Search Results (1,632)

A receipt information extraction task requires both textual and spatial analyses. Early receipt analysis systems primarily relied on template matching to extract data from spatially structured documents. However, these methods lack generalizability across various document layouts and require defining the specific spatial characteristics of unseen document sources. The advent of convolutional and recurrent neural networks has led to models that generalize better over unseen document layouts, and more recently, multi-modal transformer-based models, which consider a combination of text, visual, and layout inputs, have led to an even more significant boost in document-understanding capabilities. This work focuses on the joint use of a neural multi-modal transformer and a rule-based model and studies whether this combination achieves higher performance levels than the transformer on its own. A comprehensively annotated dataset, comprising real-world and synthetic receipts, was specifically developed for this study. The open source optical character recognition model DocTR was used to textually scan receipts and, together with an image, provided input to the classifier model. The open-source pre-trained LayoutLMv3 transformer-based model was augmented with a classifier model head, which was trained for classifying textual data into 12 predefined labels, such as date, price, and shop name. The methods implemented in the rule-based model were manually designed and consisted of four types: pattern-matching rules based on regular expressions and logic, database search-based methods for named entities, spatial pattern discovery guided by statistical metrics, and error correcting mechanisms based on confidence scores and local distance metrics. Following hyperparameter tuning of the classifier head and the integration of a rule-based model, the system achieved an overall F1 score of 0.98 in classifying textual data, including line items, from receipts. Full article

The synthesis, crystal structure, phase transformations, and thermal expansion of (Y_1−xEu_x)₂(SO₄)₃*8H₂O (where x = 0, 0.17, 0.33, 0.50, 0.66, 0.83, and 1) are presented. (Y_1−xEu_x)₂(SO₄)₃*8H₂O solid solutions were synthesized via crystallization from an aqueous solution. (Y_1−xEu_x)₂(SO₄)₃*8H₂O (C2/c) ↔ (Y_1−xEu_x)₂(SO₄)₃ (Pbcn) → (Y_1−xEu_x)₂O₂SO₄ (C2/c) and Eu₂(SO₄)₃*8H₂O (C2/c) ↔ Eu₂(SO₄)₃ (C2/c) → Eu₂O₂SO₄ (C2/c) phase transformations for all samples were investigated by high-temperature powder X-ray diffraction, differential scanning calorimetry and thermogravimetry in the temperature ranges of 25–750 and 25–1350 °C, respectively. The aim of this work is to identify the structural heredity of the phases formed during thermal transformations of (Y_1−xEu_x)₂(SO₄)₃*8H₂O solid solutions, and to study the mechanisms of the thermal deformations of the crystal structure. Structural relations between these phases were found. The crystal structures of YEu(SO₄)₃*8H₂O and (Y_0.83Eu_0.17)₂(SO₄)₃*8H₂O were refined at −173, −123, −73, −23, 27, and 77 °C. Thermal expansion coefficients for (Y_1−xEu_x)₂(SO₄)₃*8H₂O, Eu₂(SO₄)₃, (Y_1−xEu_x)₂O₂SO₄ (where x = 0, 0.17, 0.33, 0.50, 0.66, 0.83, and 1) compounds and solid solutions were calculated for the first time. The thermal expansion of Eu₂(SO₄)₃ was highest in the direction approximately coinciding with the c-axis, because the Eu–O chains extended in this direction. As temperature increased, the crystal structure of (Y_1−xEu_x)₂(SO₄)₃*8H₂O expanded significantly in the ac plane along directions close to the a and c axes, while thermal expansion along the b axis was relatively low. The distance between layers in the (Y_1−xEu_x)₂(SO₄)₃*8H₂O crystal structure increased with increasing temperature, and corrugated layers (parallel to (101) direction) straightened out due to the rotation of the S₂O₄ tetrahedra. At high temperature, thermal expansion of Y₂O₂SO₄ was highest along the longer diagonal of the ac parallelogram perpendicular to the plane of the oxo-centered ${\displaystyle \frac{2}{\infty }}$[YO] layers. Full article

Molten salt, as a phase change heat storage material, can be used to mitigate the volatility of clean energy. Increasing the specific heat of molten salts can help to increase heat storage density and reduce costs. In this study, nanoparticles with different potentials were prepared and doped into Solar Salt (NaNO₃-KNO₃). The modification results of the nanoparticles were evaluated by transmission electron microscopy, energy dispersive X-ray spectroscopy and infrared spectroscopy, and the modification process was analyzed by density functional theory. The specific heat, thermal diffusion coefficient, melting point, latent heat of the composites and their variation mechanism were analyzed using synchronized thermal analyzer, laser flash analyzer and scanning electron microscope. It was found that acidification was able to modify the SiO₂ nanoparticles and that the higher the acidity, the more the negative charge of the nanoparticles was neutralised. A 25.8% decrease in zeta potential to −23.17 mV was observed for the nano-SiO₂ after treatment with HCl at pH 1, compared to the non-acidified sample. The microelectric field generated by the charged nanoparticles affects the thermophysical properties such as the specific heat of the molten salt-nanoparticle composites, with one of the samples having the largest specific heat (1.79 J/(g·K)) and thermal diffusion coefficient (0.94 mm²/s), which were increased by 13.3% and 14.6%, respectively, compared to the Solar Salt. This study attributes the alterations in thermophysical properties to the variation in ion separation distance induced by the charge on nanoparticles. Full article

This study presents a terrestrial-laser-scanning-based scan-to-BIM workflow that transforms point cloud data into a BIM-based digital twin and analyzes how data collected with LiDAR (Light Detection and Ranging) can be converted into an information-rich model using Autodesk ReCap and Revit. Point clouds provided by laser scanning were processed in the ReCap environment and imported into Revit in an application that took place within an industrial facility of approximately 240 m² in Izmir. The scans were registered and pre-processed in Autodesk ReCap 2022 and modeled in Autodesk Revit 2022, with visualization updates prepared in Autodesk Revit 2023. Geometric quality was evaluated using point-to-model distance checks, since the dataset was imported in a pre-registered form and ReCap did not provide station-level RMSE values. The findings indicate that the ReCap–Revit integration offers high geometric accuracy and visual detail for both building elements and production-line machinery, but that high data density and complex geometry limit processing performance and interactivity. The study highlights both the practical applicability and the current technical limitations of terrestrial-laser-scanning-based scan-to-BIM workflows in an industrial context, offering a replicable reference model for future digital twin implementations in Turkey. Full article

In advanced manufacturing, accurate and reliable 3D geometry measurement is vital for the quality control of large-sized components with multiple small key local features. To obtain both the geometric form and spatial position of these local features, a hybrid robot-assisted laser scanning strategy is introduced, combining a laser tracker, a fringe-projection 3D scanner, and a mobile robotic unit that integrates an industrial robot with an Automated Guided Vehicle. As for improving the overall measurement accuracy, we propose an accuracy-enhanced calibration method that incorporates both error control and compensation strategies. Firstly, an accurate extrinsic parameter calibration method is proposed, which integrates robust target sphere center estimation with distance-constrained-based optimization of local common point coordinates. Subsequently, to construct a high-accuracy, large-scale spatial measurement field, an improved global calibration method is proposed, incorporating coordinate optimization and a hierarchical strategy for error control. Finally, a robot-assisted laser scanning hybrid measurement system is developed, followed by calibration and validation experiments to verify its performance. Experiments verify its high precision over 14 m (maximum error: 0.117 mm; mean: 0.112 mm) and its strong applicability in large-scale scanning of key geometric features, providing reliable data for quality manufacturing of large-scale components. Full article

Terrestrial laser scanning (TLS) point clouds require high-precision registration and georeferencing to be used effectively. Only then can data from multiple stations be integrated and transformed from the instrument’s local coordinate system into a common, stable reference frame that ensures temporal consistency for further analyses of displacement and deformation. The article demonstrates the validation of an innovative referencing system devised to improve the reliability and accuracy of registering and georeferencing TLS point clouds. The primary component of the system is openable reference spheres, whose centroids can be directly and precisely determined using surveying methods. It also includes dedicated adapters: tripods and adjustable F-clamps with which the spheres can be securely mounted on various structural components, facilitating the optimal distribution of the reference markers. Laboratory tests with four modern laser scanners (Z+F Imager 5010C, Riegl VZ-400, Leica ScanStation P40, and Trimble TX8) revealed sub-millimetre accuracy of sphere fit and form errors, along with the sphere distance error within the acceptance threshold. This confirms that there are no significant systematic errors and that the system is fully compatible with various TLS technologies. The registration and georeferencing quality parameters demonstrate the system’s stability and repeatability. They were additionally verified with independent control points and geodetic levelling of the centres of the spheres. The system overcomes the critical limitations of traditional reference spheres because their centres can be measured directly using surveying methods. This facilitates registration and georeferencing accuracy on par with, or even better than, that of commercial targets. The proposed system serves as a stable and repeatable reference frame suitable for high-precision engineering applications, deformation monitoring, and longitudinal analyses. Full article

Metal additive manufacturing (AM) offers promising advancements in producing implants with complex geometry for biomedical applications, where accuracy and near-net-shape production are essential. Metal AM by laser powder bed fusion (PBF-LB) is a promising route to produce biodegradable iron implants made of complex lattice structures. However, processing windows for pure iron remain poorly defined. This work focuses on optimizing PBF-LB parameters for pure iron using a design of experiments (DoE) approach on bulk samples of different geometries to evaluate different parameters. Hatch laser power, scanning speed, hatch distance and point distance were varied and their effect on porosity, surface roughness and dimensional accuracy was evaluated. This was followed by the fabrication of rhombitruncated cuboctahedron (RTCO) lattice structures with the best parameters previously defined for the bulk samples. The best parameter set (hatch laser power 180 W, scanning speed 600 mm/s, hatch distance 110 µm and point distance 12 µm, corresponding to a volumetric energy density of 90.9 J/mm³) produced bulk samples with a porosity as low as 0.07% (99.93% density) measured in polished sections. Using these parameters, RTCO lattices with designed relative densities of 10.28%, 35.29% and 65.16% were successfully manufactured with small geometric deviations and good control of strut thickness and relative density. The results of this study define a robust PBF-LB processing window for pure iron and demonstrate the feasibility of producing geometrically controlled, biodegradable iron lattice structures suitable for future load-bearing biomedical applications. Full article

The problem of poor coupling and wheel breakage is a critical issue in the rapid inspection of rails using contact piezoelectric ultrasonic technology for trolleys and vehicles. To overcome this shortcoming, a non-contact unidirectional Shear Vertical Wave EMAT (USV-EMAT) for rapid rail flaw detection with a larger emission angle is proposed and optimized. First, the core characteristics of the USV-EMAT and the Unidirectional Line-Focusing Shear Vertical Wave EMAT (ULSV-EMAT) are compared and analyzed, including emission angle, directivity, intensity, and detection scan distance. The results confirmed that the USV-EMAT is more suitable for rapid rail flaw detection. Secondly, the orthogonal experimental analysis method was used to optimize the structural parameters of the probe. This study systematically identified the key factors influencing the directivity and intensity of acoustic waves excited by the probe, as well as the detection blind zones. Finally, the structural parameters of the integrated 37° USV-EMAT probe were determined by comparing and analyzing the received signal characteristics of the transmit–receive racetrack coil and the self-transmitting–receiving meander coil. The results show that the optimized probe achieves a 14.3 dB SNR for detecting a 5 mm diameter, 50 mm deep transverse hole in the rail, and a 14.0 dB SNR for a 3 mm diameter, 25 mm long, 50 mm deep flat-bottomed hole. Additionally, this study reveals that as the burial depth of the transverse holes increases, the detection scan distance for such defects exhibits an “N”-shaped trend, with the minimum occurring at a depth of 90 mm. Full article

Generative adversarial networks (GANs) typically require large datasets for effective training, which poses challenges for volumetric medical imaging tasks where data are scarce. This study addresses this limitation by extending adaptive discriminator augmentation (ADA) for three-dimensional (3D) StyleGAN2 to improve generative performance on limited volumetric data. The proposed 3D StyleGAN2-ADA redefines all 2D operations for volumetric processing and incorporates the full set of original augmentation techniques. Experiments are conducted on the NoduleMNIST3D dataset of lung CT scans containing 590 voxel-based samples across two classes. Two augmentation pipelines are evaluated—one using color-based transformations and another employing a comprehensive set of 3D augmentations including geometric, filtering, and corruption augmentations. Performance is compared against the same network and dataset without any augmentations at all by assessing generation quality with Kernel Inception Distance (KID) and 3D Structural Similarity Index Measure (SSIM). Results show that volumetric ADA substantially improves training stability and reduces the risk of a mode collapse, even under severe data constraints. A strong augmentation strategy improves the realism of generated 3D samples and better preserves anatomical structures relative to those without data augmentation. These findings demonstrate that adaptive 3D augmentations effectively enable high-quality synthetic medical image generation from extremely limited volumetric datasets. The source code and the weights of the networks are available in the GitHub repository. Full article

Background: Precise delineation of the rectum is crucial in treatment planning for cancers in the pelvic region, such as prostate and cervical cancers. Manual segmentation is also still time-consuming and suffers from inter-observer variability. Since there are meaningful differences in rectal anatomy between males and females, incorporating sex-specific anatomical patterns can be used to enhance the performance of segmentations. Furthermore, recent deep learning advancements have provided promising solutions for automatically classifying patient sex from CT scans and leveraging this information for enhancing the accuracy of rectal segmentation. However, their clinical utility requires comprehensive validation against real-world standards. Methods: In this study, a two-stage deep learning pipeline was developed using CT scans from 186 patients with either prostate or cervical cancer. First, a CNN model automatically classified the patient’s biological sex from CT images in order to capture anatomical variations dependent on sex. Second, a sex-aware U-Net model performed automated rectal segmentation, allowing the network to adjust its feature representation based on the anatomical differences identified in stage one. The internal validation had an 80/20 train–test split, and 15% of the training portion was held out for validation to ensure balanced distribution regarding sex and diagnosis. Model performance was evaluated using spatial similarity metrics, including the Dice Similarity Coefficient (DSC), Hausdorff Distance, and Average Surface Distance. Additionally, a radiation oncologist conducted a retrospective clinical evaluation using a 3-point Likert scale. Statistical significance was examined using Wilcoxon signed-rank tests, Welch’s t-tests, and Mann–Whitney U test. Results: The sex-classification model attained an accuracy of 94.6% (AUC = 0.98, 95% CI: 0.96–0.99). Incorporation of predicted sex into the segmentation pipeline improved anatomical consistency of U-Net outputs. Mean DSC values were 0.91 (95% CI: 0.89–0.92) for prostate cases and 0.89 (95% CI: 0.87–0.91) for cervical cases, with no significant difference between groups (p = 0.12). Surface distance metrics calculated on resampled isotropic voxels showed mean HD values of 3.4 ± 0.8 mm and ASD of 1.2 ± 0.3 mm, consistent with clinically acceptable accuracy. On clinical evaluation, 89.2% of contours were rated as excellent, while 9.1% required only minor adjustments. Automated segmentation reduced the average contouring time from 12.7 ± 2.3 min manually to 4.3 ± 0.9 min. Conclusions: The proposed sex-aware deep learning framework offers accurate, robust segmentation of the rectum in pelvic CT imaging by explicitly modeling sex-specific differences in anatomical characteristics. This physiologically informed approach enhances segmentation performance and supports reliable integration of AI-based delineation into radiotherapy workflows to improve both contouring efficiency and clinical consistency. Full article

To examine travel distance and its impact on wait time for positron emission tomography–computed tomography (PET/CT) in patients with lung and prostate cancers and lymphoma in Alberta. We used the Alberta cancer registry and diagnostic imaging database to identify patients with lung and prostate cancers and lymphoma who had a PET/CT scan during April 2017 and March 2023. The Alberta Facilities Distance/Time Look Up Table was used to calculate travel distance from the patient’s residence to the PET/CT facility. Negative binomial regression was used to assess the association between travel distance and wait time for PET/CT. The study included 9503 patients. Lung cancer accounted for 43.4% of the patients, followed by lymphoma (37.1%) and prostate (19.5%) cancer. There were more female patients with lung cancer (55.5%) than lymphoma (42.9%; p < 0.001). The mean (SD) age was 66.8 (13.8) years and lymphoma patients were younger (59.6 years) than lung (70.3 years; p < 0.001) or prostate (72.7 years; p < 0.001) cancer patients. Diabetes (14.2%) was the most prevalent comorbidity. The median (IQR) travel distance was 21 (12–121) km and this was shorter for urban (16 km) than rural (148 km; p < 0.001) patients, but the wait time was similar (median = 20 vs. 21 days; p = 0.378). There were no significant associations between travel distance and wait time (IRR = 1.00; p = 0.108). The results were robust in subgroup analyses by type of cancer and scan priority. There were no associations between travel distance and wait time for PET/CT. Additional research is warranted to examine the potential impact of longer travel distances on overall access to care and patient outcomes. Full article

Background/Objectives: The cavernous segment of the internal carotid artery (ICA) is a critical neurovascular structure with complex cranial nerve relationships. Understanding its morphometric variability is essential for safe microsurgical and endovascular procedures. This study aimed to characterize the morphometry of the cavernous ICA using Magnetic resonance imaging (MRI) and assess associations with demographic variables. Methods: A retrospective observational study was conducted on 135 MRI scans of adult patients, distributed among 79 women and 56 men with an average age of 50.8 years, without cerebrovascular pathology, performed between March 2023 and January 2025. The diameters of the left and right cavernous ICA and the intercarotid distance were measured using RadiAnt DICOM Viewer. Statistical analyses included descriptive statistics, t-tests, correlations, and multivariate regression models adjusted for age and sex. Principal component and cluster analyses were applied to identify morphometric patterns. Results: The mean left and right ICA diameters were both 5.09 ± 0.65 mm, with a mean intercarotid distance of 17.4 ± 4.22 mm. No age-related associations were found (p > 0.05). Male patients showed significantly larger right ICA diameters (p = 0.008). Bilateral symmetry was confirmed (p > 0.05). Two morphometric clusters were identified: Morphotype 1 (larger ICA caliber and narrower spacing) and Morphotype 2 (smaller caliber and wider spacing), showing a significant sex distribution difference (p = 0.012). Conclusions: The cavernous ICA demonstrates stable bilateral symmetry with minor sex-dependent differences. Morphometric characterization supports safer planning of transsphenoidal, endovascular, and skull-base surgeries by reducing the risk of iatrogenic neurovascular injury. Full article

This study presents the development and validation of an in situ monitoring method for the laser direct energy deposition (DED) process, utilizing an integrated optical camera (720 HD, 60 fps) to analyze melt pool imagery. The approach is grounded in an experimental framework employing Taguchi orthogonal arrays, which ensures a stable dataset by controlling process variability and enabling reliable extraction of relevant features. The monitoring system focuses on analyzing brightness distribution regions within the melt pool image, identified as specific clusters that reflect external process conditions. The method emphasizes precise segmentation of the melt pool area, combined with automatic detection and classification of cluster features associated with key process parameters—such as focus distance, the number of deposited layers, powder feed rate, and scanning speed. The main contribution of this work is demonstrating the effectiveness of using an optical camera for DED monitoring, based on an algorithm that processes a set of melt pool identification features through computer vision and machine learning techniques, including Random Forest and HistGradient Boosting, achieving classification accuracies exceeding 95%. By continuously tracking the evolution of these features within a closed-loop control system, the process can be maintained in a stable, defect-free state, effectively preventing the formation of common process defects. Full article

Background/Objectives: Accurate intraoperative margin assessment is essential for ensuring complete tumour excision in breast-conserving surgery, minimising local recurrence, and avoiding reoperations. Ex vivo fusion confocal microscopy (EVFCM) provides real-time, high-resolution imaging of fresh, unfixed tissues that closely resembles conventional histological imaging. This study aimed to validate the diagnostic performance and clinical feasibility of EVFCM for real-time intraoperative margin assessment during breast cancer surgery. Methods: A prospective observational diagnostic validation study was conducted using 144 breast tissue specimens. The samples were stained with acridine orange and fast green and scanned using a VivaScope 2500M-G4 system. Two breast pathologists independently evaluated the EVFCM images, blinded to the conventional histology results, which served as the reference standard. The diagnostic accuracy, sensitivity, specificity, and interobserver agreement were calculated using Cohen’s κ. Results: Interobserver agreement was almost perfect for neoplasia detection (97.3%, κ = 0.942) and tumour type classification (93.8%, κ = 0.883). The EVFCM achieved 93.7% sensitivity and specificity, with 94.0% accuracy for tumour detection (κ = 0.929, p < 0.001); 95.8% accuracy for tumour type classification (κ = 0.925, p < 0.001); and 95.1% accuracy for invasive subtype identification (κ = 0.907, p < 0.001). For margin assessment, EVFCM achieved 80% sensitivity, 100% specificity, and 99.3% accuracy (κ = 0.857, p < 0.001), whereas margin distance evaluation (<2 mm vs. ≥2 mm) yielded 75% sensitivity, 100% specificity, and 98.6% accuracy (κ = 0.854, p < 0.001). Conclusions: EVFCM enables rapid, high-resolution imaging of fresh breast tissue, facilitating real-time intraoperative margin evaluation with excellent diagnostic concordance and workflow efficiency. Its integration into surgical practice could reduce re-excisions, enhance oncological safety, and improve patient outcomes in breast-conserving surgeries. Full article

Achieving efficient Coverage Path Planning (CPP) in indoor and semi-structured settings necessitates both organized area segmentation and dependable transitions between coverage zones. This research introduces an improved region-guided CPP framework that incorporates rectangular region expansion, Boustrophedon-based coverage within regions, and an obstacle-aware planner for transitioning between regions. In contrast to conventional methods that depend solely on A*-based routing, the suggested transition module utilizes a multi-weighted cost model that integrates Euclidean distance, obstacle density, and heading changes to create smoother, more context-sensitive links between regions. The approach is assessed on five representative grid maps inspired by the layouts of building corridors and greenhouse-like strip structures. Performance indicators—including intra-region coverage distance, inter-region transition cost, overall path distance, coverage ratio, and computation duration—illustrate the method’s efficiency. Experimental findings indicate consistent coverage rates ranging from 96% to 99%, with total computation times between 312 and 844 ms. When compared to traditional global Boustrophedon and spiral scanning methods, the proposed system attains noticeably shorter transition paths and enhanced navigation efficiency, particularly in narrow corridors and cluttered environments. In summary, the framework provides a modular, computationally efficient, and obstacle-aware solution that is well-suited for autonomous mobile robot coverage path planning tasks. Full article