Search Results (1,150)

Background: Brain computed tomography (CT) is the primary imaging modality for patients with acute neurological complaints in emergency departments, despite having a low diagnostic yield for many conditions. This study aimed to assess the common indications for brain CT, evaluate the prevalence of acute pathologies, and explore whether certain patient groups may be overexposed to unnecessary scans, impacting both patient safety and healthcare costs. Methods: We conducted a retrospective review of brain CT requests from the General Emergency Department in a single center over a one-month period. We recorded patient demographics (sex, age), scan indications, presence of focal neurological symptoms, acute pathology on CT, and final diagnoses. Descriptive statistics, including means ± SEM, were calculated using GraphPad Prism version 10.4.1. Results: A total of 584 brain CT scans were requested, of which 532 (91.1%) were normal, and 52 (8.9%) showed acute pathology. The age of all included patients were 70.8 ± 0.7 years with women (n = 304, 52.1%) being 71.9 ± 1.0 years old and men (n = 280, 47.9%) 69.7 ± 1.0 years old (p > 0.1). The most common indication for CT was head trauma (265, 45.4%) followed by ischemic stroke (130, 22.3%). The most frequent pathologies were ischemic stroke (2.7%), subdural hematoma (1.7%), and other traumatic bleeds (1.7%). Of the 52 patients with acute pathology, 42 (80.8%) exhibited focal neurological deficits. Conclusions: 91.1% of the brain CT scans in the emergency department were normal and did not lead to further intervention. While this may indicate a low diagnostic yield in certain patient groups—particularly those presenting with mild or nonspecific neurological symptoms—it does not alone confirm overuse. These findings highlight the importance of careful clinical evaluation to optimize imaging decisions. Reducing potentially unnecessary brain CT scans could lower healthcare costs and minimize radiation exposure, but the health-economic impact depends on balancing the savings with the potential costs of missing critical diagnoses and the associated societal consequences. Full article

Background and Objectives: The Drosophila retinal determination network comprises the transcription factor Teashirt (Tsh) and the transcription co-regulator C-terminal Binding Protein (CtBP), both of which are essential for normal adult eye development. Both Tsh and CtBP show a pattern of co-expression in the proliferating cells anterior to the morphogenetic furrow that demarcates the boundary between the anteriorly placed proliferating eye precursor cells and the posteriorly placed differentiating photoreceptor cells in the larval eye-precursor tissue, the eye–antennal disc. The disc ultimately develops into the adult compound eyes, antenna, and other head structures. Both Tsh and CtBP were found to interact genetically during ectopic eye formation in Drosophila, and both were present in molecular complexes purified from gut and cultured cells. However, it remained unknown whether Tsh and CtBP molecules could interact in the eye–antennal discs and elicit an effect on eye development. The present study answers these questions. Methods: 5′ GFP-tagging of the tsh gene in the Drosophila genome and 5′ FLAG-tagging of the ctbp gene were accomplished by the CRISPR-Cas9 and BAC recombineering methods, respectively, to produce GFP-Tsh- and FLAG-CtBP-fused proteins in specific transgenic Drosophila strains. Verification of these proteins’ expression in the larval eye–antennal discs was performed by immunohistological staining and confocal microscopy. Genetic screening was performed to establish functional interaction between Tsh and CtBP during eye development. Scanning Electron Microscopy was performed to image the adult eye structure. Co-immunoprecipitation and GST pulldown assays were performed to show that Tsh and CtBP interact in the cells of the third instar eye–antennal discs. Results: This study reveals that Tsh and CtBP interact genetically and physically in the Drosophila third instar larval eye–antennal disc to regulate adult eye development. This interaction is likely to limit the population of the eye precursor cells in the larval eye disc of Drosophila. Conclusions: The relative abundance of Tsh and CtBP in the third instar larval eye–antennal disc can dictate the outcome of their interaction on the Drosophila eye formation. Full article

Heat stress severely impacts pig welfare and farm productivity. However, existing methods lack the capability to detect subtle physiological cues (e.g., skin erythema) in complex farm environments while maintaining real-time efficiency. This paper proposes PigStressNet, a novel lightweight detector designed for accurate and efficient heat stress recognition. Our approach integrates four key innovations: (1) a Normalization-based Attention Module (NAM) integrated into the backbone network enhances sensitivity to localized features critical for heat stress, such as posture and skin erythema; (2) a Rectangular Self-Calibration Module (RCM) in the neck network improves spatial feature reconstruction, particularly for occluded pigs; (3) an MBConv-optimized detection head (MBHead) reduces computational cost in the head by 72.3%; (4) the MPDIoU loss function enhances bounding box regression accuracy in scenarios with overlapping pigs. We constructed the first fine-grained dataset specifically annotated for pig heat stress (comprising 710 images across 5 classes: standing, eating, sitting, lying, and stress), uniquely fusing posture (lying) and physiological traits (skin erythema). Experiments demonstrate state-of-the-art performance: PigStressNet achieves 0.979 mAP for heat stress detection while requiring 15.9% lower computation (5.3 GFLOPs) and 11.7% fewer parameters compared to the baseline YOLOv12-n model. The system achieves real-time inference on embedded devices, offering a viable solution for intelligent livestock management. Full article

Introduction: Sperm morphology is a fundamental parameter in the evaluation of male infertility, offering critical insights into reproductive health. However, traditional manual assessments under microscopy are limited by operator dependency and subjective interpretation caused by biological variation. To overcome these limitations, there is a need for accurate and fully automated classification systems. Objectives: This study aims to develop a two-stage, fully automated sperm morphology classification framework that can accurately identify a wide spectrum of abnormalities. The framework is designed to reduce subjectivity, minimize misclassification between visually similar categories, and provide more reliable diagnostic support in reproductive healthcare. Methods: A novel two-stage deep learning-based framework is proposed utilizing images from three staining-specific versions of a comprehensive 18-class dataset. In the first stage, sperm images are categorized into two principal groups: (1) head and neck region abnormalities, and (2) normal morphology together with tail-related abnormalities. In the second stage, a customized ensemble model—integrating four distinct deep learning architectures, including DeepMind’s NFNet-F4 and vision transformer (ViT) variants—is employed for detailed abnormality classification. Unlike conventional majority voting, a structured multi-stage voting strategy is introduced to enhance decision reliability. Results: The proposed framework consistently outperforms single-model baselines, achieving accuracies of 69.43%, 71.34%, and 68.41% across the three staining protocols. These results correspond to a statistically significant 4.38% improvement over prior approaches in the literature. Moreover, the two-stage system substantially reduces misclassification among visually similar categories, demonstrating enhanced ability to detect subtle morphological variations. Conclusions: The proposed two-stage, ensemble-based framework provides a robust and accurate solution for automated sperm morphology classification. By combining hierarchical classification with structured decision fusion, the method advances beyond traditional and single-model approaches, offering a reliable and scalable tool for clinical decision-making in male fertility assessment. Full article

In this study, a new approach was developed for the estimation of optimum parameters (ODP), in terms of materials and design in livestock barns, and for optimal design. For this purpose, two thousand simulations were run using Monte Carlo (MC) techniques and Latin hypercube methods using the Energy Plus program on a 50-head closed dairy farm. In this study, the heat balance in the barn was adapted to Energy Plus using an innovative approach, using heat balance equations according to the ASHRAE Standard. First, data normality was determined using the Shapiro–Wilk (SW) and Kolmogorov–Smirnov (KS) tests. Data on thermal stress duration and energy consumption for dairy cattle welfare were estimated directly from the simulations, and sensitivity (SA) and uncertainty (UA) analyses were conducted. Furthermore, the statistical relationship between thermal comfort and energy consumption was determined using Pearson correlation. The predicted values obtained from the simulations were validated with barn values, and time-series overlay plots and histograms were generated. Furthermore, interpretations of the validation processes were made based on MBE, RSME, and R² statistical values. The study estimated an indoor thermal comfort temperature of 12 °C, and this value was taken into account in the innovatively developed simulations. The estimated optimum design parameters in the study resulted in energy reductions of 25% and 41% for walls and roofs, 48% and 19% for cooling and heating setpoint temperatures, 43% and 37% for window areas, and 75% and 40% for natural and mechanical ventilation, respectively. When the design parameters were evaluated holistically and analyzed in terms of average values, the new simulation model achieved approximately 50% energy savings. We believe that the newly developed approach will guide future planning for countries, the public, and private sectors to ensure animal welfare and reduce energy consumption. Full article

Background/Objectives: Low semen quality and male infertility are critical global health issues. Emerging research highlights that nutritional factors could play a significant role in determining reproductive outcomes. Understanding and optimizing these dietary influences, including the role of polyphenols, is crucial for developing targeted strategies to improve male fertility. We aimed to explore the relationship between the intake of different classes of polyphenols and semen quality indicators in a cohort of healthy young males. Methods: This is a secondary analysis involving 106 male individuals, aged 18–35 years, from the FERTINUTS trial. Dietary intake was assessed using 3-day dietary records, and semen quality parameters were analyzed. Multivariable linear regression analysis was employed to evaluate the associations between dietary polyphenol consumption and semen quality indicators. Results: Our findings revealed both positive and negative associations between polyphenol consumption and sperm morphology parameters. A higher intake of total polyphenols was associated with a lower percentage of abnormalities in sperm heads but a higher rate of abnormalities in the principal piece. Similar results were observed for lignan and flavonoid intake. Additionally, a higher intake of flavonoids was also associated with a greater percentage of normal sperm forms. In contrast, a higher dietary intake of stilbenes was associated with a higher percentage of combined abnormalities. Conclusions: Higher intake of polyphenols, particularly flavonoids and lignans, was associated with improved sperm head morphology but also with increased tail abnormalities, although no associations with motility or vitality were observed. These results suggest that specific polyphenol classes may have both beneficial and adverse effects on sperm structure, warranting consideration of compound type and dosage in dietary recommendations. Further studies are needed to determine whether these morphological changes impact fertilization outcomes and reproductive potential. Full article

Underwater debris detection plays a crucial role in marine environmental protection. However, existing object detection algorithms generally suffer from excessive model complexity and insufficient detection accuracy, making it difficult to meet the real-time detection requirements in resource-constrained underwater environments. To address this challenge, this paper proposes a novel lightweight object detection network named the Shared Pyramid Lightweight Network (SPyramidLightNet). The network adopts an improved architecture based on YOLOv11 and achieves an optimal balance between detection performance and computational efficiency by integrating three core innovative modules. First, the Split–Merge Attention Block (SMAB) employs a dynamic kernel selection mechanism and split–merge strategy, significantly enhancing feature representation capability through adaptive multi-scale feature fusion. Second, the C3 GroupNorm Detection Head (C3GNHead) introduces a shared convolution mechanism and GroupNorm normalization strategy, substantially reducing the computational complexity of the detection head while maintaining detection accuracy. Finally, the Shared Pyramid Convolution (SPyramidConv) replaces traditional pooling operations with a parameter-sharing multi-dilation-rate convolution architecture, achieving more refined and efficient multi-scale feature aggregation. Extensive experiments on underwater debris datasets demonstrate that SPyramidLightNet achieves 0.416 on the mAP@0.5:0.95 metric, significantly outperforming mainstream algorithms including Faster-RCNN, SSD, RT-DETR, and the YOLO series. Meanwhile, compared to the baseline YOLOv11, the proposed algorithm achieves an 11.8% parameter compression and a 17.5% computational complexity reduction, with an inference speed reaching 384 FPS, meeting the stringent requirements for real-time detection. Ablation experiments and visualization analyses further validate the effectiveness and synergistic effects of each core module. This research provides important theoretical guidance for the design of lightweight object detection algorithms and lays a solid foundation for the development of automated underwater debris recognition and removal technologies. Full article

Aero-engines, as complex systems integrating numerous rotating components and accessory equipment, operate under harsh and demanding conditions. Prolonged use often leads to frequent mechanical wear and surface defects on accessory parts, which significantly compromise the engine’s normal and stable performance. Therefore, accurately and rigorously identifying failure modes is of critical importance. In this study, failure modes are categorized into notches, scuffs, and scratches based on original bearing structure images. The YOLOv8 architecture is adopted as the base framework, and a Dilated Reparameterization Block (DRB) is introduced to enhance the Dilation-Wise Residual (DWR) module. This structure uses a large convolutional kernel to capture fragmented and sparse features in wear images, ensuring a wide receptive field. The concept of structural reparameterization is incorporated into DWR to improve its ability to capture detailed target information. Additionally, the standard convolutional layer in the head of the improved DWR-DRB structure is replaced by Spatial-Depth Convolution (SPD-Conv) to reduce the loss of wear morphology and enhance the accuracy of fault feature extraction. Finally, a fusion structure combining Focaler and MPDIoU is integrated into the loss function to leverage their strengths in handling imbalanced classification and bounding box geometric regression. The proposed method achieves effective recognition and diagnosis of mechanical wear fault patterns. The experimental results demonstrate that, compared to the baseline YOLOv8, the proposed method improves the mAP50 for fault diagnosis and recognition from 85.4% to 91%. Full article

Background: Leber’s hereditary optic neuropathy (LHON) is the most common mitochondrial disorder and an inherited optic neuropathy. Recently, two different LHON inheritance types have been discovered: mitochondrially inherited LHON (mtLHON) and autosomal recessive LHON (arLHON). Our case report is the first diagnosed case of arLHON in a patient of Lithuanian descent and confirms the DnaJ Heat Shock Protein Family (Hsp40) Member C30 (DNAJC30) c.152A>G p.(Tyr51Cys) founder variant. Case Presentation: A 34-year-old Lithuanian man complained of headache and sudden, painless loss of central vision in his right eye. On examination, the visual acuity of the right and left eyes was 0.1 and 1.0, respectively. Visual-field examination revealed a central scotoma in the right eye, and visual evoked potentials (VEPs) showed prolonged latency in both eyes. Optical coherence tomography showed thickening of the retinal nerve fiber layer in the upper quadrant of the optic disk in the left eye. Magnetic resonance imaging of the head showed evidence of optic nerve inflammation in the right eye. Blood tests were within normal range and showed no signs of inflammation. Retrobulbar neuritis of the right eye was suspected, and the patient was treated with steroids, which did not improve visual acuity. He later developed visual loss in the left eye as well. A genetic origin of the optic neuropathy was suspected, and a complete mitochondrial DNA analysis was performed, but it did not reveal any pathologic mutations. Over time, the visual acuity of both eyes slowly deteriorated, and the retinal nerve fiber layer (RNFL) thinning of the optic disks progressed. A multidisciplinary team of specialists concluded that vasculitis or infectious disease was unlikely to be the cause of the vision loss, and a genetic cause for the disease was still suspected, although a first-stage genetic test did not yield the diagnosis. Thirty-three months after disease onset, whole-exome sequencing revealed a pathogenic variant in the DNAJC30 gene, leading to the diagnosis of arLHON. Treatment with Idebenone was started 35 months after the onset of the disease, resulting in no significant worsening of the patient’s condition. Conclusion: This case highlights the importance of considering arLHON as a possible diagnosis for patients with optic neuropathy, because the phenotype of arLHON appears to be identical to that of mtLHON and cannot be distinguished by clinicians. Full article

In maritime blurred image recognition, ship collision accidents frequently result from three primary blur types: (1) motion blur from vessel movement in complex sea conditions, (2) defocus blur due to water vapor refraction, and (3) scattering blur caused by sea fog interference. This paper proposes a dual-branch recognition method specifically designed for motion blur, which represents the most prevalent blur type in maritime scenarios. Conventional approaches exhibit constrained computational efficiency and limited adaptability across different modalities. To overcome these limitations, we propose a hybrid CNN–Transformer architecture: the CNN branch captures local blur characteristics, while the enhanced Transformer module models long-range dependencies via attention mechanisms. The CNN branch employs a lightweight ResNet variant, in which conventional residual blocks are substituted with Multi-Scale Gradient-Aware Residual Block (MSG-ARB). This architecture employs learnable gradient convolution for explicit local gradient feature extraction and utilizes gradient content gating to strengthen blur-sensitive region representation, significantly improving computational efficiency compared to conventional CNNs. The Transformer branch incorporates a Hierarchical Swin Transformer (HST) framework with Shifted Window-based Multi-head Self-Attention for global context modeling. The proposed method incorporates blur invariant Positional Encoding (PE) to enhance blur spectrum modeling capability, while employing DyT (Dynamic Tanh) module with learnable α parameters to replace traditional normalization layers. This architecture achieves a significant reduction in computational costs while preserving feature representation quality. Moreover, it efficiently computes long-range image dependencies using a compact 16 × 16 window configuration. The proposed feature fusion module synergistically integrates CNN-based local feature extraction with Transformer-enabled global representation learning, achieving comprehensive feature modeling across different scales. To evaluate the model’s performance and generalization ability, we conducted comprehensive experiments on four benchmark datasets: VAIS, GoPro, Mini-ImageNet, and Open Images V4. Experimental results show that our method achieves superior classification accuracy compared to state-of-the-art approaches, while simultaneously enhancing inference speed and reducing GPU memory consumption. Ablation studies confirm that the DyT module effectively suppresses outliers and improves computational efficiency, particularly when processing low-quality input data. Full article

Background: Monocarboxylate-transporter-8-(MCT8) deficiency, or Allan–Herndon–Dudley syndrome (AHDS), is a rare X-linked disorder caused by pathogenic variants in the SLC16A2 gene, leading to impaired transport of thyroid hormones, primarily T3 and T4, across cell membranes. The resulting central hypothyroidism and peripheral hyperthyroidism cause neurodevelopmental impairment and thyrotoxicosis. Despite the availability of therapy options, e.g., with triiodothyroacetic acid (TRIAC), diagnosis is often delayed, partly due to normal TSH levels or incomplete genetic panels. MCT8 deficiency is not yet included in newborn-screening programs worldwide. Case Description: We present a case of an infant genetically diagnosed with MCT8 deficiency at 5 months of age after presenting with muscular hypotonia, lack of head control, and developmental delay. Thyroid function testing revealed a normal TSH, low free T4, and significantly elevated free T3 and free T3/T4 ratio. Treatment with TRIAC (Emcitate^®) was initiated promptly, with close drug monitoring. Despite persistent motor deficits and dystonia, some developmental progress was observed, as well as reduction in hyperthyroidism. Discussion/Conclusions: This case underscores the importance of early free T3 and fT3/fT4 ratio testing in infants with unexplained developmental delay. Broader inclusion of SLC16A2 in genetic panels and consideration of newborn screening could improve early diagnosis and outcomes in this rare but treatable condition. Full article

Transmission lines are widely distributed in complex environments, making them susceptible to foreign object intrusion, which could lead to serious consequences, i.e., power outages. Currently, foreign object detection on transmission lines is primarily conducted through UAV-based field inspections. However, the captured data must be transmitted back to a central facility for analysis, resulting in low efficiency and the inability to perform real-time, industrial-grade detection. Although recent YOLO series models can be deployed on UAVs for object detection, these models’ substantial computational requirements often exceed the processing capabilities of UAV platforms, limiting their ability to perform real-time inference tasks. In this study, we propose a novel lightweight detection algorithm, SCL-YOLOv8, which is based on the original YOLO model. We introduce StarNet to replace the CSPDarknet53 backbone as the feature extraction network, thereby reducing computational complexity while maintaining high feature extraction efficiency. We design a lightweight module, CGLU-ConvFormer, which enhances multi-scale feature representation and local feature extraction by integrating convolutional operations with gating mechanisms. Furthermore, the detection head of the original YOLO model is improved by introducing shared convolutional layers and group normalization, which helps reduce redundant computations and enhances multi-scale feature fusion. Experimental results demonstrate that the proposed model not only improves the detection accuracy but also significantly reduces the number of model parameters. Specifically, SCL-YOLOv8 achieves a mAP@0.5 of 94.2% while reducing the number of parameters by 56.8%, FLOPS by 45.7%, and model size by 50% compared with YOLOv8n. Full article

Precise wheat head detection is essential for plant counting and yield estimation in precision agriculture. To tackle the difficulties arising from densely packed wheat heads with diverse scales and intricate occlusions in real-world field conditions, this research introduces YOLO v11n-GRN, an improved wheat head detection model founded on the streamlined YOLO v11n framework. The model optimizes performance through three key innovations: This study introduces a Global Edge Information Transfer (GEIT) module architecture that incorporates a Multi-Scale Edge Information Generator (MSEIG) to enhance the perception of wheat head contours through effective modeling of edge features and deep semantic fusion. Additionally, a C3k2_RFCAConv module is developed to improve spatial awareness and multi-scale feature representation by integrating receptive field augmentation and a coordinate attention mechanism. The utilization of the Normalized Gaussian Wasserstein Distance (NWD) as the localization loss function enhances regression stability for distant small targets. Experiments were, respectively, validated on the self-built multi-temporal wheat field image dataset and the GWHD2021 public dataset. Results showed that, while maintaining a lightweight design (3.6 MB, 10.3 GFLOPs), the YOLOv11n-GRN model achieved a precision, recall, and mAP@0.5 of 92.5%, 91.1%, and 95.7%, respectively, on the self-built dataset, and 91.6%, 89.7%, and 94.4%, respectively, on the GWHD2021 dataset. This fully demonstrates that the improvements can effectively enhance the model’s comprehensive detection performance for wheat ear targets in complex backgrounds. Meanwhile, this study offers an effective technical approach for wheat head detection and yield estimation in challenging field conditions, showcasing promising practical implications. Full article

Accurate real-time detection of hawthorn by vision systems is a fundamental prerequisite for automated harvesting. This study addresses the challenges in hawthorn orchards—including target overlap, leaf occlusion, and environmental variations—which lead to compromised detection accuracy, high computational resource demands, and poor real-time performance in existing methods. To overcome these limitations, we propose YOLO-DCL (group shuffling convolution and coordinate attention integrated with a lightweight head based on YOLOv8n), a novel lightweight hawthorn detection model. The backbone network employs dynamic group shuffling convolution (DGCST) for efficient and effective feature extraction. Within the neck network, coordinate attention (CA) is integrated into the feature pyramid network (FPN), forming an enhanced multi-scale feature pyramid network (HSPFN); this integration further optimizes the C2f structure. The detection head is designed utilizing shared convolution and batch normalization to streamline computation. Additionally, the PIoUv2 (powerful intersection over union version 2) loss function is introduced to significantly reduce model complexity. Experimental validation demonstrates that YOLO-DCL achieves a precision of 91.6%, recall of 90.1%, and mean average precision (mAP) of 95.6%, while simultaneously reducing the model size to 2.46 MB with only 1.2 million parameters and 4.8 GFLOPs computational cost. To rigorously assess real-world applicability, we developed and deployed a detection system based on the PySide6 framework on an NVIDIA Jetson Xavier NX edge device. Field testing validated the model’s robustness, high accuracy, and real-time performance, confirming its suitability for integration into harvesting robots operating in practical orchard environments. Full article

Nomex honeycomb composites (NHCs) are highly sensitive to the abnormal wear state of disc tools during cutting, leading to poor product quality. This paper proposes a real-time anomaly detection method combining a novel CNN–GRU–Attention (CGA) deep learning model with an Exponentially Weighted Moving Average (EWMA) control chart to monitor sensor data from the disc tool. The CGA model integrates an improved CNN layer to extract multidimensional local features, a GRU layer to capture long-term temporal dependencies, and a multi-head attention mechanism to highlight key information and reduce error accumulation. Trained solely on normal operation data to address the scarcity of abnormal samples, the model predicts cutting force time series with an RMSE of 0.5012, MAE of 0.3942, and R² of 0.9128, outperforming mainstream time series data prediction models. The EWMA control chart applied to the prediction residuals detects abnormal tool wear trends promptly and accurately. Experiments on real NHC cutting datasets demonstrate that the proposed method effectively identifies abnormal machining conditions, enabling timely tool replacement and significantly enhancing product quality assurance. Full article