Search Results (140)

Background: Accurate preoperative prediction of length of hospital stay (LOS) after surgery for colorectal liver metastases (CRLMs) could improve patient counselling and resource planning, yet reliable risk tools are lacking. We aimed to develop an interpretable machine learning model predicting LOS following first-time liver-directed surgery for CRLMs. Methods: In this multicenter cohort study, we included patients who underwent first-time liver resection, ablation, or a combination for CRLMs at three Danish hepatobiliary centers between 2016 and 2023. Preoperative features from two national registries were used to train Elastic Net, Random Forest, HistGradientBoosting, and Explainable Boosting Machine (EBM) algorithms. Hyperparameters were optimized using five-fold cross-validation. Performance was evaluated on a 20% hold-out test sample using mean absolute error (MAE) with bootstrapped 95% confidence intervals (CIs). Results: Among 915 patients, median LOS was 4.0 days (interquartile range (IQR) 3.0–6.0). All four algorithms achieved comparable prediction error (MAE 3.0–3.1 days). The EBM (MAE 3.1 days, 95% CI 2.6–4.3) algorithm was selected for its inherent interpretability. Surgical approach was the strongest predictor, where percutaneous and laparoscopic approaches were associated with reductions of 1.9 and 1.2 days, respectively. Tumor burden, including number of lesions and largest lesion diameter, showed progressive non-linear associations with longer stays. Nonetheless, overall explained variance was low (R² ≤ 0.10), and calibration showed systematic underestimation of stays beyond five days. Conclusions: An inherently interpretable machine learning model matched the predictive performance of opaque algorithms for LOS after CRLM surgery, although overall predictive accuracy was modest and longer stays were underestimated. Explainability analysis identified surgical approach and tumor burden as the most influential predictors. External validation in healthcare systems with different discharge practices is warranted. Full article

To measure the cross-view spacing between adjacent fastener bolts in railway turnouts, this study develops a dual-DLP-sensor structured-light measurement system without overlapping fields of view. A bridge-type calibration device is used to rapidly update the extrinsic parameters of the two DLP sensors. In a unified coordinate frame, the system integrates two-dimensional region-of-interest candidate generation, local three-dimensional geometric fitting, cross-view pairing, and measurement validity assessment to output bolt-spacing results. Experiments were conducted on 23 pairs of adjacent bolts with 15 repeated measurements using two DLP sensors. Under normal conditions, the mean absolute error, root mean square error, and average standard deviation were 0.261 mm, 0.290 mm, and 0.062 mm, respectively. Compared with fixed extrinsic parameters without updating, the bridge-based extrinsic update reduced the mean absolute error from 1.500 mm to 0.261 mm. The results indicate that the proposed task-driven dual-DLP-sensor measurement system can achieve stable cross-view spacing measurement with explicit validity criteria under non-overlapping fields of view, repeated deployment, and varying on-site data quality. Full article

Background/Objectives. Automated lateral ventricle volumetry is increasingly used in population-based neuroimaging, but correlation between methods does not establish agreement of absolute volumes. We quantified agreement and calibration between FreeSurfer and a visually quality-controlled FSL/FAST–ALVIN lateral ventricle workflow within the Study of Health in Pomerania (SHIP). Methods. This cross-sectional agreement-and-calibration study included 2988 SHIP participants with visually accepted FSL/FAST–ALVIN total lateral ventricle volumes; paired FreeSurfer data were available for 1913 participants. FSL/FAST–ALVIN was treated as the study reference scale rather than biological ground truth. Agreement was assessed using Pearson and Spearman correlations, Bland–Altman analysis, log-ratio agreement, Lin’s concordance correlation coefficient, and a two-way mixed-effects single-measure absolute agreement intraclass correlation coefficient. Directional calibration models predicted FSL/FAST–ALVIN volume from FreeSurfer volume and were internally validated using 2000 bootstrap resamples. Results. In the paired sample, volumes were almost perfectly associated (Pearson r = 0.9978; Spearman ρ = 0.9974), but FreeSurfer yielded systematically lower values (mean FreeSurfer-minus-FSL bias, −3.02 mL; 95% limits of agreement, −4.52 to −1.53 mL; geometric mean FreeSurfer/FSL ratio, 0.844). Lin’s concordance coefficient and the absolute agreement ICC were both 0.9598. Calibration was strong but workflow-specific: FSL/FAST–ALVIN volume = 2.611 + 1.0210 × FreeSurfer volume (R2 = 0.9955; optimism-corrected RMSE = 0.732 mL). Conclusions. FreeSurfer and visually quality-controlled FSL/FAST–ALVIN preserved participant ranking extremely well but were not directly interchangeable as absolute measurements. Cross-workflow comparisons require explicit method reporting, formal agreement analysis, and calibration to the intended measurement scale; the equation should not be used as a universal conversion formula outside comparable acquisition, segmentation, QC and software settings. Full article

Bipolar junction transistor (BJT)-based 2D temperature-sensor arrays are factory-calibrated to ±0.1 °C, but post-deployment thermal and mechanical stresses drift their per-sensor gain–offset parameters by an order of magnitude, and in-lab recalibration is impractical. We present RASC (Region-Aware Self-Calibration), a five-stage algorithm that decomposes the global ill-posed problem into local cluster-level problems, runs robust alternating estimation (trimmed-mean field reconstruction + Huber iteratively reweighted least squares (IRLS)) inside each cluster, and reconciles overlapping estimates by linear consensus on the cluster-overlap graph with provable exponential convergence. On 7632 frames from a deployed 16 × 16 array exhibiting ≈5× factory-spec non-uniformity, RASC cuts the locally non-smooth fixed-pattern residual by 71 ± 5% (10-fold cross-validation (CV)), reducing this residual to a level comparable to the ±0.1 °C factory specification (as assessed by local-smoothness residual metrics, not independent absolute-temperature validation) while perturbing the calibrated field by only 0.041 °C RMSE; reduction concentrates at the edges (78% vs. 55% interior). In simulations on 8 × 8 to 32 × 32 arrays, RASC matches an oracle centralised extended Kalman filter (EKF) within 0.10 °C with ≈4× lower bandwidth. The real-data evaluation is a single-deployment proof of concept on one array and one host PCB; broader, longitudinal validation remains future work. Full article

Urban planners need scalable ways to monitor pedestrian conditions across heterogeneous cities, but conventional Level-of-Service (LOS) methods are often locally calibrated and difficult to transfer. This study proposes a city-adaptive framework for pedestrian LOS mapping using spatio-temporal graph models and few-shot transfer learning. Pedestrian count data from Melbourne, Dublin, and Zurich were converted into six ordinal LOS classes using city-specific percentile thresholds computed from the training data, yielding a relative congestion measure rather than an absolute cross-city standard. We developed a spatio-temporal graph transformer with an ordinal prediction head and evaluated it under in-domain, zero-shot, few-shot, and domain-adaptive settings. The results show strong in-domain performance in Melbourne (accuracy 79.7%; Acc ± 1 99.1%) and effective adaptation to the city-adaptive ordinal classification task. Few-shot fine-tuning with only 5% labeled target city data recovered 95–99% of in-domain performance, suggesting that small amounts of local supervision can substantially reduce calibration requirements in data-scarce environments. KernelSHAP analysis indicates that short-term temporal lag features dominate predictions across cities, whereas spatial and contextual features vary more strongly with local urban structure. The findings suggest that few-shot transfer learning can support pedestrian LOS estimation in cities with limited labeled data; however, the proposed LOS formulation should be interpreted as a city-specific relative indicator rather than an absolute measure of pedestrian comfort, crowding, or service quality. While the framework was evaluated across three cities, additional validation in diverse urban contexts and against perceptual measures of pedestrian experience remains necessary. Overall, the study contributes a city-adaptive framework for transferable relative LOS prediction rather than a universal cross-city LOS standard. Full article

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

To address the limitations of the traditional cross-scanning method in absolute calibration of weather radars using metal spheres, including insufficient spatial coverage, limited target acquisition efficiency, and echo underestimation in inter-range bins, this study proposes a sector scanning field calibration method. In this approach, standard metal spheres are suspended from UAVs, and a three-dimensional scanning volume around their theoretical positions is constructed to enable high-density echo sampling. By applying drive backlash correction, quadratic Gaussian surface fitting, and three-dimensional ellipsoid model inversion, key radar parameters can be retrieved. Experimental results show that the improved sector scanning method enhances automation, accuracy, and robustness in field environments and minor target drifts. The experiments were conducted under low-wind and low-clutter conditions. The average calibration error of antenna pointing is 0.08°, the average error of echo intensity calibration is 0.3 dB, the average beamwidth error is 0.07°, the range resolution is 6.6 m, and the average radial ranging error is 14 m. These results indicate that the proposed method can meet the main calibration requirements of weather radars in the present experiments. Full article

In high-stakes settings, the most consequential failure of a language model is not a wrong answer but an answer it was not entitled to give. Existing retrieval-augmented generation (RAG) pipelines retrieve context, generate text, and perhaps add citations, but they do not decide whether the evidence justifies answering, how uncertain the answer is, or at what level the system should intervene. We argue that LLMs should not only generate answers; they should be embedded inside a selective decision architecture that jointly estimates answerability, quantifies uncertainty, verifies structural validity, and chooses among direct response, escalation, abstention, or failure. We introduce BRAG (Bayesian Retrieval-Augmented Generation), a framework that operationalises this shift from answer generation to evidence-governed decision support. BRAG estimates an answerability posterior, decomposes uncertainty into epistemic and aleatoric components, and applies a structural validity gate prior to answer emission. Evaluation is conducted using controlled Monte Carlo simulation (n = 2400 queries) and a calibrated statistical pilot (N = 500), both parametric models of the pipeline’s output distribution, together with a governed operational validation that executes the full released pipeline end-to-end on independently generated MIMIC-IV-schema records (N = 100; not credentialed patient records), expert adjudication on a stratified subset (N = 200), and secondary transfer experiments on SEC EDGAR and CUAD. In simulation, BRAG reduces hallucination from 0.257 to 0.016 (93.8%) and achieves the highest coverage-adjusted utility (0.632) among five systems. In the synthetic MIMIC-IV-schema pilot, hallucination decreases from 0.292 to 0.020 (93.2%), with utility 0.538 at 89.6% coverage and an answerability AUROC of 0.692, which is moderate in absolute terms and is therefore positioned as a routing signal that operates jointly with the deterministic validity gate rather than as a stand-alone clinical classifier. Expert adjudication yields substantial agreement (Cohen’s κ = 0.778) and 93.5% concordance with BRAG decisions. Cross-domain transfer demonstrates 96–97% hallucination reduction without retriever modification, while ablation identifies the structural validity gate as the primary safety mechanism and the answerability posterior as the primary coverage and routing-precision mechanism. These results show that combining answerability estimation with structural validity enforcement can substantially reduce unsupported outputs. All findings are methodological rather than clinical: every evaluation tier uses synthetic or schema-conformant data, and validation on credentialed de-identified patient records remains necessary before any clinical deployment. Full article

Objectives: Cone-beam computed tomography (CBCT) is central to three-dimensional assessment in oral surgery and implant dentistry; however, CBCT-derived gray values expressed as HU-like units are not equivalent to true CT-derived Hounsfield Units (HU). This brief methodological secondary analysis evaluated the reliability and practical limitations of such values in assessing radiographic changes after peri-implantitis surgery. Methods: The analysis used the imaging protocol and group-level radiological data from a previously published prospective clinical cohort, conducted under the same protocol and ethical approval of the Institutional Ethics Committee of the Medical University of Lublin (KE-0254/248/11/2023; 23 November 2023). The source cohort included 57 patients treated after implant removal for severe peri-implantitis with small-particle dentin (n = 22), Bio-Oss (n = 15), or spontaneous healing without grafting (n = 20). CBCT scans were analyzed in OnDemand3D (version 1.0.11.1007) using manually selected square regions of interest (ROI; 30 × 30 pixels). No external phantom calibration, cross-device normalization, or formal intra-/inter-observer reproducibility assessment was available in the secondary dataset. Results: The previously reported mean study-site values were 779.62 ± 325.92 gray-value units for small-particle dentin, 910.51 ± 155.03 gray-value units for Bio-Oss, and 206.04 ± 174.21 gray-value units for controls. These findings are presented as protocol-dependent attenuation patterns, not as direct material rankings, bone-density thresholds, or proof of regeneration. Variability remained substantial, with study-site coefficients of variation of 41.8%, 17.0%, and 84.6%, respectively, and high adjacent-site variability. Interpretation was constrained by manual ROI placement, lack of calibration, absence of observer-agreement metrics, unequal follow-up timing, and CBCT sensitivity to scatter, beam hardening, field of view, reconstruction settings, and metal-related artifacts. Conclusions: CBCT-derived gray values may be useful as relative indicators of local radiographic attenuation change within a standardized protocol, but they should not be interpreted as absolute measures of bone density. Future regenerative oral surgery studies should combine standardized acquisition, explicit ROI methodology, repeated measurements, observer-agreement analysis, and complementary clinical, radiographic, or histological outcomes. Full article

The gap dimension of a railway switch machine is a critical physical quantity for determining the locking status of railway turnouts. Under operating conditions characterized by heavy oil contamination, complex illumination, and equipment vibration, existing visual measurement methods often struggle to maintain stability and achieve sub-pixel precision. To address this issue, this paper proposes a gap measurement method based on the fusion of vision and geometric features (G-VFM). The method first utilizes a confidence-aware optimized YOLOv8 model to achieve robust localization of the gap region. Subsequently, an improved multi-channel U-Net is employed to extract soft-edge probability maps, based on which a 20-dimensional structured geometric descriptor is constructed. Finally, visual semantic features and geometric priors are fused for regression through an R34-Fusion two-stream residual network, and systematic errors are corrected using a weighted Huber loss combined with a piecewise linear calibration strategy. Test results on a constructed field dataset show that the proposed method achieves a Mean Absolute Error (MAE) of 0.0076 mm and a maximum error of 0.0193 mm. It achieves a 100% pass rate under an industrial tolerance of 0.02 mm, with an end-to-end inference time of 52.23 ms (~19.15 FPS), balancing both precision and efficiency. Further tests on illumination degradation, noise interference, and cross-batch evaluations indicate that the method maintains relatively stable performance across various complex scenarios. However, performance decreases significantly under extremely low-light conditions, suggesting that actual deployment may require integration with active lighting or multi-sensor fusion to ensure system reliability across all working conditions. Overall, this method achieves high-precision gap measurement under current experimental conditions and provides a feasible solution for vision-based switch machine status monitoring. Full article

Impinging injectors are extensively utilized in liquid rocket engines, characterized by a large number of paired inclined injection orifices. The diameter and axis alignment deviation of these orifices directly influence propellant flow distribution, atomization and mixing behavior, and engine operational stability. To address the challenges associated with micro-sized orifices, inclined axes, large quantities, spatial intersection, and the low detection efficiency of conventional approaches, this paper proposes a dual-line laser 3D point cloud reconstruction-based method for measuring the diameter and impact alignment deviation of injector orifices. A dual-line laser measurement system is established to capture surface point clouds on both sides of the orifice inlets. Through system calibration and point cloud registration, the 3D point cloud data of the injector orifices within a unified coordinate system are reconstructed. Cross-sectional mapping, boundary extraction, and geometric fitting techniques are applied to determine the diameter and axis parameters of the orifices, and the spatial alignment deviation of paired orifices is subsequently calculated. To validate the feasibility of the proposed method, experimental investigation is conducted on test specimens with both 8 pairs of Φ2 mm through-holes and Φ0.5 mm micro-orifices. For the Φ2 mm specimen, the diameter measurement results are compared with industrial computed tomography (CT) data, while the alignment deviation results are verified using a combination of pin gauges and coordinate measuring machine (CMM) measurements. For the Φ0.5 mm micro-orifices, both diameter and alignment deviation results are verified using a 3D coaxial line confocal sensor. After system calibration, the fitting residuals of three Φ8 mm standard spheres are all maintained within 0.08 mm. The diameter measurement results of 8 selected Φ2 mm orifices show good overall agreement with industrial CT data: the maximum absolute deviation is 22 μm, the average absolute deviation is 15 μm, the maximum relative error is 1.09%, and the average relative error is 0.74%. The diameter and alignment deviation results of Φ0.5 mm micro-orifices show good consistency with the 3D coaxial line confocal sensor: the maximum absolute deviation is 13 μm for diameter and 0.047° for alignment deviation, with maximum relative errors of 2.41% and 0.058%, respectively. The alignment deviation results of 8 pairs of Φ2 mm orifices indicate that the proposed dual-line laser method is generally consistent with the combined pin gauge and CMM approach: the maximum absolute deviation is 0.170°, the average absolute deviation is 0.125%, the maximum relative error is 0.284%, and the average relative error is 0.125%. The results demonstrate that the proposed method enables non-contact and high-efficiency measurement of the diameter and alignment angle of injector orifices in impinging injectors for both conventional Φ2 mm orifices and micro Φ0.5 mm orifices, with high measurement accuracy and promising engineering application potential, thereby providing a new technical approach for the geometric parameter inspection of multi-scale micro-injection orifices. Full article

Objectives: The aim of this study was to compare a widely applied table-top digital non-mydriatic camera (Topcon TRC-NW-8) with a handheld digital non-mydriatic camera (Optomed Aurora IQ) regarding the quantitative assessment of the retinal microcirculation using established biomarkers: central retinal arteriolar equivalent (CRAE), central retinal venular equivalent (CRVE) and arterio-venous ratio (AVR). Methods: The present cross-sectional study included 26 randomly selected participants (51 eyes) who underwent retinal imaging of both eyes with the two devices and were analyzed using a static retinal vessel analyzer. Results: The mean differences in CRAE, CRVE and AVR between the two devices (Topcon/Aurora) were 24.96 ± 11.7, 22.7 ± 11.7 and 0.026 ± 0.045, respectively. Strong correlations were observed between devices (r = 0.84 for CRAE, 0.75 for CRVE and 0.83 for AVR; all p < 0.001), with high agreement as indicated by ICC values (0.91, 0.85, and 0.90, respectively). Bland–Altman plots indicated evidence of systemic bias (95% within 2 SD) with no proportional bias, as the differences were consistently distributed across the range of average values. Regression-based equations were derived to approximate the transformation of measurements between devices. Conclusions: The handheld fundus camera demonstrates strong correlation and good relative agreement with the table-top device; however, a consistent device-dependent bias limits the direct interchangeability of absolute measurements. The derived transformation equations may facilitate approximate cross-device comparison, although external validation is required. These findings support the complementary use of handheld devices and highlight the need for calibration strategies when integrating measurements across platforms. Full article

Wind resource assessment (WRA) in densely forested and complex terrain remains challenging due to strong canopy-induced turbulence and enhanced wind shear, which significantly affect wind flow characteristics and increase modeling uncertainties. Methods relying on Plant Area Density (PAD) or Leaf Area Density (LAD) estimation require costly airborne surveys and site-specific calibration, limiting their industrial applicability. Based on a scientific collaboration between Meteodyn and EDF Power, this study proposes a complete and reproducible Computational Fluid Dynamics (CFD) methodology built around an Iterative Model Adjustment (IMA) procedure implemented in Meteodyn WT™ to improve wind resource assessment accuracy in highly forested areas using standard industrial inputs. The IMA procedure iteratively calibrates the canopy drag coefficient and forest model parameters using wind speed profile measurements from a single reference mast until the simulated wind shear matches observations. The methodology was evaluated at three sites located in Finland, France, and Scotland, yielding six calibration and cross-prediction cases under heterogeneous forest and complex terrain conditions. Cross-prediction uncertainties were reduced significantly, with horizontal mean speed errors decreasing from the range [1.0–9.5%] to [0.5–2.2%] and a global mean absolute error of approximately 1.1%. The study provides new physical insight into the sensitivity of the canopy drag force term within RANS-based forest models, showing that both drag coefficient and canopy height have a comparable and jointly necessary influence on wind shear simulation. These findings demonstrate that robust and accurate wind resource assessment can be achieved in complex terrain and forested areas without relying on remote-sensing-derived canopy density datasets, providing a pragmatic and industrially scalable alternative. Full article

High-frequency (HF) skywave propagation exploits ionospheric reflection for beyond-line-of-sight transmission, making time-difference-of-arrival (TDOA)-based geolocation a primary technique for localizing non-cooperative HF emitters. However, reliable TDOA estimation remains challenging due to time-varying ionospheric conditions, wideband multipath dispersion, and low signal-to-noise ratio (SNR). This paper proposes an integrated framework coupling realistic channel synthesis, deep learning-based TDOA estimation, and convex optimization-based localization. Three contributions are made. First, an improved wideband ionospheric channel model is constructed by integrating the International Reference Ionosphere (IRI) with region-specific calibration and a stochastic perturbation module, yielding time-varying multipath responses for physics-consistent waveform generation. Second, a convolutional neural network (CNN)-based TDOA estimator is designed to jointly exploit time-domain complex-baseband in-phase/quadrature (I/Q) waveforms, multi-weight generalized cross-correlation (GCC) feature maps, and channel-state information (CSI) within a unified regression network, achieving robust delay estimation under severe noise and multipath conditions. Third, the geolocation problem is formulated as a bias-regularized constrained least-squares problem with unknown ionospheric excess-delay surrogates, and a semidefinite programming (SDP) relaxation is derived to yield a tractable solution without prescribing a fixed virtual reflection height. Simulations show that the proposed estimator consistently outperforms competing algorithms across a wide SNR range and narrows the gap to the Cramér–Rao lower bound (CRLB) at high SNR. On field-recorded signals, the estimator reduces the mean absolute TDOA deviation by 51% relative to GCC with phase transform (GCC-PHAT), and the end-to-end pipeline achieves a mean geolocation error of 19.67 km across 100 field segments, outperforming all compared baselines. Full article

Backgrounds/Objectives: Non-small cell lung cancer (NSCLC) exhibits substantial prognostic heterogeneity that is not fully captured by conventional anatomical staging, highlighting the need for individualized risk assessment. Radiomics enables non-invasive characterization of tumor phenotype, yet high dimensionality and inter-feature correlations often limit model stability and interpretability. Methods: To address these challenges, we developed a multimodal late-fusion framework integrating radiomic, clinical, and demographic information to predict patient-specific absolute risk in the Lung1 cohort (N = 398). Radomic features (N = 107) were extracted from primary tumor volumes and refined using a Group Lasso–penalized Cox model, preserving biological coherence and producing a parsimonious imaging signature. This signature was combined with clinical and demographic variables using five different late-fusion strategies: weighted averaging, Cox regression, logistic stacking, Random Survival Forests (RSF), and XGBoost. Model performance was evaluated using 5-fold cross-validation based on discrimination, calibration, and risk stratification metrics. Results: Using 5-fold cross validation, the radiomics-only model outperformed conventional clinical staging in patients’ risk prediction (C-index 0.5717 vs. 0.5350) and accuracy, demonstrating the prognostic value of imaging biomarkers. All fusion strategies improved risk prediction performance, with the Cox fusion model slightly better than other fusion methods with C-index of 0.58, time-dependent AUC of 0.60, and the distinct risk stratification with log-rank χ² of 22.85. Conclusions: These findings suggest that multimodal late fusion may provide robust and interpretable risk estimates with potential clinical relevance, supporting personalized risk prediction for informed decision-making in NSCLC. Full article