Search Results (748)

Visual inspection remains a cornerstone of quality control in welded structures, yet manual evaluations are inherently constrained by subjectivity, inconsistency, and limited scalability. This study presents WeldVGG, a deep learning-based visual inspection model designed to automate weld defect classification using radiographic imagery. The proposed model is trained on the RIAWELC dataset, a publicly available collection of X-ray weld images acquired in real manufacturing environments and annotated across four defect conditions: cracking, porosity, lack of penetration, and no defect. RIAWELC offers high-resolution imagery and standardized class labels, making it a valuable benchmark for defect classification under realistic conditions. To improve trust and explainability, Grad-CAM++ is employed to generate class-discriminative saliency maps, enabling visual validation of predictions. The model is rigorously evaluated through stratified cross-validation and benchmarked against traditional machine learning baselines, including SVC, Random Forest, and a state-of-the-art architecture, MobileNetV3. The proposed model achieves high classification accuracy and interpretability, offering a practical and scalable solution for intelligent weld inspection. Furthermore, to prove the model’s ability to generalize, a test on the GDXray was performed, yielding positive results. Additionally, a Wilcoxon signed-rank test was conducted separately to assess statistical significance between model performances. Full article

Background: Muscle latency is an often-overlooked factor contributing to increased implant wear and higher rates of hip and knee osteoarthritis. Latency reduces the protective role of muscles against external joint loads during movement initiation, leading to cumulative microtrauma. This study investigates whether preliminary quadriceps contraction can mitigate these adverse effects during early rehabilitation after arthroplasty. Materials and methods: The study was conducted in two university hospitals in Sofia, Bulgaria, including 46 patients (mean age 63.76 ± 9.49 years): 25 with hip arthroplasty and 21 with knee arthroplasty. Participants were randomly assigned to a control group (n = 25; 13 hip, 12 knee: standard postoperative advice) or an experimental group (n = 21; 12 hip, 9 knee: standard advice plus preliminary quadriceps contraction). Primary outcome: pain intensity (VAS). Secondary outcomes: range of motion (ROM, %), manual muscle testing (MMT, %), thigh circumference difference (cm), and success rate of preliminary quadriceps contraction (%). Results: Both groups improved after one month (p < 0.05), but the experimental group showed significantly greater improvement (p < 0.05). Higher success rates of preliminary quadriceps contraction correlated with greater improvements in all outcomes (p < 0.05). Conclusions: Preliminary quadriceps contraction enhances standard postoperative advice by reducing pain, improving mobility and muscle strength, and reducing hypotrophy during early rehabilitation after hip and knee arthroplasty. Patients should be encouraged to perform it consistently, even when pain subsides. Full article

Potato leaf diseases are recognized as a major threat to agricultural productivity and global food security, emphasizing the need for rapid and accurate detection methods. Conventional manual diagnosis is limited by inefficiency and susceptibility to bias, whereas existing automated approaches are often constrained by insufficient feature extraction, inadequate integration of multiple leaves, and poor generalization under complex field conditions. To overcome these challenges, a ResNet18-SAWF model was developed, integrating a self-attention mechanism with a multi-scale feature-fusion strategy within the ResNet18 framework. The self-attention module was designed to enhance the extraction of key features, including leaf color, texture, and disease spots, while the feature-fusion module was implemented to improve the holistic representation of multi-leaf structures under complex backgrounds. Experimental evaluation was conducted using a comprehensive dataset comprising both simple and complex background conditions. The proposed model was demonstrated to achieve an accuracy of 98.36% on multi-leaf images with complex backgrounds, outperforming baseline ResNet18 (91.80%), EfficientNet-B0 (86.89%), and MobileNet_V2 (88.53%) by 6.56, 11.47, and 9.83 percentage points, respectively. Compared with existing methods, superior performance was observed, with an 11.55 percentage point improvement over the average accuracy of complex background studies (86.81%) and a 0.7 percentage point increase relative to simple background studies (97.66%). These results indicate that the proposed approach provides a robust, accurate, and practical solution for potato leaf disease detection in real field environments, thereby advancing precision agriculture technologies. Full article

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF motorized manipulator providing linear and rotational motions, with a stereo vision sensor mounted on the end effector, was deployed. In combination with a manual rotation plate, this configuration enhances accessibility and expands the field of view for crack monitoring. Another stereo vision sensor, mounted at the front of the robot, was used to acquire point cloud data of the surrounding environment, enabling tasks such as SLAM (simultaneous localization and mapping), path planning and following, and obstacle avoidance. Cracks are detected and segmented using the deep learning algorithms YOLO (You Only Look Once) v6-s and SFNet (Semantic Flow Network), respectively. To enhance the performance of crack segmentation, synthetic image generation and preprocessing techniques, including cropping and scaling, were applied. The dimensions of cracks are calculated using point clouds filtered with the median absolute deviation method. To validate the performance of the proposed crack-monitoring and mapping method with the robot system, indoor experimental tests were performed. The experimental results confirmed that, in cases of divided imaging, the crack propagation direction was predicted, enabling robotic manipulation and division-point calculation. Subsequently, total crack length and width were calculated by combining reconstructed 3D point clouds from multiple frames, with a maximum relative error of 1%. Full article

Background: Bladder cancer (BLCA) is a malignant growth that originates from the urothelial lining of the urinary bladder. Diagnosing BLCA is complex due to the variety of tumor features and its heterogeneous nature, which leads to significant morbidity and mortality. Understanding tumor histopathology is crucial for developing tailored therapies and improving patient outcomes. Objectives: Early diagnosis and treatment are essential to lower the mortality rate associated with bladder cancer. Manual classification of muscular tissues by pathologists is labor-intensive and relies heavily on experience, which can result in interobserver variability due to the similarities in cancerous cell morphology. Traditional methods for analyzing endoscopic images are often time-consuming and resource-intensive, making it difficult to efficiently identify tissue types. Therefore, there is a strong demand for a fully automated and reliable system for classifying smooth muscle images. Methods: This paper proposes a deep learning (DL) technique utilizing the EfficientNet-B3 model and a five-fold cross-validation method to assist in the early detection of BLCA. This model enables timely intervention and improved patient outcomes while streamlining the diagnostic process, ultimately reducing both time and costs for patients. We conducted experiments using the Endoscopic Bladder Tissue Classification (EBTC) dataset for multiclass classification tasks. The dataset was preprocessed using resizing and normalization methods to ensure consistent input. In-depth experiments were carried out utilizing the EBTC dataset, along with ablation studies to evaluate the best hyperparameters. A thorough statistical analysis and comparisons with five leading DL models—ConvNeXtBase, DenseNet-169, MobileNet, ResNet-101, and VGG-16—showed that the proposed model outperformed the others. Conclusions: The EfficientNet-B3 model achieved impressive results: accuracy of 99.03%, specificity of 99.30%, precision of 97.95%, recall of 96.85%, and an F1-score of 97.36%. These findings indicate that the EfficientNet-B3 model demonstrates significant potential in accurately and efficiently diagnosing BLCA. Its high performance and ability to reduce diagnostic time and cost make it a valuable tool for clinicians in the field of oncology and urology. Full article

Background. Automatic detection of Sit phases in people with Parkinson’s disease (PD) using a single body-worn sensor is crucial for enhancing long-term, home-based monitoring of mobility. Aim. The aim of this study was to enhance the accuracy of detecting and segmenting Sit phases in people with PD using a single SmartWatch worn at the ankle. Method. Twenty-two patients living with PD performed activities of daily living that incorporate repeated transitions to a seated position in a simulated free-living environment during 3 min, 4 min, and 5 min trials. Tri-axial accelerations and angular velocities of the right or left ankle were recorded at 50 Hz using a SmartWatch. Random forest algorithms were trained using raw and filtered data to automatically detect and segment Sit phases. Sensibility, specificity, and F-scores were calculated based on manual segmentation using the OptiTrack motion capture system. Results. Sensibility, specificity, and F-score achieved 78.3%, 93.8%, and 84.7% for Sit phase detection of the 3 min trial; 78.8%, 85.5%, and 80.6% for Sit phase detection of the 4 min trial; and 71.6%, 84.8%, and 75.6% for Sit phase detection of the 5 min trial. The median time difference between the manual and automatic segmentation was 0.95s, 0.89s, and 0.84s, respectively, for the 3 min, 4 min, and 5 min trial. Conclusion. This study demonstrates that a random forest algorithm can accurately detect and segment Sit phases in people with PD using data from a single ankle-worn SmartWatch. The algorithm’s performance was comparable to manual segmentation, while substantially reducing the time and effort required. These findings represent a meaningful step forward in enabling efficient, long-term, and home-based monitoring of mobility and symptom progression in people with PD. Full article

Natural latex harvest is pushing the boundaries of unmanned agricultural production in rubber milk collection via integrated robots in hilly and mountainous regions, such as the fixed and mobile tapping robots widely deployed in forests. As there are bad working conditions and complex natural environments surrounding rubber trees, the real-time and precision assessment of rubber milk yield status has emerged as a key requirement for improving the efficiency and autonomous management of these kinds of large-scale automatic tapping robots. However, traditional manual rubber milk yield status detection methods are limited in their ability to operate effectively under conditions involving complex terrain, dense forest backgrounds, irregular surface geometries of rubber milk, and the frequent occlusion of rubber milk bowls (RMBs) by vegetation. To address this issue, this study presents an unmanned aerial vehicle (UAV) imagery rubber milk yield state detection method, termed YOLOv8n-RMB, in unstructured field environments instead of manual watching. The proposed method improved the original YOLOv8n by integrating structural enhancements across the backbone, neck, and head components of the network. First, a receptive field attention convolution (RFACONV) module is embedded within the backbone to improve the model’s ability to extract target-relevant features in visually complex environments. Second, within the neck structure, a bidirectional feature pyramid network (BiFPN) is applied to strengthen the fusion of features across multiple spatial scales. Third, in the head, a content-aware dynamic upsampling module of DySample is adopted to enhance the reconstruction of spatial details and the preservation of object boundaries. Finally, the detection framework is integrated with the BoT-SORT tracking algorithm to achieve continuous multi-object association and dynamic state monitoring based on the filling status of RMBs. Experimental evaluation shows that the proposed YOLOv8n-RMB model achieves an AP@0.5 of 94.9%, an AP@0.5:0.95 of 89.7%, a precision of 91.3%, and a recall of 91.9%. Moreover, the performance improves by 2.7%, 2.9%, 3.9%, and 9.7%, compared with the original YOLOv8n. Plus, the total number of parameters is kept within 3.0 million, and the computational cost is limited to 8.3 GFLOPs. This model meets the requirements of yield assessment tasks by conducting computations in resource-limited environments for both fixed and mobile tapping robots in rubber plantations. Full article

Timely and accurate traffic information is crucial for maintaining safety and efficiency on motorway networks. This research examines time delays in traffic information transmission through intelligent transport systems (ITSs) and cooperative intelligent transport systems (C-ITSs) on the Slovenian motorway network. The aim of the research is to assess the effectiveness of existing notification systems and the impact of time delays on the timely informing of drivers in the event of an accident in a tunnel. Using real-world data from Regional Traffic Center (RCC) in Vransko, manual and automated activations of traffic portals and different update frequencies of the Promet+ mobile application were analyzed during peak hours. Results show that automated activation reduces delays from 34 to 25 s at portals and from 27 to 18 s in the Promet+ app. Continuous updates in the app provided the highest driver coverage, leaving only 15 uninformed drivers in the morning peak and 8 in the afternoon, whereas 60 s update intervals left up to 71 drivers uninformed. These findings highlight the effectiveness of automation and continuous updates in minimizing delays and improving driver awareness. The research contributes by quantifying latency in ITSs and C-ITSs and demonstrating that their combined use offers the most reliable information delivery. Future improvements should focus on hybrid integration of ITS and C-ITS, dynamic update intervals, and infrastructure upgrades to ensure consistent real-time communication, shorter response times, and enhanced motorway safety. Full article

Lumbar spine pain (LBP) is a leading cause of disability worldwide and remains a major challenge in clinical practice. Among non-invasive treatment strategies, manual therapy plays a central role, offering individualized interventions that target both biomechanical dysfunction and pain. This narrative review compares three commonly used physiotherapeutic approaches—Kaltenborn-Evjenth mobilization, the McKenzie method, and high-velocity low-amplitude (HVLA) manipulation—based on current evidence regarding their effectiveness, safety, and clinical application. A total of 32 randomized controlled trials, systematic reviews, and meta-analyses published between 2003 and 2024 were analyzed. The Kaltenborn-Evjenth method demonstrated notable effectiveness in improving range of motion and reducing chronic pain, particularly in patients with segmental hypomobility. The McKenzie method showed strong outcomes in both acute and chronic LBP, especially in cases involving symptom centralization and high patient engagement. HVLA techniques offered rapid symptom relief in acute phases but required careful patient selection due to their mechanical intensity. The findings suggest that no single method is universally superior. Instead, optimal outcomes are achieved through individualized treatment plans that integrate multiple techniques based on clinical presentation, pain chronicity, and functional limitations. Multimodal strategies that combine manual therapy with exercise and patient education appear to be the most effective in managing LBP and preventing recurrence. Full article

In clinical medicine, rats are commonly used as experimental subjects. However, their estrous cycle significantly impacts their biological responses, leading to differences in experimental results. Therefore, accurately determining the estrous cycle is crucial for minimizing interference. Manually identifying the estrous cycle in rats presents several challenges, including high costs, long training periods, and subjectivity. To address these issues, this paper proposes a classification network, Spatial Long-distance EfficientNet (SLENet). This network is designed based on EfficientNet, specifically modifying the Mobile Inverted Bottleneck Convolution (MBConv) module by introducing a novel Spatial Efficient Channel Attention (SECA) mechanism to replace the original Squeeze Excitation (SE) module. Additionally, a non-local attention mechanism is incorporated after the last convolutional layer to enhance the network’s ability to capture long-range dependencies. On 2655 microscopy images of rat vaginal epithelial cells (with 531 test), SLENet achieves 96.31% accuracy, surpassing EfficientNet (94.20%). This finding provides practical value for optimizing experimental design in rat-based studies such as reproductive and pharmacological research, but this study is limited to microscopy image data, without considering other factors; thus, future work could incorporate temporal pattern and multi-modal inputs to further enhance robustness. Full article

Fish capture usually requires classification of fish species, and the cost of manual classification is relatively high. Recently, deep learning has been widely applied in the fishery field. Transfer learning was conducted on ResNet18, ShuffleNet, EfficientNet, MobileNetV3, and YOLOv8. Through analysis of the influence of the law of learning rate on accuracy during the network learning process, a variable-step learning rate optimization strategy was proposed. Experimental results indicate that the optimal learning rates for fish classification utilizing this strategy were determined to be 0.01, 0.015, 0.001, 0.001, and 0.006 for ResNet18, ShuffleNet, EfficientNet, MobileNetV3, and YOLOv8, respectively. The recognition accuracy rates on the sample set reach 96.33%, 96.74%, 97.50%, 86.73%, 88.49%, respectively, and the average recognition accuracy rate between the sample set and other multi-species interfering fish reaches 93.13%, 93.44%, 96.13%, 95.21%, and 92.16%, respectively. This enables high-precision and rapid sorting of the target fish and other multi-species interfering fish. Compared with global optimization, the number of optimizations can be reduced by more than 97.1%; and compared with the same number of optimizations, the accuracy can be improved by more than 34.21%, which improves the efficiency and accuracy of network training and provides a theoretical reference for the setting of learning rate during model training in the field of deep learning. Full article

Background/Objectives: Cervicogenic headache (CeH) is linked to upper cervical dysfunctions. The obliquus capitis inferior (OCI) muscle may contribute to restricted cervical rotation at the C1–C2 level, altered proprioception and pain. Dry needling (DN) of the OCI is hypothesized to target these dysfunctions. The aim of this study was to investigate whether a single intervention combining DN and manual therapy (MT) compared to sham needling (SN) and MT, improves C1–C2 rotation, functional, headache-related and psychological outcomes in a subgroup of CeH patients with a positive cervical flexion–rotation test (CFRT). Methods: Thirty-four participants were randomly assigned to (1) DN or (2) SN. The primary outcome was C1–C2 rotational mobility. Secondary outcomes included headache-related parameters (frequency, intensity, duration and perceived effect), functional parameters (cervical mobility, pain pressure thresholds, motor control and proprioception) and psychological parameters (central sensitization, pain catastrophizing, coping strategies and kinesiophobia). Outcomes were re-evaluated at one-week follow-up. Results: Linear mixed-effects models showed a significant and clinically relevant increase of C1–C2 rotation in the DN group compared to the SN group post-intervention (mean difference [MD]: 4.51°; 95% confidence interval [CI]: 1.74; 7.28), which was maintained at the 1-week follow-up (MD: 5.44°; 95% CI: 2.55; 8.33). No clinically relevant changes were observed in other secondary outcome measures. Conclusions: Targeting the OCI may be of added value in restoring atlanto-axial dysfunction. While short-term mobility gains were observed, a single intervention appears insufficient as a stand-alone treatment to impact functional or psychological outcomes. Future research involving larger samples should examine DN effects as part of a multimodal approach with long-term follow-up. Full article

Objectives: This study aimed to evaluate the available evidence on the use of orthodontic mini-implants (MIs) as temporary anchorage devices (TADs), with particular focus on how insertion angulation may influence clinical outcomes. A clinical case report was also included to complement the review findings. Methods: A systematic review was performed following PRISMA guidelines and a focused PICO question. Searches in PubMed, Web of Science, and Scopus, supplemented by manual screening of reference lists. Duplicates, systematic reviews, and studies outside the PICO scope were excluded. An observational analysis of CBCT and intraoral images, and a clinical case report, were evaluated with a standardized protocol for angulation classification based on anatomical landmarks and angular measurements. Results: Ten studies met the eligibility criteria. Most reported high survival rates, with stability defined by the absence of TAD mobility or loss. CBCT-derived data from two studies, together with one clinical case, demonstrated maintenance of alveolar bone. Improved outcomes were occasionally associated with changes in insertion angulation. Vertical positioning was more frequently linked to complications in shorter TADs, while horizontal placement preserved bone but introduced hygiene-related difficulties. Conclusions: TAD success and bone preservation may depend on insertion angulation, TAD size, and soft tissue conditions. Further standardized prospective studies are needed to validate these findings, particularly regarding intermediate diagonal insertion angles (between vertical and horizontal) extending from palatal to buccal, as observed in our clinical case, which is not yet reported in the literature. Full article

Background: Midfacial trauma involving the zygomatic-maxillary-orbital (ZMO) complex poses significant reconstructive challenges due to anatomical complexity and the necessity for high-precision alignment. Traditional manual reduction techniques often result in inconsistent outcomes, necessitating revisions. Methods: This feasibility study presents two clinical cases treated using a novel, fully digital workflow incorporating computer-aided design and manufacturing (CAD/CAM) of patient-specific osteosynthesis plates and surgical drill guides. Following virtual fracture reduction and implant design, drill guides and implants were fabricated using selective laser melting. Surgical procedures included intraoral and transconjunctival approaches with intraoperative 3D imaging (mobile C-arm CT) to verify implant positioning. Postoperative results were compared to the virtual plan through image fusion. Results: Both cases demonstrated precise fit and anatomical restoration. The “one-position-fits-only” orbital implant design enabled highly accurate orbital wall reconstruction. Key procedural refinements between cases included enhanced interdisciplinary collaboration and improved guide designs, resulting in decreased planning-to-surgery intervals (<7 days) and seamless intraoperative application. Image fusion confirmed near-identical congruence between planned and achieved outcomes. Conclusions: The presented method demonstrates that fully digital, CAD/CAM-based midface reconstruction is feasible in the primary trauma setting. The technique offers reproducible precision, reduced intraoperative time, and improved functional and aesthetic outcomes. It may represent a paradigm shift in trauma care, particularly for complex ZMO fractures. Broader clinical adoption appears viable as production speed and workflow integration continue to improve. Full article

Concrete infrastructure inspection is essential for maintaining the safety and longevity of urban environments. Traditional manual crack detection methods are labor-intensive, inconsistent, and difficult to scale. Recent advancements in deep learning and computer vision offer automated alternatives, particularly when deployed via unmanned aerial vehicles (UAVs) for enhanced coverage and flexibility. However, achieving real-time performance on embedded systems requires models that are not only accurate but also lightweight and computationally efficient. This study presents CrackDetect-Lite, a comparative analysis of three deep learning architectures for binary crack detection using the SDNET2018 benchmark dataset: CNNSimple (a custom lightweight model), RSNet (a shallow residual network), and MobileVNet (a fine-tuned MobileNetV2). Class imbalance was addressed using a weighted cross-entropy loss function, and models were evaluated across multiple criteria including classification accuracy, crack-class F1-score, inference latency, and model size. Among the models, MobileVNet achieved the best balance between detection performance and deployability, with an accuracy of 90.5% and a crack F1-score of 0.73, while maintaining a low computational footprint suitable for UAV-based deployment. These findings demonstrate that carefully selected lightweight CNN architectures can deliver reliable, real-time crack detection, supporting scalable and autonomous infrastructure monitoring in smart city systems. Full article