Search Results (745)

Modern external beam radiotherapy (EBRT) on lung cancer improved dose distribution thanks to advanced dose calculation algorithms, but side effects and relapses can occur in any case onset. Differential diagnosis of relapses and side effects is difficult, and when computed tomography (CT) is uncertain 18-fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG-PET/CT) can support the diagnosis, even if it can also be difficult to construe. The aim of this retrospective analysis was to evaluate 18F-FDG PET/CT qualitative patterns and semiquantitative parameters, both automatic and preceded by physicians, in interpreting lung lesions in the radiotherapy (RT) lung irradiation field. In total, 94 patients (pts) submitted to EBRT (3 months before) for stage II lung cancer were included (74 men, 20 women, mean age of 68 years old, range of 49–84 years old). CT scans were performed on pts, which showed lung lesions in the RT field. 18F-FDG-PET/CT scans were analyzed qualitatively as negative or positive, and the presence of the lung area with a high 18F-FDG uptake pattern was distinguished as the following: focal/wide, deep/shade, or homogeneous/inhomogeneous. Furthermore, the following semiquantitative parameters were collected: gSUVmax (global standardized uptake value max), MTV (tumor metabolic volume), metabolic spatial distribution (MSD) = proximal SUVmax/distal SUVmax, and intratumoral difference in spatial distribution (IDSD%) = [distal SUVmax/proximal SUVmax] × 100. 18F-FDG PET/CT was related to the pts’ outcome (biopsy and/or clinical–instrumental follow-up): positive for lung relapse, negative if the lesions were phlogistic. The following diagnostic performance parameters of 18F-FDG PET/CT were calculated: sensitivity (Sens), specificity (Spec), diagnostic accuracy (DA), positive predictive value (PPV), and negative predictive value (NPV). Qualitative variables were compared by Chi-squared test, while for semiquantitative parameters Student’s t-test was applied; p < 0.05 was considered statistically significant. Statistics tests were performed with MedCalc V.22.018 ©2024. In 76/94 (80.8%) pts, 18F-FDG uptake was higher compared to the background; in 18/94 (19.2%) no high 18F-FDG uptake areas were detected. Outcome was positive for lung relapse in 49/94 pts, while negative in 45/94, with disease prevalence of 52.13% (95%CI = 41.57–62.54%). In the 18/94 pts without high 18F-FDG uptake, the outcome was negative for lung relapse. In 49/76 pts with higher 18F-FDG uptake, the outcome confirmed the presence of relapse, while in 27/76 the lesion was phlogistic. Results about the Sens, Spec, DA, PPV, and NPV (95%CI) were, respectively: 100% (92.75–100%), 40% (25.7–55.67%), 71.28% (61.02–80.14%), 64.47% (58.84–69.73%), and 100% (81.47–100%). Chi-square test showed significant statistical difference between the positive and negative outcome for patterns focal/wide (p = 0.02) and deep/shade (p < 0.00001). A total of 35/49 (71.4%) pts with lung relapse had a focal lesion and 15/27 (55.6%) with phlogosis had a wide pattern. A total of 34/49 (69.4%) pts with lung relapse had a deep pattern and 25/27 (92.6%) with lung phlogosis had the shade one. Significant difference was observed in evaluating the three patterns (p = 0.00007), with prevalence of “focal/deep/homogeneous” patterns in lung relapse and “wide/shade/inhomogeneous” in phlogosis. gSUVmax, MTV, MSD, and IDSD% were in the following order: in the 76 pts, 5.63 (1.4–24.7), 42.49 (4.94–193), 3.61 (1–5.54), and 70.7% (18–100%); in the 49/76 true positive pts, 6.93 (1.5–24.7), 35.28 (4.94–85.99), 3.30 (1.05–5.54), and (18–95%); in the 27/76 false positive pts, 3.27 (1.4–19.2), 38.37 (4.94–193), 1.57 (1–2.13), and 78.6% (4.7–100%). The difference was statistically significant only for MSD (t = 2.779; p = 0.0069) and IDSD% (t = 2.769; p = 0.0071). 18F-FDG-PET/CT confirms its high sensitivity and NPV in evaluating lung lesions after RT. To improve physician confidence in interpreting lung 18F-FDG uptake without further support, MSD and IDSD% could be considered. Heterogeneity of lung lesions, especially in radiotreated tissue, can be turned from a drawback to a resource and analyzed for differentiating relapses from EBRT side effects. Considering the calculation of semiquantitative parameters that require “human intelligence”, even if slightly more time-consuming, can improve the nuclear physician’s confidence in interpreting 18F-FDG PET/CT images. Full article

Expanding the capacity of Matrix-Assisted Laser Desorption Ionization Time of Flight Mass Spectrometry (MALDI-TOF MS) beyond species identification to strain typing becomes a new challenge in clinical microbiology. This study demonstrated a specific identification of Streptococcus agalactiae sequence type 1 (ST1) by a manual decision tree and automatically ranking from the newly added MTPPs library, which has not been previously reported. The mass spectra of 25 STs (277 isolates) were generated. The presence and absence of specific peaks were combined to create a decision tree for manual identification. Three peaks at 3127, 5914, and 6252 in combination with m/z 3368 and 6281 were used for primary identification of ST1. However, to differentiate ST1 and ST314, five additional peaks were required. For the automatic system, the MTPP of all isolates was divided into three training–testing ratios of 40:60, 50:50, and 60:40. All categories revealed excellent accuracy rates of above 90% for ST1 identification. The 60:40 group showed the highest overall performance, in which sensitivity was observed at 83.9 to 96.8%, and specificity reached up to 100.0% for both the top two and the top three matches. In conclusion, we propose that the MTPP from MALDI-TOF is a potential model for speedy bacterial typing, crucial in epidemiology, prevention, and patient management. Full article

Phytoplankton plays a pivotal role in marine ecosystems and global biogeochemical cycles. Accurate identification and monitoring of phytoplankton are essential for understanding environmental dynamics and climate variations. Despite the significant progress made in automatic phytoplankton identification, current datasets predominantly consist of idealized laboratory images, leading to models that demonstrate persistent limitations in the fine-grained differentiation of phytoplankton species. To achieve high accuracy and transferability for morphologically similar species and diverse ecosystems, we introduce a hybrid dataset by integrating laboratory-based observations with in situ marine environmental data. We evaluate the performance of our dataset on contemporary deep learning models, revealing that CNN-based architectures offer superior stability (85.27% mAcc., 93.76% oAcc.). Multimodal learning facilitates refined phytoplankton recognition through the integration of visual and textual representations, thereby enhancing the model’s semantic comprehension capabilities. We present a fine-tuned visual language model leveraging enhanced textual prompts augmented with expert-annotated morphological descriptions, significantly enhancing visual-semantic alignment and allowing for more accurate and interpretable recognition of closely related species (84.11% mAcc., 94.48% oAcc.). Our research establishes a benchmark dataset that facilitates real-time ecological monitoring and aquatic biodiversity research. Furthermore, it also contributes to the field by enhancing model robustness and transferability to diverse environmental contexts and taxonomically similar species. Full article

Background/Objectives In this study we approach the problem of medical image segmentation by introducing a new loss function envelope that is derived from the Top-k loss strategy. We exploit the fact that, for semantic segmentation, the training loss is computed at two levels, more specifically at pixel level and at image level. Quite often, the envisaged problem has particularities that include noisy annotation at pixel level and limited data, but with accurate annotations at image level. Methods To address the mentioned issues, the Top-k strategy at image level and respectively the “Bottom all but $\sigma$” strategy at pixel level are assumed. To deal with the discontinuities of the differentials faced in the automatic learning, a derivative smoothing procedure is introduced. Results The method is thoroughly and successfully tested (in conjunction with a variety of backbone models) for several medical image segmentation tasks performed onto a variety of image acquisition types and human body regions. We present the burned skin area segmentation in standard color images, the segmentation of fetal abdominal structures in ultrasound images and ventricles and myocardium segmentation in cardiac MRI images, in all cases yielding performance improvements. Conclusions The proposed novel mechanism enhances model training by selectively emphasizing certain loss values by the use of two complementary strategies. The major benefits of the approach are clear in challenging scenarios, where the segmentation problem is inherently difficult or where the quality of pixel-level annotations is degraded by noise or inconsistencies. The proposed approach performs equally well in both convolutional neural networks (CNNs) and vision transformer (ViT) architectures. Full article

In this study, a prototype system was developed as a potential alternative to lockdown measures against the spread of airborne infectious diseases such as COVID-19. The system integrates real-time estimation functions for respiratory flow and mask leakage into a low-cost powered air-purifying respirator (PAPR) designed for the general public. Using only a single differential-pressure sensor (SDP810) and a controller (Arduino UNO R4 WiFi), the respiratory flow (Q_3e) is estimated from the differential pressure (ΔP) and battery voltage (V_b), and both the wearing status and leak status are transmitted to and displayed on a smartphone application. For evaluation, a testbench called the Respiratory Airflow Testbench was constructed by connecting a cylinder–piston drive to a mannequin head to simulate realistic wearing conditions. The estimated respiratory flow Q_3e, calculated solely from ΔP and V_b, showed high agreement with the measured flow Q_3m obtained from a reference flow sensor, confirming the effectiveness of the estimation algorithm. Furthermore, an automatic leak detection method based on the time-integrated value of Q_3e was implemented, enabling the detection of improper wearing. This system thus achieves respiratory flow estimation and leakage detection based only on ΔP and V_b. In the future, it is expected to be extended to applications such as pressure control synchronized with breathing activity and health monitoring based on respiratory and coughing analysis. This platform also has the potential to serve as the foundation of a PAPR Wearing Status Network Management System, which will contribute to societal-level infection control through the networked sharing of wearing status information. Full article

Under the “dual carbon” strategy, clarifying the relationship between economic growth and carbon emissions and revealing the differences in green transition pathways among different urban tiers within the metropolitan area is of great significance for promoting regional low-carbon development. Based on panel data of prefecture-level cities in 27 national metropolitan areas in China from 2000 to 2020, this paper employs a two-way fixed effects model and a mediation effect model to test the Environmental Kuznets Curve (EKC) hypothesis and to evaluate the mediating role of industrial structure advancement. The results show that, at the national level, carbon emissions and economic growth exhibit a significant inverted U-shaped relationship, but the EKC becomes invalid in non-core cities after dividing the sample into core and non-core cities. Industrial structure advancement significantly curbs carbon emissions in core cities, while its effect is insignificant in non-core cities, indicating insufficient structural transformation capacity. The findings suggest that core cities have initially formed a “structure-embedded” emission reduction pathway, whereas non-core cities face a dual challenge of growth and emission reduction. In terms of policy, excessive reliance on the “automatic decoupling of growth” should be avoided, and a differentiated governance system centred on structural transformation capacity should be established, with particular attention to enhancing the green transition capacity of non-core cities so as to promote regionally equitable and coordinated low-carbon development. Full article

This work addresses the automatic berthing control problem of underactuated ships under false data injection (FDI) attack, and an event-sampled automatic berthing control scheme is proposed. To avoid the FDI attack signals from entering the closed-loop system through the sensor–controller channel and worsening the berthing control performance as much as possible, a novel event-sampled adaptive neural network state observer is developed, which is independent of the controller. To solve the control design problem of berthing caused by underactuated features, an equivalent motion model of underactuated ships under FDI attack is established by differential homeomorphic transformation. Furthermore, under the backstepping design framework, using the state observer and adaptive neural network technology, a single-parameter learning-based automatic berthing control solution is developed. Meanwhile, to further reduce the network resource consumption and load caused by the transmission of control signals, an event-triggered mechanism for the controller–actuator channel is established. The theoretical analysis by Lyapunov indicates that the constructed closed-loop system for automatic berthing control is stable, and all the signals are bounded. Simulation and comparison are carried out to verify the effectiveness and superiority of proposed control scheme, and the results verify the conclusions and theoretical feasibility of this work. Full article

System representation via computational graphs has become a cornerstone of modern machine learning, underpinning the gradient-based training of complex models. We have previously introduced the Partial Lagrangian Method—a divide-and-conquer approach that decomposes the Lagrangian into link-wise components—to derive and evaluate the equations of motion for robot systems with dynamically changing structures. That method leverages the symbolic expressiveness of computational graphs with automatic differentiation to streamline dynamic analysis. In this paper, we advance this framework by establishing a principled way to encode time-dependent differential equations as computational graphs. Our approach, which augments the state vector and applies the chain rule, constructs fully time-independent graphs directly from the Lagrangian, eliminating the erroneous time-derivative embeddings that previously required manual correction. Because our transformation is derived from first principles, it guarantees graph correctness and generalizes to any system governed by variational dynamics. We validate the method on a simple serial-link robotic arm, showing that it faithfully reproduces the standard equations of motion without graph failure. Furthermore, by compactly representing state variables, the resulting computational graph achieves a seven-fold reduction in evaluation time compared to our prior implementation. The proposed framework thus offers a more intuitive, scalable, and efficient design and analysis of complex dynamic systems. Full article

Methane concentration anomalies during coal mining operations are identified as important factors triggering major safety accidents. This study aimed to address the key issues of insufficient adaptability of existing detection methods in dynamic and complex underground environments and limited characterization capabilities for non-uniform sampling data. Specifically, an intelligent diagnostic model was proposed by integrating the improved Dung Beetle Optimization Algorithm (SGDBO) with Transformer-SVM. A dual-path feature fusion architecture was innovatively constructed. First, the original sequence length of samples was unified by interpolation algorithms to adapt to deep learning model inputs. Meanwhile, statistical features of samples (such as kurtosis and differential standard deviation) were extracted to deeply characterize local mutation characteristics. Then, the Transformer network was utilized to automatically capture the temporal dependencies of concentration time series. Additionally, the output features were concatenated with manual statistical features and input into the LSSVM classifier to form a complementary enhancement diagnostic mechanism. Sine chaotic mapping initialization and a golden sine search mechanism were integrated into DBO. Subsequently, the SGDBO algorithm was employed to optimize the hyperparameters of the Transformer-LSSVM hybrid model, breaking through the bottleneck of traditional parameter optimization falling into local optima. Experiments reveal that this model can significantly improve the classification accuracy and robustness of anomaly curve discrimination. Furthermore, core technical support can be provided to construct coal mine safety monitoring systems, demonstrating critical practical value for ensuring national energy security production. Full article

Background/Objectives: Thyroid cancer encompasses distinct histological subtypes with varying biological behavior and treatment implications. Accurate preoperative subtype differentiation remains challenging. Although ultrasound (US) is widely used for thyroid nodule evaluation, qualitative assessment alone is often insufficient to distinguish between papillary (PTC), follicular (FTC), and medullary thyroid carcinoma (MTC). Methods: A retrospective analysis was performed on patients with histologically confirmed PTC, FTC, or MTC. A total of 224 standardized B-mode ultrasound images were analyzed. A set of fully quantitative features was extracted, including morphological characteristics (aspect ratio and perimeter-to-area ratio), internal echotexture (echogenicity and local entropy), boundary sharpness (gradient measures and KL divergence), and structural components (calcifications and cystic areas). Feature extraction was conducted using semi-automatic algorithms implemented in MATLAB. Statistical differences were assessed using the Kruskal–Wallis and Dunn–Šidák tests. A Random Forest classifier was trained and evaluated to determine the discriminatory performance of individual and combined features. Results: Significant differences (p < 0.05) were found among subtypes for key features such as perimeter-to-area ratio, normalized echogenicity, and calcification pattern. The full-feature Random Forest model achieved an overall classification accuracy of 89.3%, with F1-scores of 93.4% for PTC, 85.7% for MTC, and 69.1% for FTC. A reduced model using the top 10 features yielded an even higher accuracy of 91.8%, confirming the robustness and clinical relevance of the selected parameters. Conclusions: Subtype classification of thyroid cancer was effectively performed using quantitative ultrasound features and machine learning. The results suggest that biologically interpretable image-derived metrics may assist in preoperative decision-making and potentially reduce the reliance on invasive diagnostic procedures. Full article

This paper develops a theoretical framework for the computation of higher-order derivatives based on the algebra of hyper-dual numbers. Extending the classical dual number system, hyper-dual numbers provide a natural and rigorous mechanism for encoding and propagating derivative information through function composition and arithmetic operations. We formalize the underlying algebraic structure, define generalized hyper-dual extensions of scalar functions via multidimensional Taylor expansions, and establish consistency with standard differential calculus. The proposed approach enables exact computation of partial derivatives and mixed higher-order derivatives without resorting to symbolic manipulation or approximation schemes. We further investigate the algebraic properties and closure under differentiable operations, illustrating the method’s potential for unifying aspects of automatic differentiation with multivariable calculus. This study contributes to the theoretical foundation of algorithmic differentiation and highlights hyper-dual numbers as a precise and elegant tool in computational differential analysis. Full article

The design of automatic control systems is critical for ensuring safety in gas field surface engineering production. However, over-reliance on standardized design approaches within the context of automation technology can compromise system flexibility and neglect individualized cost-effectiveness considerations. This paper identifies a comprehensive evaluation method as the preferred approach for assessing station control systems by comparing the advantages and disadvantages of various common evaluation techniques. We propose an integrated semi-quantitative and quantitative evaluation method designed to comprehensively and accurately assess the effectiveness of station automatic control systems. For the semi-quantitative framework, we first establish a specific indicator system for the control system and employ the Analytic Hierarchy Process (AHP) to determine indicator weights tailored to different station types, achieving a scientific quantification of evaluation criteria. Additionally, we utilize quantitative calculation methods, specifically reliability and availability analyses, to evaluate the station’s automatic control system. Differential research is conducted to customize the evaluation based on the distinct process characteristics of various gas field stations. Differential design calculations and analyses were performed for a single station, improving the economy and adaptability of the automatic control system design. The proposed comprehensive evaluation method ensures the safe and stable operation of control system designs and provides a new approach for the automation and intelligent transformation of gas field surface engineering. Full article

Background: Mosquitoes from the Aedes (Ae.) genus are vectors of dengue, Zika, chikungunya, and other arboviruses, posing a significant public health threat. In 2005, Aedes aegypti was detected for the first time in Madeira Island, Portugal, in the city of Funchal, and has since become established in the region. In 2017, Aedes albopictus was detected for the first time in mainland Portugal. These invasion events require targeted entomological surveillance, which demands substantial human resources and a high management capacity for traditional vector monitoring. Following promising results obtained in laboratory conditions, a field-deployable model of a bioacoustic sensor for the automatic classification of mosquitoes integrated with a Biogents Sentinel trap as part of the VECTRACK system was tested in three regions in Portugal. Methods: The VECTRACK system was deployed in three locations: Funchal on Madeira Island, and Palmela and Algarve on mainland Portugal. Catch bags were manually inspected at intervals ranging from daily to weekly, resulting in a total of 38 captures in Madeira, 10 in Palmela, and 7 in the Algarve. Manual identifications were compared with those generated by the VECTRACK system, and the degree of correlation between the two datasets was assessed using Spearman’s rank correlation coefficient. Results: A total of 176 mosquitoes were captured in Madeira, 732 in Palmela, and 143 in the Algarve. Both manual and sensor-based identifications demonstrated similar performance, with high correlation observed between the two methods. Spearman’s rank correlation coefficients indicated high agreement for both female and male mosquitoes across all sites: Madeira: females = 0.84, males = 0.92, Palmela: females = 0.99, males = 0.84, Algarve: females = 0.98, and males = 0.99, all with p-values < 0.001. Conclusions: The VECTRACK system demonstrated strong performance in accurately distinguishing mosquitoes from non-mosquitoes, differentiating between Aedes and Culex genera, and identifying the sex of individual specimens. These promising results provide a solid foundation for the development of automated early warning systems and enhance mosquito surveillance strategies, which are critical for timely responses to potential vector-borne disease outbreaks. Full article

Background: Tracking differential growth of secondary liver metastases is important for early detection of progression but remains challenging due to variable tumor growth rates. We aimed to automate accurate, consistent, and efficient longitudinal monitoring. Methods: We developed an automatic 3D segmentation and tracking algorithm to quantify differential growth, tested on contrast-enhanced MRI follow-ups of patients with neuroendocrine liver metastases (NELMs). The output was integrated into a decision support tool to distinguish between progressive disease, stable disease, and partial/complete response. A user study involving an expert group of seven expert radiologists evaluated its impact. Group comparisons used the Friedman test with post hoc analyses. Results: Our algorithm detected 991 metastases in 30 patients: 13% new, 30% progressive, 18% stable, and 18% regressive; the remainder were either too small to measure (15%) or merged with another metastasis in the follow-up assessment (6%). Diagnostic accuracy improved with additional information on hepatic tumor load and differential growth, albeit not significantly (p = 0.72). The diagnosis time increased (p < 0.001). All radiologists found the method useful and expressed a desire to integrate it in existing diagnostic tools. Conclusions: We automated segmentation and quantification of individual NELMs, enabling comprehensive longitudinal analysis of differential tumor growth with the potential to enhance clinical decision-making. Full article

Housing vacancy rate is a key indicator for evaluating urban sustainable development. Due to rapid urbanization, population outflow and insufficient industrial support, the housing vacancy problem is particularly prominent in China’s underdeveloped regions. However, the lack of official data and the limitations of traditional survey methods restrict in-depth research. This study proposes a vacancy rate estimation method based on Baidu Street View residential exterior images and deep learning technology. Taking Nanning, Guangxi as a case study, an automatic discrimination model for residential vacancy status is constructed by identifying visual clues such as window occlusion, balcony debris accumulation, and facade maintenance status. The study first uses Baidu Street View API to collect images of residential communities in Nanning. After manual annotation and field verification, a labeled dataset is constructed. A pre-trained deep learning model (ResNet50) is applied to estimate the vacancy rate of the community after fine-tuning with labeled street view images of Nanning’s residential communities. GIS spatial analysis is combined to reveal the spatial distribution pattern and influencing factors of the vacancy rate. The results show that street view images can effectively capture vacancy characteristics that are difficult to identify with traditional remote sensing and indirect indicators, providing a refined data source and method innovation for housing vacancy research in underdeveloped regions. The study further found that the residential vacancy rate in Nanning showed significant spatial differentiation, and the vacancy driving mechanism in the old urban area and the emerging area was significantly different. This study expands the application boundaries of computer vision in urban research and fills the research gap on vacancy issues in underdeveloped areas. Its results can provide a scientific basis for the government to optimize housing planning, developers to make rational investments, and residents to make housing purchase decisions, thus helping to improve urban sustainable development and governance capabilities. Full article