular surface inflammation in glaucoma patients. Full article