Search Results (78)

Background/Objectives: The spinal cord is a critical component of the central nervous system that transmits neural signals between the brain and the body’s peripheral regions through its nerve roots. Despite being partially protected by the vertebral column, the spinal cord remains highly vulnerable to trauma, tumors, infections, and degenerative or inflammatory disorders. These conditions can disrupt neural conduction, resulting in severe functional impairments, such as paralysis, motor deficits, and sensory loss. Therefore, accurate and comprehensive spinal cord segmentation is essential for characterizing its structural features and evaluating neural integrity. Methods: In this study, we propose a fully automated method for segmentation of the cervical spinal cord in sagittal magnetic resonance (MR) images. This method facilitates rapid clinical evaluation and supports early diagnosis. Our approach uses a Swin-Unet architecture, which integrates vision transformer blocks into the U-Net framework. This enables the model to capture both local anatomical details and global contextual information. This design improves the delineation of the thin, curved, low-contrast cervical cord, resulting in more precise and robust segmentation. Results: In experimental studies, the proposed Swin-Unet model (SWU1), which uses transformer blocks in the encoder layer, achieved Dice Similarity Coefficient (DSC) and Hausdorff Distance 95 (HD95) scores of 0.9526 and 1.0707 mm, respectively, for cervical spinal cord segmentation. These results confirm that the model can consistently deliver precise, pixel-level delineations that are structurally accurate, which supports its reliability for clinical assessment. Conclusions: The attention-enhanced Swin-Unet architecture demonstrated high accuracy in segmenting thin and complex anatomical structures, such as the cervical spinal cord. Its ability to generalize with limited data highlights its potential for integration into clinical workflows to support diagnosis, monitoring, and treatment planning. Full article

This study presents the development and evaluation of an automated ultraviolet-C irradiation system for maize seed treatment, emphasizing disinfection performance, environmental control, and vision-based monitoring. The system features dual 8-watt ultraviolet-C lamps, sensors for temperature and humidity, and an air extraction unit to regulate the microclimate of the chamber. Without air extraction, radiation stabilized within one minute, with internal temperatures increasing by 5.1 °C and humidity decreasing by 13.26% over 10 min. When activated, the extractor reduced heat build-up by 1.4 °C, minimized humidity fluctuations (4.6%), and removed odors, although it also attenuated the intensity of ultraviolet-C by up to 19.59%. A 10 min ultraviolet-C treatment significantly reduced the fungal infestation in maize seeds by 23.5–26.25% under both extraction conditions. Thermal imaging confirmed localized heating on seed surfaces, which stressed the importance of temperature regulation during exposure. Notable color changes ($\Delta E>2.3$) in treated seeds suggested radiation-induced pigment degradation. Ultraviolet-C intensity mapping revealed spatial non-uniformity, with measurements limited to a central axis, indicating the need for comprehensive spatial analysis. The integrated computer vision system successfully detected seed contours and color changes under high-contrast conditions, but underperformed under low-light or uneven illumination. These limitations highlight the need for improved image processing and consistent lighting to ensure accurate monitoring. Overall, the chamber shows strong potential as a non-chemical seed disinfection tool. Future research will focus on improving radiation uniformity, assessing effects on germination and plant growth, and advancing system calibration, safety mechanisms, and remote control capabilities. Full article

Egg weight monitoring provides critical data for calculating the feed-to-egg ratio, and improving poultry farming efficiency. Installing a computer vision monitoring system in egg collection systems enables efficient and low-cost automated egg weight measurement. However, its accuracy is compromised by egg clustering during transportation and low-contrast edges, which limits the widespread adoption of such methods. To address this, we propose an egg measurement method based on a computer vision and multi-feature extraction and regression approach. The proposed pipeline integrates two artificial neural networks: Central differential-EfficientViT YOLO (CEV-YOLO) and Egg Weight Measurement Network (EWM-Net). CEV-YOLO is an enhanced version of YOLOv11, incorporating central differential convolution (CDC) and efficient Vision Transformer (EfficientViT), enabling accurate pixel-level egg segmentation in the presence of occlusions and low-contrast edges. EWM-Net is a custom-designed neural network that utilizes the segmented egg masks to perform advanced feature extraction and precise weight estimation. Experimental results show that CEV-YOLO outperforms other YOLO-based models in egg segmentation, with a precision of 98.9%, a recall of 97.5%, and an Average Precision (AP) at an Intersection over Union (IoU) threshold of 0.9 (AP90) of 89.8%. EWM-Net achieves a mean absolute error (MAE) of 0.88 g and an R² of 0.926 in egg weight measurement, outperforming six mainstream regression models. This study provides a practical and automated solution for precise egg weight measurement in practical production scenarios, which is expected to improve the accuracy and efficiency of feed-to-egg ratio measurement in laying hen farms. Full article

Achieving rapid and accurate object classification holds significant importance in various domains. However, conventional vision-based techniques suffer from several limitations, including high data redundancy and strong dependence on image quality. In this work, we present a high-speed, image-free object classification method based on dual-pixel measurement and normalized central moment invariants. Leveraging the complementary modulation capability of a digital micromirror device (DMD), the proposed system requires only five tailored binary illumination patterns to simultaneously extract geometric features and perform classification. The system can achieve a classification update rate of up to 4.44 kHz, offering significant improvements in both efficiency and accuracy compared to traditional image-based approaches. Numerical simulations verify the robustness of the method under similarity transformations—including translation, scaling, and rotation—while experimental validations further demonstrate reliable performance across diverse object types. This approach enables real-time, low-data throughput, and reconstruction-free classification, offering new potential for optical computing and edge intelligence applications. Full article

This paper discusses the viability of using a low-code multimodal large language model agent with computer vision functionality to support occupational safety and health evaluations on construction sites. The central hypothesis aims to verify that these systems can provide reliable answers, as evaluated against a ground truth review, including the identification of high-risk dangers. A conversational agent was given the task of finding hazards and checking for national legislative compliance within a dataset of 100 real-world construction photos. The comparison of the agent’s results to the ground truth provides insight into current limitations. The primary issues identified were inconsistent taxonomies, inadequate causal reasoning, and insufficient contextual consideration, all of which adversely impacted performance—particularly when analyzing low-resolution images. The metrics supporting the conclusion synthesize that this tool is a valuable augmentation technology, enhancing safety evaluations while still requiring human supervision to ensure reliability. Full article

Background: Intraocular lens (IOL) alignment is crucial for optimal performance in presbyopia-correcting designs. The aim was to report a case of a patient with a high angle kappa implanted with the continuous transitional focus (CTF) Precizon Prebyopic NVA IOL. Case presentation: A 51-year-old patient presenting large angle kappa values (0.6/0.8 mm) was implanted with the Precizon Prebyopic NVA IOL and followed-up 1 and 10 months post-surgery. This IOL is designed with a butterfly-shaped central area that allows the orientation of the lens so that the visual axis passes through the wider diameter of the optic zone. Postoperative refraction was −0.25D of cyl at 80° for the right eye and +0.25D −0.50D cyl at 170°. Corrected distance visual acuity (CDVA) at the last visit was −0.1 logMAR monocularly and −0.2 logMAR binocularly. Binocular uncorrected distance (UDVA), intermediate (UIVA) and near visual acuities (UNVA) were −0.1, 0.1 and 0.1 logMAR, respectively. The corrected binocular defocus curve exhibited outstanding vision at the 0.00D defocus level and showed a continuous range of functional vision from distance to near. Overall excellent satisfaction was reported, along with low levels of photopic phenomena. Conclusions: Precizon Presbyopic NVA IOL provided satisfactory vision and low levels of photic phenomena in a high angle kappa patient who would potentially be excluded from presbyopia-correcting IOL implantation. Full article

Our study explored the role of serum 25-hydroxyvitamin D [25(OH)D] levels as an indicator of response to intravitreal anti–vascular endothelial growth factor (anti-VEGF) therapy in patients with diabetic macular edema (DME), highlighting functional and anatomical outcomes linked to systemic biomarker profiles. In a cohort of treatment-naive diabetic patients, vitamin D status was correlated with post-treatment changes in central macular thickness (CMT) and best-corrected visual acuity (BCVA), illustrating layered therapeutic responses among deficient, insufficient, and sufficient vitamin D groups. Functional gains, measured as improvements in decimal BCVA, and anatomical improvements, defined by CMT reduction via spectral-domain optical coherence tomography (SD-OCT), were primarily detected in patients with sufficient vitamin D levels. Remarkably, patients with serum 25(OH)D ≥ 30 ng/mL revealed complete dual-response rates, while those in the deficient group manifested partial therapeutic efficacy, supporting the immunoangiogenic modulatory role of vitamin D. Statistical associations exposed a tight linear connection between baseline and final visual acuity and a pronounced inverse relationship between CMT and final vision, suggesting that vitamin D may play a role in treatment-mediated structural recovery. These results may imply that low vitamin D levels lead to subclinical endothelial dysfunction and impaired retinal barrier repair, possibly through dysregulated anti–vascular endothelial growth factor (anti-VEGF) signaling, chronic inflammation, and oxidative stress. Our findings underscore the need for and importance of further research of vitamin D status as an adjunctive biomarker in the clinical approach of personalized DME and validates the potential of circulating vitamin D evaluation in therapeutic classification and predictive eye care. Full article

Radiotherapy is utilized in the treatment of various cancers of the central nervous system and head and neck. Given the high concentration of organs-at-risk in this region, care must be exercised to minimize the dose delivered to these structures. Studies have shown that excessive radiation exposure can adversely impact the eyes, potentially resulting in the loss of their function. For instance, radiation doses greater than 50 Gy have been shown to increase the incidence of retinopathy, and radiation doses as low as 0.5 Gy have been shown to induce cataract formation. In this review, we discuss the ocular complications of radiotherapy used in the treatment of cancers of the central nervous system and head and neck. We then transition to potential strategies to spare the eyes during radiotherapy in an effort to reduce the rates and severity of ocular complications and preserve vision. Full article

Despite rapid advances in robot learning, the coordination of closed-loop manipulation in cluttered environments remains a challenging and relatively underexplored problem. We present a novel two-level hierarchical architecture for a depth vision-equipped robotic arm that integrates pushing, grasping, and high-level decision making. Central to our approach is a prioritised action–selection mechanism that facilitates efficient early-stage learning via behaviour cloning (BC), while enabling scalable exploration through reinforcement learning (RL). A high-level decision neural network (DNN) selects between grasping and pushing actions, and two low-level action neural networks (ANNs) execute the selected primitive. The DNN is trained with RL, while the ANNs follow a hybrid learning scheme combining BC and RL. Notably, we introduce an automated demonstration generator based on oriented bounding boxes, eliminating the need for manual data collection and enabling precise, reproducible BC training signals. We evaluate our method on a challenging manipulation task involving five closely packed cubic objects. Our system achieves a completion rate (CR) of 100%, an average grasping success (AGS) of 93.1% per completion, and only 7.8 average decisions taken for completion (DTC). Comparative analysis against three baselines—a grasping-only policy, a fixed grasp-then-push sequence, and a cloned demonstration policy—highlights the necessity of dynamic decision making and the efficiency of our hierarchical design. In particular, the baselines yield lower AGS (86.6%) and higher DTC (10.6 and 11.4) scores, underscoring the advantages of content-aware, closed-loop control. These results demonstrate that our architecture supports robust, adaptive manipulation and scalable learning, offering a promising direction for autonomous skill coordination in complex environments. Full article

The city of Al Ain is a fast-developing area. With building typology varying from low-rise to mid-rise, sustainable design in buildings is needed. As the majority of the city’s population is Emirati Citizens, the percentage of expats is increasing. The expats tend to live in mid-rise buildings. One of the central midrise areas is AL Ain Square. This study aims to investigate how an optimized mashrabiya pattern can impact the energy and the Predicted Mean Vote (PMV) in a 3-bedroom apartment, fully oriented to the south, of an expat family. The methodology is as follows: case study selection, Weather analysis, Modeling/Validation of the base case scenario, Optimization of the mashrabiya pattern, Simulation of various scenarios, and Results. Analyzing the selected case study is the initial step of the methodology. This analysis begins with the district, building typology, and the chosen apartment. The weather analysis is relevant for using the mashrabiya (screen device) and the need to improve energy consumption and thermal comfort. The modeling of the base case shall be performed in Rhino Grasshopper. The validation is based on a one-year electricity bill provided by the owner. The optimization of mashrabiya patterns is an innovative process, where various designs are compared and then optimized to select the most efficient pattern. The solutions to the selected scenarios will then yield the results of the optimal scenario. This study is relevant to industry, academia, and local authorities as an innovative approach to retrofitting buildings. Additionally, the research presents a creative vision that suggests optimized mashrabiya patterns can significantly enhance energy savings, with the hexagonal grid configuration demonstrating the highest efficiency. This finding highlights the potential for geometry-driven shading optimization tailored to specific climatic and building conditions. Contrasting earlier mashrabiya studies that assess one static pattern, we couple a geometry-agnostic evolutionary solver with a utility-calibrated EnergyPlus model to test thousands of square, hexagonal, and triangular permutations. This workflow uncovers a previously undocumented non-linear depth perforation interaction. It validates a hexagonal screen that reduces annual cooling energy by 12.3%, establishing a replicable, grid-specific retrofit method for hot-arid apartments. Full article

Wipe-out is defined as a sudden, unexplained, and irreversible loss of residual central vision following glaucoma surgery, typically in eyes with advanced visual field damage and severely compromised optic nerves. The purpose of this review is to critically assess the current incidence, risk factors, pathophysiological mechanisms, and clinical relevance of “wipe-out”, a rare but devastating complication of glaucoma surgery characterized by sudden, unexplained central vision loss postoperatively. A comprehensive literature review was conducted, analyzing key peer-reviewed studies from electronic databases (PubMed, Medline, and Google Scholar) published up to 2025. The data from the literature published prior to the year 2000 suggest that wipe-out incidences range broadly from <1% to 13%. Contemporary prospective studies and large-scale reviews indicate a significantly lower current incidence, frequently below 1%. Identified risk factors include severe preoperative visual field loss (especially split fixation), older age, immediate postoperative hypotony, and compromised optic nerve head perfusion. The proposed mechanisms involve acute vascular insults, ischemia–reperfusion injury, and accelerated apoptosis of already vulnerable retinal ganglion cells. Modern MIGS and refined trabeculectomy techniques exhibit notably lower wipe-out risks compared to historical data. The literature emphasizes preventive management, including careful patient selection, incremental intraocular pressure reduction, and minimally invasive anesthetic approaches. Although wipe-out syndrome represents a serious complication, its incidence in modern glaucoma surgery is minimal. The considerable benefits of contemporary surgical approaches—particularly MIGS—in preserving vision clearly outweigh this very low risk. Ophthalmologists should remain vigilant but confident in the safety and efficacy of modern glaucoma surgical techniques, emphasizing proactive intervention to prevent blindness rather than avoiding necessary surgery in consideration of the minimal risk of wipe-out. Full article

The transition to clean energy is at the heart of the European Union’s climate strategy, with citizen participation promoted as a key driver. Clean energy communities (CECs) are central to this vision, yet their uptake across Europe remains limited. This study provides a novel comparative perspective on perceived barriers to CEC participation by examining two distinct groups: current members (early adopters) and the general public (potential adopters). Using a cross-national mixed-methods approach, we integrate data from semi-structured interviews with CEC members and a representative survey of citizens in six European countries. The results show that awareness of CECs is generally low and that initiatives are still in the early stages of adoption. While interviewees highlighted regulatory complexity and institutional barriers, survey respondents were more likely to cite lack of awareness, knowledge gaps, and financial concerns. The findings reveal distinct patterns in perceived barriers across adopter groups and national contexts. To support broader engagement, we propose a dual strategy: addressing structural challenges through regulatory and policy reform, while strengthening targeted communication and outreach. We also highlight the role of early adopters as trusted messengers who can help bridge the gap between innovation and mainstream adoption. Full article

Precision agriculture is necessary for dealing with problems like pest outbreaks, a lack of water, and declining crop health. Manual inspections and broad-spectrum pesticide application are inefficient, time-consuming, and dangerous. New drone photography and IoT sensors offer quick, high-resolution, multimodal agricultural data collecting. Regional diversity, data heterogeneity, and privacy problems make it hard to conclude these data. This study proposes a lightweight, hybrid deep learning architecture called federated LeViT-ResUNet that combines the spatial efficiency of LeViT transformers with ResUNet’s exact pixel-level segmentation to address these issues. The system uses multispectral drone footage and IoT sensor data to identify real-time insect hotspots, crop health, and yield prediction. The dynamic relevance and sparsity-based feature selector (DRS-FS) improves feature ranking and reduces redundancy. Spectral normalization, spatial–temporal alignment, and dimensionality reduction provide reliable input representation. Unlike centralized models, our platform trains over-dispersed client datasets using federated learning to preserve privacy and capture regional trends. A huge, open-access agricultural dataset from varied environmental circumstances was used for simulation experiments. The suggested approach improves on conventional models like ResNet, DenseNet, and the vision transformer with a 98.9% classification accuracy and 99.3% AUC. The LeViT-ResUNet system is scalable and sustainable for privacy-preserving precision agriculture because of its high generalization, low latency, and communication efficiency. This study lays the groundwork for real-time, intelligent agricultural monitoring systems in diverse, resource-constrained farming situations. Full article

This study addresses the labor-intensive and safety-critical challenges of manual oyster processing by innovating an advanced robotic intelligent sorting system. Central to this system is the integration of a high-resolution vision module, dual operational controllers, and the collaborative AUBO-i3 robot, all harmonized through a sophisticated Robot Operating System (ROS) framework. A specialized oyster image dataset was curated and augmented to train a robust You Only Look Once version 8 Oriented Bounding Box (YOLOv8-OBB) model, further enhanced through the incorporation of MobileNet Version 4 (MobileNetV4). This optimization reduced the number of model parameters by 50% and lowered the computational load by 23% in terms of GFLOPS (Giga Floating-point Operations Per Second). In order to capture oyster motion dynamically on a conveyor belt, a Kalman filter (KF) combined with a Low-Pass filter algorithm was employed to predict oyster trajectories, thereby improving noise reduction and motion stability. This approach achieves superior noise reduction compared to traditional Moving Average methods. The system achieved a 95.54% success rate in static gripping tests and an impressive 84% in dynamic conditions. These technological advancements demonstrate a significant leap towards revolutionizing seafood processing, offering substantial gains in operational efficiency, reducing potential contamination risks, and paving the way for a transition to fully automated, unmanned production systems in the seafood industry. Full article

Hyperspectral image classification faces significant challenges in effectively extracting and integrating spectral-spatial features from high-dimensional data. Recent deep learning (DL) methods combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have demonstrated exceptional performance. However, two critical challenges may cause degradation in the classification accuracy of these methods: interference from irrelevant information within the observed region, and the potential loss of useful information due to local spectral variability within the same class. To address these issues, we propose a central pixel-based dual-branch network (CPDB-Net) that synergistically integrates CNN and ViT for robust feature extraction. Specifically, the central spectral feature extraction branch based on CNN serves as a strong prior to reinforce the importance of central pixel features in classification. Additionally, the spatial branch based on ViT incorporates a novel frequency-aware HiLo attention, which can effectively separate high and low frequencies, alleviating the problem of local spectral variability and enhancing the ability to extract global features. Extensive experiments on widely used HSI datasets demonstrate the superiority of our method. Our CPDB-Net achieves the highest overall accuracies of 92.67%, 97.48%, and 95.02% on the Indian Pines, Pavia University, and Houston 2013 datasets, respectively, outperforming recent representative methods and confirming its effectiveness. Full article