Search Results (25,498)

Traffic accident detection and object detection have become key areas of research due to their direct impact on safety, traffic congestion mitigation, and intelligent traffic planning. This study presents a structured analysis of classical detection methods and artificial intelligence-based techniques, highlighting their methodologies, objectives, and performance results. The study categorizes existing research into threshold-based approaches, statistical approaches, image processing, rule-based approaches, and machine learning approaches, with further emphasis on predictive modeling, graph-based approaches, and optimization approaches. Considerable emphasis is placed on identifying systems that are capable of operating under adverse weather conditions such as fog, rain, and snow. These scenarios significantly affect detection accuracy. Although several authors incorporate environmental resilience into their models, most studies still evaluate performance under ideal conditions, revealing a critical gap in research. This analysis highlights the need to develop robust detection mechanisms that can adapt to real-world variability and environmental disturbances. Findings show that AI-based methods significantly outperform classical approaches in terms of adaptability and scalability, but their dependence on training data limits their performance in adverse conditions. The study concludes with recommendations for future work to prioritize multimodal sensing, generalization across weather conditions, and integration of environmental intelligence to ensure reliable real-time detection of traffic events under all operating conditions. Full article

Accurate assessment of the functional significance of coronary artery stenoses is essential for guiding revascularization decisions and improving clinical outcomes in patients with coronary artery disease (CAD). While invasive wire-based fractional flow reserve (FFR) remains the gold standard for physiological lesion assessment, its adoption in routine clinical practice is limited by procedural complexity, patient discomfort, time consumption, and cost. These limitations have driven the development of angiography-derived FFR techniques that enable physiological evaluation without pressure wires or pharmacologic hyperaemia. Recent advances in computational modelling, artificial intelligence, and image processing have facilitated the estimation of FFR from conventional coronary angiography, including approaches that require only a single angiographic view. Single-view angiography-derived FFR methods—such as Murray law-based quantitative flow ratio (µQFR), FFR2D, Angio-iFR/FFR, sAccuFFR, and X1-FFR—aim to simplify workflow while maintaining diagnostic accuracy. Among these, µQFR has demonstrated the most consistent validation against invasive FFR across a broad range of clinical scenarios, including complex lesions, severe aortic stenosis, multivessel disease, and acute coronary syndromes. This review summarizes the principles, validation data, clinical applications, and limitations of single-view angiography-derived FFR technologies and highlights their potential to expand the adoption of physiology-guided coronary intervention. Full article

Healthcare systems worldwide face increasing pressure to deliver accurate, affordable, and scalable diagnostic services while maintaining long-term sustainability. Chest X-ray screening is considered one of the most cost-effective methods for detecting lung disease. However, many deep learning approaches are computationally intensive and difficult to interpret, which limits their adoption in high-throughput, resource-constrained clinical settings. This study proposes a hybrid CNN–tree framework for automated lung disease classification from chest X-ray images, which targets COVID-19, pneumonia, tuberculosis, lung cancer, and normal cases. To ensure robustness and generalization, four publicly available chest X-ray datasets from different sources are merged into a unified five-class dataset, which introduces realistic variations in imaging conditions and patient populations. A ResNet-18 model is fine-tuned to extract domain-specific deep feature representations. Feature dimensionality and redundancy are reduced using Principal Component Analysis, while class imbalance is addressed through the Synthetic Minority Over-sampling Technique. The resulting compact feature vectors are used to train interpretable tree-based classifiers, which include Decision Tree, Random Forest, and XGBoost. Experiments conducted using five-fold stratified cross-validation demonstrate substantial and consistent performance gains. When trained on fine-tuned and preprocessed deep features, all evaluated tree-based classifiers achieve weighted F1-scores between 0.977 and 0.982 using five-fold cross-validation, with a significant reduction in inter-class confusion. In addition, the proposed framework maintains low per-sample inference latency, which supports energy-efficient and scalable deployment. These results indicate that combining deep feature learning with interpretable tree-based models provides a practical and reliable solution for sustainable chest X-ray screening in real-world clinical environments. Full article

Grain breakage occurs in sand specimens subjected to high stress levels; however, the magnitude and characteristics of the resulting deformation remain insufficiently quantified. This study investigates particle-scale fracture behavior in a standardized quartz sand subjected to controlled mechanical loading. Rapid, unconsolidated–undrained (UU) direct shear box tests were performed under normal stresses of 700, 800, and 900 kPa to induce grain breakage. The mechanical loading procedure was applied as a controlled stress induction mechanism to promote particle fragmentation rather than to determine conventional geotechnical parameters. A uniformly prepared quartz sand containing no additional mineral phases was used to ensure material consistency. Post-test specimens were examined through systematic visual and image-based analysis. The sample obtained from the 900 kPa test, where breakage was most pronounced, was analyzed in detail to characterize quartz fracture behavior under compressive and shear stress conditions using advanced image processing techniques. A deep learning-based mineral segmentation framework was developed using a ResNet50 architecture with transfer learning. A custom dataset consisting of high-resolution mineral images and corresponding pixel-level segmentation masks was constructed. The proposed model achieved 86.21% overall accuracy, a Dice coefficient of 91.35%, and an Intersection-over-Union (IoU) score of 84.07%. Validation results demonstrated strong generalization capability, with validation accuracy, Dice score, and IoU of 87.47%, 90.07%, and 81.96%, respectively. The high-precision segmentation performance enabled a comprehensive fracture analysis of 3333 quartz mineral images obtained from specimens exposed to systematic stress conditions. Full article

A notable drawback of Double Random Phase Encryption (DRPE), a prominent optical cryptography technique, is its low data efficiency. This is because both the encrypted image and the decryption key are represented as complex numbers. To address this issue, a conventional method was proposed that encrypts two images simultaneously by treating the first image as amplitude and the second image as phase. Nevertheless, processes such as integral imaging, which extract 3D object information from images, utilize vast amounts of imagery, necessitating further enhancements in data efficiency. The objective of this research is to enhance DRPE and improve data efficiency by increasing the number of images that can be processed simultaneously. This paper incorporates the information from a third image into the random phase mask used in conventional methods, enabling the simultaneous processing of three images. It also proposes a method to synthesize two images by extracting their high-order bits and combining them. The combination of this image composition method as a preprocessing step with the proposed DRPE method enables the simultaneous processing of six images. As a result, the proposed method achieves a data efficiency approximately six times that of the basic DRPE and approximately three times that of conventional methods. The quality of the decrypted images was evaluated using PSNR and SSIM, while the encryption strength was assessed in terms of key space, key sensitivity, entropy, and correlation coefficients. Full article

Lumbar interbody fusion is widely performed for degenerative, deformity-related, and instability-associated spinal conditions. Yet, reported outcomes remain variable across grafting strategies and surgical techniques. While advances in instrumentation and cage design improve immediate construct stability, successful arthrodesis depends on early graft behavior within the interbody environment. This includes positional stability, interface contact, and load transfer prior to mature bone formation. Synthetic bone graft substitutes are commonly used to supplement or replace autograft. However, the clinical literature describing these materials is heterogeneous with respect to composition, structural presentation, surgical context, and outcome reporting. This narrative review synthesizes clinical, translational, and biomechanical studies published between 2019 and 2025 that evaluate synthetic bone graft substitutes used in adult lumbar interbody fusion. Rather than comparing individual products or reported fusion rates, grafts are organized by material class and examined through early mechanical events such as graft migration, loss of graft–endplate contact, and cage subsidence. Across recent studies, variability in fusion definitions, imaging modalities, postoperative timepoints, and documentation of early mechanical events limits direct comparison and quantitative synthesis. These findings highlight the need for improved reporting consistency and greater emphasis on engineering-relevant variables in future investigations. Full article

Objectives: To evaluate the impact of non-invasive imaging techniques such as dermoscopy, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) to monitor the efficacy of risankizumab on plaque psoriasis of the legs by analyzing morpho-histological changes. Materials and Methods: Multicentre, real-world retrospective study involving 37 adults with moderate-to-severe plaque psoriasis. Assessments performed during routine visits at baseline, Week 4 and Week 12 included clinical response, dermoscopy, RCM and OCT. Results: Thirty-seven patients were included (mean age 52.1 years; 54% male; mean BMI 27.0 kg/m²). Dermoscopy showed progressive vascular normalization: at Week 12, 94.29% of lesions had minimal or no vascular pattern. White and yellow scales decreased significantly. On RCM, dilated vessels, inflammatory infiltrate, and papillomatosis progressively normalized. OCT showed reduction in epidermal and stratum corneum thickness and a decline in vascular intensity at multiple depths. Baseline haemorrhagic dots predicted early complete response: 44.8% of lesions with dots achieved complete clearance at Week 4 versus 0% without. Conclusions: Risankizumab induced rapid, significant regression of psoriatic changes, normalizing vascular patterns and skin architecture and reducing epidermal thickness. Findings support its efficacy and rapid onset of action in difficult-to-treat areas and highlight the value of non-invasive imaging for monitoring. Full article

Tomato cultivation is a cornerstone of global agriculture, yet it faces significant challenges from a variety of diseases that can drastically reduce yield and quality. Traditional methods of disease detection, which rely on manual inspection, are labor-intensive, time-consuming, and prone to human error. To address these challenges, this study presents an advanced, automated system for tomato disease detection and spray prescription using an enhanced YOLOv9 (You Only Look Once) model. By leveraging advanced deep learning techniques, the proposed system accurately identifies and detects nine tomato leaf diseases in real-time by making efficient, precise, and accurate decisions. This YOLOv9 model is modified for detecting tomato leaf diseases and optimized for getting higher accuracy and efficiency. The system automatically prescribes the spray based on detected disease, which helps in reducing pesticide use, along with the environmental impact. This system helps in maximizing crop health and yield. After testing the system on the test dataset and real-time images, the results demonstrate the system’s accuracy and efficiency, achieving a detection accuracy of 97% and spray prescription accuracy of 94%. Integrating a YOLOv9 with a spray prescription system provides a sustainable, cost-effective solution for managing tomato plant diseases. Implementing this system on edge devices paves the way for more extensive precision agriculture applications. By integrating advanced technology with real-world agricultural needs, this work makes a contribution and a global effort to ensure food security and ecological farming practices. Full article

For sensing applications, a complementary metal oxide semiconductor (CMOS) image sensor (CIS) with a lateral overflow integration capacitor (LOFIC) is in high demand. The LOFIC CIS can achieve high-dynamic-range (HDR) imaging by combining a low-conversion-gain (LCG) signal for large maximum signal electrons and a high-conversion-gain (HCG) signal for a low electron-referred noise floor. However, the LOFIC CIS faces challenges regarding the power consumption and circuit area when reading both HCG and LCG signals. To address these issues, this study proposes a readout circuit composed of area-efficient MOS capacitors using a folding DC operating point technique and an in-column signal selector for an on-chip HDR merger of HCG and LCG signals. A 10-bit test chip was fabricated with a $0.18$ µm CMOS process with MOS capacitors. The fabricated chip maintains high linearity, achieving an integral nonlinearity (INL) of +7.17/−6.93 LSB for the HCG signal and +7.95/−7.41 LSB for the LCG signal. Furthermore, the proposed design achieves a $14.92\%$ reduction in the average power consumption of the total readout circuit and a $36.5\%$ reduction in the readout circuit area. Full article

The rapid development of remote sensing satellite technology has enabled remote sensing images to be widely used in agriculture, meteorology, environmental monitoring and other fields. However, the presence of clouds in these images can lead to blurred and incomplete observations of the Earth’s surface, limiting the quality and applicability of the data. Current cloud detection networks usually adopt a single encoder–decoder structure that uniformly processes all spectral features without distinguishing between various spectral bands. To overcome this limitation, this paper proposes an Optical characteristics-guided Asymmetric Dual Encoder Feature Fusion cloud detection algorithm (OADEF²). The algorithm adopts an asymmetric dual encoder framework to divide the spectral bands of Sentinel-2A into two groups: RGB visible light bands and infrared/atmospheric correction bands, which are subsequently input into two different encoder branches. This method utilizes the unique physical characteristics of different spectral bands to improve the accuracy of cloud detection. In order to direct the focus of the network to cloud-related optical characteristics, an Optical characteristics-guided Multi-Scale cloud feature module (OCGMSCFM) based on Dynamic HOT Index and Full-Band Cloud Index is introduced. This module effectively solves the problem of insufficient representation of cloud features. In order to improve the efficiency of feature fusion, a Feature Aggregation and Filtering module (FAFM) is proposed. This module uses aggregation and techniques to filter basic features, thereby improving the accuracy of cloud detection. In order to overcome the limitations of feature modeling, a dual attention module that fuses Multi-interaction Local Spatial Attention mixed Channel Attention (MILSAMCAM) is added to the decoder. The experimental results validated the effectiveness of this algorithm in cloud detection tasks, achieving an F1-score of 97.30% on the S2-CMC dataset. Full article

To investigate the effect of different grouting pressures on the reinforcement of fractured sandy mudstone, grouting tests, mechanical experiments, CT scanning, and SEM analysis were conducted on fractured rock samples. Based on CT data, the precise internal structure of the grouted rock samples was obtained. High-fidelity numerical models were constructed in ABAQUS through image processing and mesh mapping techniques and then imported into ANSYS for uniaxial compression simulation. The results showed that under grouting pressures of 1 MPa, 3 MPa, and 5 MPa, the compressive strengths of the samples were 10.08 MPa, 12.39 MPa, and 13.28 MPa, corresponding to increases of 22.9% and 7.2%, respectively. The elastic moduli were 1.16 GPa, 1.52 GPa, and 1.63 GPa, with increases of 31% and 7.2%, respectively. The toughness index and brittleness index exhibited opposite trends: the toughness index increased from 1.6555 to 1.7135 and then to 1.7648 (rises of 3.5% and 2.9%), while the brittleness index decreased from 1.5255 to 1.4020 and then to 1.3075 (reductions of 8.1% and 6.7%). The ductility index rose from 1.8760 to 2.0972 and then to 2.2637 (increases of 11.8% and 7.9%). The failure mode of the grouted rock samples shifted from brittle to ductile behavior, with the most pronounced overall mechanical improvement observed at 3 MPa grouting pressure. SEM analysis indicated that as the grouting pressure increased, the dominant crack type changed from large cracks to micro-cracks. At 3 MPa, the grout fully penetrated micro-pores and enhanced the sample’s integrity, whereas at 5 MPa, excessive grouting pressure induced damage to the rock matrix itself. Fracture simulations further demonstrated that as the grouting pressure increased from 1 MPa to 3 MPa and above, the failure mode shifted from being controlled by pre-existing fractures to a holistic rupture involving both the grout and the rock matrix, leading to significantly improved structural integrity. This study establishes an integrated numerical simulation approach of “CT scanning—in situ modeling—mechanical analysis”, providing a scientific basis for optimizing grouting parameters. Full article

Background/Objectives: Fetal growth restriction (FGR), historically termed intrauterine growth restriction (IUGR), is a multifactorial condition in which the fetus fails to reach its genetically determined growth potential, most often due to placental insufficiency. Beyond its link with increased perinatal morbidity and mortality, FGR has been associated with long-term cardiovascular risk through early-life programming. The developing fetal heart is vulnerable to chronic hypoxia and nutrient deprivation, potentially inducing structural and functional alterations with lifelong consequences. This narrative review summarizes and critically appraises experimental and clinical evidence on the impact of FGR on myocardial development and cardiovascular health from fetal life to adulthood. Methods: We conducted a narrative review using a structured literature search of studies published in the last 15 years in PubMed and Scopus, focusing on experimental, imaging, and epidemiological research evaluating cardiac structure, function, and long-term cardiovascular outcomes in FGR. Evidence from fetal and neonatal echocardiography, including Doppler and speckle-tracking techniques, as well as molecular and histological studies, was examined. No statistical meta-analysis was performed. Results: FGR has been associated with reduced cardiomyocyte number, altered myocardial architecture, increased interstitial fibrosis, and persistent ventricular remodeling. Functional studies suggest early impairments in systolic and diastolic performance, with alterations in cardiac energy metabolism and epigenetic regulation. Advanced imaging may enable detection of subclinical cardiac dysfunction in utero and early postnatally. Epidemiological data suggest an increased risk of hypertension, ischemic heart disease, heart failure, and metabolic disorders in adulthood among individuals born growth-restricted. Conclusions: FGR represents an early cardiovascular risk condition. Improved understanding of fetal cardiac programming may help refine risk stratification, surveillance, and preventive strategies to reduce long-term cardiovascular morbidity in individuals born growth-restricted. Full article

Objective: This study aimed to compare the clinical outcomes of navigation-assisted and conventional (freehand) ventriculoperitoneal (VP) shunt placement in pediatric hydrocephalus patients. Methods: A retrospective review was conducted of 164 patients under the age of 18 who underwent VP shunt placement for hydrocephalus between 2015 and 2023 and had a minimum postoperative follow-up of 12 months. The conventional technique was used in 116 patients. The navigation-assisted technique (intraoperative ultrasonography or frameless neuronavigation) was used in 48 patients. Demographic data, hydrocephalus etiology, catheter tip position (Yim classification), revision rates, infection, complications, and length of hospital stay were recorded. Catheter tip position was assessed on postoperative imaging by two independent investigators. Results: No significant differences were found between the groups in terms of age, sex, and hydrocephalus etiology. The optimal catheter placement rate was significantly higher in the navigation-assisted group compared to the conventional technique (81.25% vs. 60.34%, p = 0.017). The revision rate was significantly lower in the navigation-assisted group (16.67% vs. 38.79%, p = 0.010). The mean hospital stay was shorter in the navigation-assisted group (7.85 ± 3.97 days vs. 10.20 ± 3.70 days, p < 0.001). The groups were similar in terms of infection (2.08% vs. 9.48%, p = 0.183) and overall complication rates (14.58% vs. 16.38%, p = 0.959). Conclusions: Navigation-assisted VP shunt placement in pediatric hydrocephalus patients is associated with a high rate of optimal catheter position, a low revision rate, and a short hospital stay. These findings support the use of navigation technology in pediatric hydrocephalus surgery, but also reveal that infection and complications are unassociated with the surgical technique. Full article

Background: In maxillofacial reconstruction, even small inaccuracies can compromise aesthetics, function, and safety. Surgeons currently rely on preoperative imaging; however, recent advances in intraoperative imaging now provide three-dimensional, real-time guidance, possibly enhancing surgical outcomes. This review evaluates the current application of intraoperative imaging in maxillary and mandibular surgery including its impact on accuracy, efficiency, and outcomes. Methods: Two separate systematic reviews (PROSPERO CRD420251125497, CRD420251124600), analyzing maxillary and mandibular repair were conducted through Cochrane, Medline, Embase, and Web of Science. Both reviews adhered to the PRISMA guidelines. Inclusion criteria encompassed intraoperative digital imaging or navigation in maxillary or mandibular surgery. Studies without human subjects, intraoperative imaging, or the surgery of interest were excluded. Bias was assessed with NIH Quality Assessment. Results: A combined total of 795 publications were screened, with 35 studies ultimately included in this review, encompassing 1643 patients. Techniques included intraoperative computed tomography (CT) (n = 12, 34.3%), stereotactic navigation (n = 16, 45.7%), augmented reality (n = 2, 5.7%), ultrasound, fluoroscopy, infrared stereoscopic and electromagnetic (n = 1, 2.9%, each). The most common indication for surgery was fracture repair. Reporting was heterogeneous, with variable metrics and reporting for accuracy, complications, and revisions. Overall, cone-beam CT (CBCT) and stereotactic navigation both demonstrated significant restoration of normal symmetry, and stereotactic navigation enabled accuracy of <2 mm. CBCT added the shortest amount of time intraoperatively, ranging from 1 to 20 min. Reporting on long-term outcomes was heterogeneous. Conclusions: A variety of intraoperative imaging and navigation techniques are being applied in maxillofacial surgery. However, inconsistent reporting metrics, small study size, and study feasibility-focused study design limit meaningful comparison across technologies. Rigorous prospective studies with standardized outcome measures are needed to further define their clinical value and guide adoption. Full article

Background: Stroke is a leading cause of mortality and long-term disability, and aphasia is among its most common and debilitating sequelae. Diffusion tensor imaging (DTI) and advanced diffusion imaging techniques enable the assessment of white matter integrity and provide clinically relevant measures in post-stroke aphasia. Methods: We conducted a comprehensive review of studies applying DTI or advanced diffusion imaging to investigate structural connectivity in adults with post-stroke aphasia (PSA). PubMed, CENTRAL, Ovid MEDLINE, and Embase were searched, and eligible studies were synthesized according to their diagnostic, prognostic, or therapeutic focus. Results: Ninety-five studies were included. Of these, 59 were classified as diagnostic, 17 as prognostic, and 19 as therapeutic. Most studies employed conventional DTI (n = 77), while a growing body of research utilized advanced diffusion models, including CSD, DSI, and DKI (n = 18). Conclusions: This comprehensive synthesis demonstrates the evolution of diffusion imaging in PSA research. While conventional DTI has provided foundational insights, advanced diffusion methods offer superior characterization of complex fiber architecture and improved clinical–anatomical correlation. Diffusion-derived markers of dorsal and ventral language pathways were consistently associated with language performance, while connectome-level analyses highlighted the importance of preserved global network architecture for recovery. Continued efforts are needed to translate diffusion imaging findings into clinical applicable biomarkers to guide personalized aphasia rehabilitation, with greater use of advanced methods. Full article