Search Results (63)

Space gravitational wave detection, which could help humanity explore the mysteries of the universe, is a significant objective in the scientific world today, and several different countries and scientific groups have organized programs targeting its realization. The telescope for gravitational wave detection is a crucial component in the detection satellite, as it is the means of receiving and transmitting the interferometric laser beam; therefore, its structural design is very significant. This paper focuses on the telescope in the TianQin program. First, a structural design scheme is given based on a five-mirror optical system Then, some of the component’s parts are refined to improve its mechanical performance. Finally, a mechanical simulation analysis is performed to verify its reliability and feasibility during the rocket launch. The results reveal that the presented structural design scheme for the telescope is both safe and viable. Full article

Background: Nosocomial pneumonia (NP) is a significant cause of morbidity and mortality in intensive care unit (ICU) patients. Prior antibiotic use, polymicrobial infections, and the limitations of conventional microbiological methods often complicate an accurate diagnosis. Bronchoalveolar lavage (BAL) and tracheal suction (TS) are commonly used methods for collecting respiratory samples; however, their diagnostic accuracy can vary. Additionally, microbiome analysis using 16S/18S rRNA gene sequencing provides an alternative approach for identifying pathogens that are difficult to culture. This study aimed to compare the diagnostic value of routine culturing and microbiome analysis in identifying pathogens in ICU patients with NP. Methods: A prospective cohort study was conducted in 23 critically ill patients at Zealand University Hospital. Samples from TS and BAL were collected from patients with suspected NP. Both culturing and 16S/18S rRNA gene amplicon-based microbiome analysis were performed to identify pathogens. Findings were compared between the two types of samples and between the two analysis methods. Results: A total of 46 samples were analyzed (23 TS and 23 BAL). Culture results showed complete concordance in 60.9% of cases and partial concordance in 21.7% between results from TS and BAL. Discrepancies often involved low-virulence organisms, such as Staphylococcus epidermidis and Candida albicans. Microbiome analysis revealed a broader spectrum of microbial diversity, detecting pathogens such as Pasteurella canis and Tropheryma whipplei that were previously missed by culture methods. In 34.8% of the samples, the pathogen identified by microbiome analysis was also detected by culture. However, microbiome analysis also identified additional microorganisms in 17.4% of the cases, which were not detected by culture. When comparing microbiome results between TS and BAL, 16 out of 23 (69.5%) showed complete concordance. Conclusions: The findings were similar in TS and BAL, both for culture and 16S/18S amplicon-based microbiome analyses. Microbiome analysis using 16S/18S rRNA gene sequencing provided new insights into NP patients, identifying pathogens that were previously undetected by conventional culturing methods. Combining microbiome analysis with traditional culture techniques could enhance the diagnostic accuracy for NP. Further studies are needed to refine diagnostic thresholds and assess the clinical impact of microbiome-based diagnostics. Full article

Campus buildings often present hidden safety risks such as falls and wheelchair instabilities, which are closely related to architectural layout, material selection, and accessibility design. This study develops YOLOv11-Safe, an attention-enhanced and geometry-aware framework that functions as both a detection model and a spatial diagnostic tool for building safety assessment. The framework integrates a modified SimAM attention mechanism and a normalized Wasserstein distance (NWD) loss to improve detection accuracy in complex indoor environments, trained on a dataset of 1000 annotated images covering fall and wheelchair accident scenarios. To interpret spatial risk patterns, a Random Forest classifier combined with SHAP analysis was applied to quantify the contribution of five architectural–behavioral variables: body–ground contact ratio (BGCR), accessibility index (AI), event duration (D), body posture angle (PA), and spatial density (SD). Results show that BGCR and AI dominate the risk-level prediction, while D, PA, and SD refine boundary conditions. Scene-based verification further demonstrated that the framework accurately localized unsafe features—such as uneven drainage edges and discontinuous handrails—and translated them into actionable design feedback. The proposed approach thus links deep-learning detection with interpretable spatial analysis, offering a quantitative foundation for evidence-based architectural safety optimization in university campuses. Full article

Background: Hepatocellular carcinoma (HCC) frequently develops in patients with chronic hepatitis B and C. Early detection is critical, but current methods, including ultrasound and AFP, have suboptimal accuracy. Objectives: This study aimed to evaluate the predictive performance of protein induced by vitamin K absence or antagonist-II (PIVKA-II) and alpha-fetoprotein (AFP) testing, alone and in combination, for HCC development. Methods: A retrospective cohort study at a single university center included 242 CHB and 181 CHC patients. Data on demographics, clinical status, laboratory parameters, and imaging were collected, with fibrosis and steatosis assessed by FibroScan^®. Serum AFP and PIVKA-II were measured, but measurements of PIVKA-II in patients receiving vitamin K antagonists were excluded from the analysis. HCC diagnosis and staging followed clinical guidelines. Cox regression and ROC analyses identified independent predictors and evaluated biomarker accuracy for HCC detection. Results: HCC incidence was comparable between cohorts (5.0% in CHB vs. 5.5% in CHC). Both AFP and PIVKA-II independently predicted HCC development in multivariate models adjusted for age and sex. The combined biomarker score (AFP × PIVKA-II) showed superior predictive accuracy with hazard ratios of 1.38 (CHB) and 1.36 (CHC). ROC analyses demonstrated high discriminative ability for PIVKA-II (AUC ~0.81) and AFP (AUC ~0.83) in both cohorts. Additional independent predictors were chronic alcohol abuse, cirrhosis, and higher liver stiffness measurements. Specific viral factors such as HBeAg positivity and HCV subgenotype 1b were also associated with increased HCC risk. Conclusions: AFP and PIVKA-II are independent, valuable biomarkers for HCC risk in chronic hepatitis B and C. Combined use improves early detection, aiding timely treatment. These results support adding PIVKA-II to AFP in surveillance, but larger studies are needed to confirm the findings and refine cut-off values. Full article

Bud break is a critical phenological stage in muscadine grapevines, marking the start of the growing season and the increasing need for irrigation management. Real-time bud detection enables irrigation to match muscadine grape phenology, conserving water and enhancing performance. This study presents BudCAM, a low-cost, solar-powered, edge computing camera system based on Raspberry Pi 5 and integrated with a LoRa radio board, developed for real-time bud detection. Nine BudCAMs were deployed at Florida A&M University Center for Viticulture and Small Fruit Research from mid-February to mid-March, 2024, monitoring three wine cultivars (A27, noble, and Floriana) with three replicates each. Muscadine grape canopy images were captured every 20 min between 7:00 and 19:00, generating 2656 high-resolution (4656 × 3456 pixels) bud break images as a database for bud detection algorithm development. The dataset was divided into 70% training, 15% validation, and 15% test. YOLOv11 models were trained using two primary strategies: a direct single-stage detector on tiled raw images and a refined two-stage pipeline that first identifies the grapevine cordon. Extensive evaluation of multiple model configurations identified the top performers for both the single-stage (mAP@0.5 = 86.0%) and two-stage (mAP@0.5 = 85.0%) approaches. Further analysis revealed that preserving image scale via tiling was superior to alternative inference strategies like resizing or slicing. Field evaluations conducted during the 2025 growing season demonstrated the system’s effectiveness, with the two-stage model exhibiting superior robustness against environmental interference, particularly lens fogging. A time-series filter smooths the raw daily counts to reveal clear phenological trends for visualization. In its final deployment, the autonomous BudCAM system captures an image, performs on-device inference, and transmits the bud count in under three minutes, demonstrating a complete, field-ready solution for precision vineyard management. Full article

Recurrent ovarian cancer (OC) is challenging to detect early using current methods like CA-125 and imaging. Circulating tumor DNA (ctDNA) may improve disease monitoring. Here, we assess the real-world clinical utility of serial ctDNA analyses in patients with recurrent OC. We analyzed serial plasma samples (N = 23) from six patients with recurrent OC using a tumor-informed next-generation sequencing assay targeting 68 cancer-related genes developed at the University of Washington. ctDNA variant allele frequencies (VAFs) were correlated with CA-125 levels, radiographic findings, and clinical outcomes. ctDNA levels generally reflected clinical status, accurately mirroring disease progression and therapeutic response. In one patient, rising ctDNA preceded clinical recurrence by four months, despite normal CA-125 and imaging, highlighting its potential advantage. Conversely, some patients exhibited clinical progression with undetectable ctDNA, indicating limitations in assay sensitivity, biological factors, or metastatic sites (e.g., brain metastases). ctDNA and CA-125 showed complementary value in most cases, suggesting potential combined use in clinical monitoring. Our findings demonstrate that ctDNA is a promising biomarker to complement existing monitoring approaches for recurrent OC. In some cases, capable of predicting relapse and treatment response ahead of current clinical indicators. However, identified discordances underscore technical and biological challenges that warrant further investigation. Larger prospective studies are necessary to refine ctDNA’s clinical utility and integration into personalized OC care. Full article

Plants vary in number of chromosomes (ploidy levels), which can influence morphological traits, including the size and density of stomata cells. Although biologists can detect these differences under a microscope, the process is often time-consuming and tedious. This study aims to automate the classification of blackcurrant (Ribes nigrum L.) ploidy levels—diploid, triploid, and tetraploid—by leveraging deep learning techniques. Convolutional Neural Networks and Vision Transformers are employed to perform microscopic image classification across two distinct blackcurrant datasets. Initial experiments demonstrate that these models can effectively classify ploidy levels when trained and tested on subsets derived from the same dataset. However, the primary challenge lies in proposing a model capable of yielding satisfactory classification results across different datasets ensuring robustness and generalization, which is a critical step toward developing a universal ploidy classification system. In this research, a variety of experiments is performed including application of augmentation technique. Model efficacy is evaluated with standard metrics and its interpretability is ensured through Gradient-weighted Class Activation Mapping visualizations. Finally, future research directions are outlined with application of other advanced state-of-the-art machine learning methods to further refine ploidy level prediction in botanical studies. Full article

Since the development of industrial robots, they have been used to enhance efficiency and reduce the need for manual labor. Industrial robots have become a universal tool across all economic sectors, with the integration of software that is extremely important for the effective operation of machines and processes. Robotic action accuracy is currently experiencing rapid development in all robot-involving activities. Currently, a significant breakthrough has been observed in modifying algorithms and controlling robot actions, as well as in monitoring and planning software and hardware compatibility to prevent errors in real-time. The integration of the Internet of Things, machine learning, and other advanced techniques has enhanced the intelligent features of industrial robots. As industrial automation advances, there is an increasing demand for precise control in a variety of robotic arm applications. It is essential to refine current solutions to address the challenges posed by the high connectivity, complex computations, and various scenarios involved. This review examines the application of vision-based models, particularly YOLO (You Only Look Once) variants, in object detection within industrial robotic environments, as well as other machine learning models for tasks such as classification and localization. Finally, this review summarizes the results presented in selected publications, compares represented methods, identifies challenges in prospective object-tracking technologies, and suggests future research directions. Full article

Detecting and alerting for falls is a crucial component of both healthcare and assistive technologies. Wearable devices are vulnerable to damage and require regular inspection and maintenance. Manned video surveillance avoids these problems, but it involves constant labor-intensive attention and, in most cases, may interfere with the privacy of the observed individuals. To address this issue, in this work we introduce and evaluate a novel approach for fully automated fall detection. The presented technique uses direct reconstruction of principal motion parameters, avoiding the computationally expensive full optical flow reconstruction and still providing relevant descriptors for accurate detections. Our method is systematically compared with state-of-the-art techniques. Comparisons of detection accuracy, computational efficiency, and suitability for real-time applications are presented. Experimental results demonstrate notable improvements in accuracy while maintaining a lower computational cost compared to traditional methods, making our approach highly adaptable for real-world deployment. The findings highlight the robustness and universality of our model, suggesting its potential for integration into broader surveillance technologies. Future directions for development will include optimization for resource-constrained environments and deep learning enhancements to refine detection precision. Full article

Background: Malnutrition and systemic inflammation are major determinants of poor outcomes in hospitalized older adults, such as length of hospital stay (LOS), mortality, and readmission risk. The C-reactive protein to albumin ratio (CRP/Alb) and the Prognostic Nutritional Index (PNI) are simple biomarkers reflecting inflammation and nutritional status. Additionally, the PNI offers a straightforward method to assess both the nutritional state and mortality risk in older patients. Objective: The objective of this study was to compare the predictive accuracy of the CRP/Alb ratio and PNI for early in-hospital mortality at 7 and 30 days after admission in older patients, independent of admitting diagnosis. Methods: We retrospectively analyzed 2776 patients aged 65 years and older, admitted to the Internal Medicine and Aging Unit of the “Policlinico Riuniti” University Hospital in Foggia, Italy, between 2019 and 2025. Laboratory data at admission included CRP, albumin, and total lymphocyte count (TLC). The CRP/Alb ratio and PNI were calculated. Prognostic performance for 7- and 30-day mortality for both the CRP/Alb ratio and PNI was assessed using ROC curves, Cox regression, Kaplan–Meier survival analyses, and positive predictive value (PPV) comparisons, stratified by rehospitalization status and length of stay (LOS). The likelihood-ratio test was also performed to compare the 7- and 30-day mortality PPVs of the CRP/Alb ratio and the PNI, both for all patients and for re-hospitalized patients. Results: In-hospital mortality occurred in 444 patients (16%). Deceased patients showed significantly higher CRP/Alb ratios and lower PNI values than survivors (p < 0.001). Both the CRP/Alb ratio and PNI independently predicted 7- and 30-day mortality. A CRP/Alb ratio > 8 strongly predicted very early mortality (HR 10.46 for 7-day death), whereas a PNI < 38 predicted both 7- and 30-day mortality (HR 8.84 and HR 3.54, respectively). Among non-rehospitalized patients, the PNI demonstrated superior predictive performance regardless of LOS (p < 0.001). Among rehospitalized patients, the PNI was a more accurate predictor for short LOS (<7 days), while the CRP/Alb ratio performed better for longer LOS (≥7 days). Conclusions: Both the CRP/Alb ratio and PNI are inexpensive, readily available biomarkers for early risk stratification in hospitalized older adults. The CRP/Alb ratio is particularly effective in detecting very early mortality risk, while the PNI offers refined prognostic value across selected subgroups. Integrating these markers at admission may support personalized geriatric care and timely interventions. Full article

Background/Objectives: Cardiac sarcoidosis (CS) is a granulomatous inflammatory cardiomyopathy with heterogeneous presentations, from palpitations to heart failure and sudden cardiac arrest. Despite advances in imaging and immunosuppressive (IS) therapy, relapse patterns and long-term outcomes remain poorly defined. This study aimed to characterize relapse and identify predictors of relapse and major adverse cardiac events (MACE) in a real-world CS cohort. Methods: This retrospective single-center study included 25 adults diagnosed with CS at Geneva University Hospitals between 2016 and 2024, classified per the 2024 American Heart Association diagnostic criteria. Relapse was defined as clinical, arrhythmic, or imaging deterioration requiring treatment escalation. MACE included cardiovascular hospitalization, device therapy, left ventricular assist device, heart transplant, or death. Statistical methods included Kaplan–Meier analysis with log-rank tests and multivariable Cox regression adjusted for age and sex. Results: Relapse occurred in 13 patients (56%), frequently subclinical (61.5%) and detected incidentally on routine PET-CT during IS tapering. In the multivariate model, predictors of relapse included right ventricular FDG uptake (aHR 13.1; 95% CI 1.3–133.7; p = 0.03) and second-line immunosuppression duration ≤24 months (aHR 20.1; 95% CI 1.1–363.8; p = 0.04). Relapse-free patients were more often maintained on dual or triple IS therapy (71.4% vs. 15.4%; p = 0.02) and low-dose prednisone (<10 mg/day) (57.1% vs. 7.7%; p = 0.03). Conclusions: Relapse is common in CS, often subclinical, and associated with PET-CT findings and premature IS tapering. Maintenance therapy may reduce risk. Multimodal imaging remains critical for disease monitoring, though tracers with higher specificity are needed. Further research should refine relapse definitions and support personalized treatment strategies. Full article

This study introduces YOLOv13-Cone-Lite, an enhanced algorithm based on YOLOv13s, designed to meet the stringent accuracy and real-time performance demands for traffic cone detection in autonomous formula racing cars on enclosed tracks. We improved detection accuracy by refining the network architecture. Specifically, the DS-C3k2_UIB module, an advanced iteration of the Universal Inverted Bottleneck (UIB), was integrated into the backbone to boost small object feature extraction. Additionally, the Non-Maximum Suppression (NMS)-free ConeDetect head was engineered to eliminate post-processing delays. To accommodate resource-limited onboard terminals, we minimized superfluous parameters through structural reparameterization pruning and performed 8-bit integer (INT8) quantization using the TensorRT toolkit, resulting in a lightweight model. Experimental findings show that YOLOv13-Cone-Lite achieves a mAP₅₀ of 92.9% (a 4.5% enhancement over the original YOLOv13s), a frame rate of 68 Hz (double the original model’s speed), and a parameter size of 8.7 MB (a 52.5% reduction). The proposed algorithm effectively addresses challenges like intricate lighting and long-range detection of small objects and offers the automotive industry a framework to develop more efficient onboard perception systems, while informing object detection in other closed autonomous environments like factory campuses. Notably, the model is optimized for enclosed tracks, with open traffic generalization needing further validation. Full article

Interstitial lung diseases (ILD) significantly impact health and mortality, affecting millions of individuals worldwide. During the COVID-19 pandemic, lung ultrasonography (LUS) became an indispensable diagnostic and management tool for lung disorders. However, utilising LUS to diagnose ILD requires significant expertise. This research aims to develop an automated and efficient approach for diagnosing ILD from LUS videos using AI to support clinicians in their diagnostic procedures. We developed a binary classifier based on a state-of-the-art CSwin Transformer to discriminate between LUS videos from healthy and non-healthy patients. We used a multi-centric dataset from the Royal Melbourne Hospital (Australia) and the ULTRa Lab at the University of Trento (Italy), comprising 60 LUS videos. Each video corresponds to a single patient, comprising 30 healthy individuals and 30 patients with ILD, with frame counts ranging from 96 to 300 per video. Each video is annotated using the corresponding medical report as ground truth. The datasets used for training the model underwent selective frame filtering, including reduction in frame numbers to eliminate potentially misleading frames in non-healthy videos. This step was crucial because some ILD videos included segments of normal frames, which could be mixed with the pathological features and mislead the model. To address this, we eliminated frames with a healthy appearance, such as frames without B-lines, thereby ensuring that training focused on diagnostically relevant features. The trained model was assessed on an unseen, separate dataset of 12 videos (3 healthy and 9 ILD) with frame counts ranging from 96 to 300 per video. The model achieved an average classification accuracy of 91%, calculated as the mean of three testing methods: Random Sampling (92%), Key Featuring (92%), and Chunk Averaging (89%). In RS, 32 frames were randomly selected from each of the 12 videos, resulting in a classification with 92% accuracy, with specificity, precision, recall, and F1-score of 100%, 100%, 90%, and 95%, respectively. Similarly, KF, which involved manually selecting 32 key frames based on representative frames from each of the 12 videos, achieved 92% accuracy with a specificity, precision, recall, and F1-score of 100%, 100%, 90%, and 95%, respectively. In contrast, the CA method, where the 12 videos were divided into video segments (chunks) of 32 consecutive frames, with 82 video segments, achieved an 89% classification accuracy (73 out of 82 video segments). Among the 9 misclassified segments in the CA method, 6 were false positives and 3 were false negatives, corresponding to an 11% misclassification rate. The accuracy differences observed between the three training scenarios were confirmed to be statistically significant via inferential analysis. A one-way ANOVA conducted on the 10-fold cross-validation accuracies yielded a large F-statistic of 2135.67 and a small p-value of 6.7 × 10⁻²⁶, indicating highly significant differences in model performance. The proposed approach is a valid solution for fully automating LUS disease detection, aligning with clinical diagnostic practices that integrate dynamic LUS videos. In conclusion, introducing the selective frame filtering technique to refine the dataset training reduced the effort required for labelling. Full article

Background/Objectives: Cystic fibrosis-associated liver disease (CFLD) is a significant complication in individuals with cystic fibrosis (CF), contributing to morbidity and mortality, with no universally accepted, reliable, non-invasive diagnostic tool for early detection. Current diagnostic methods, including liver biopsy and imaging, remain resource-intensive and invasive. Non-invasive biomarkers like the Fibrosis-4 (FIB-4) index have shown promise in diagnosing liver fibrosis in various chronic liver diseases. This study explores the potential of the FIB-4 index to predict CFLD in an adult CF population and assesses its correlation with transient elastography (TE) as a potential diagnostic tool. The aim of this study is to evaluate the diagnostic performance of the FIB-4 index for CFLD in adults with CF and investigate its relationship with TE-based liver stiffness measurements (LSM). Methods: The study was conducted in a regional cystic fibrosis unit, including 261 adult CF patients. FIB-4 scores were calculated using an online tool (mdcalc.com) based on patient age, aspartate aminotransferase (AST), alanine aminotransferase (ALT), and platelet count. In parallel, 29 patients underwent liver stiffness measurement using TE (Fibroscan^®). Statistical analyses included non-parametric tests for group comparisons and Pearson’s correlation to assess the relationship between FIB-4 scores and TE results. Results: The mean FIB-4 score in patients diagnosed with CFLD was higher (0.99 ± 0.83) compared to those without CFLD (0.64 ± 0.38), although the difference was not statistically significant (p > 0.05). TE results for CFLD patients (5.9 kPa) also did not show a significant difference compared to non-CFLD patients (4.2 ± 1.6 kPa, p > 0.05). However, a positive correlation (r = 0.401, p = 0.031) was found between FIB-4 scores and TE-based LSM, suggesting a potential complementary diagnostic role. Conclusions: The FIB-4 index, while not sufficient as a standalone diagnostic tool for CFLD in adults with CF, demonstrates potential when used in conjunction with other diagnostic methods like TE. This study introduces a novel approach for integrating non-invasive diagnostic markers in CF care, offering a pathway for future clinical practice. The combination of FIB-4 and TE could serve as an accessible, cost-effective alternative to invasive diagnostic techniques, improving early diagnosis and management of CFLD in the CF population. Additionally, future research should explore the integration of these tools with emerging biomarkers and clinical features to refine diagnostic algorithms for CFLD, potentially reducing reliance on liver biopsies and improving patient outcomes. Full article

The rapid advancement of environmental DNA (eDNA) technology has transformed ecological research, particularly in aquatic ecosystems. However, the optimal sampling matrix (e.g., water or sediment) and the potential for eDNA to replace or complement traditional underwater visual census (UVC) remain unclear. Here, we integrate water eDNA, sediment eDNA, and UVC approaches to systematically compare the diversity of benthic macrofauna in the subtidal zones of the Nanji Islands, China. Our results show that sediment eDNA samples exhibited the highest species richness, while UVC had the lowest. Each method revealed distinct species profiles, with relatively few shared taxa at the order level and below. Environmental eDNA showed significant advantages in detecting key phyla such as Annelida and Arthropoda. In contrast, traditional UVC was crucial for identifying certain taxa, such as Bryozoa, which were undetectable by eDNA methods. The low overlap in species detected by these methods underscores their complementary nature, highlighting the necessity of integrating multiple approaches to achieve a more comprehensive and accurate biodiversity assessment. Future research should focus on refining eDNA techniques, such as developing more universal primers, to further enhance their applicability in biodiversity monitoring. Full article