Search Results (23,258)

Sperm morphology analysis is critical for assessing bovine fertility, since it provides insight into bull reproductive potential as well as subfertility and infertility. Traditional sperm morphology analysis is time-consuming, subjective, and prone to human error, all of which highlight the need for automated, objective solutions. This study presents the design and implementation of a computer-aided system for bovine sperm morphology analysis, leveraging deep learning models to detect and classify sperm cells based on their morphological characteristics. Using micrographs of bull sperm, we present a sequential deep learning framework that automatically detects morphological sperm aberrations. The model segments and analyzes each cell, identifying defects in the head, neck/midpiece, tail, and residual cytoplasm. Specifically, the system employs the YOLOv7 object detection framework, trained on a dataset of 277 annotated images comprising six morphological categories, to automatically identify and classify sperm abnormalities. The experimental results demonstrate a global mAP@50 of 0.73, precision of 0.75, and recall of 0.71, indicating a balanced tradeoff between accuracy and efficiency. By reducing reliance on manual analysis, this work enhances efficiency and accuracy in animal reproduction laboratories, contributing to veterinary reproduction through a cost-effective and scalable solution for sperm quality assessment. Full article

Breast cancer is one of the leading causes of mortality among women globally, and an early and accurate diagnosis is essential for effective treatment and improved survival rates. Traditional diagnostic techniques often struggle to differentiate between benign and malignant tumors due to overlapping visual characteristics, resulting in false positives or delayed detection. For efficient breast cancer detection with machine learning, it is vital to identify the most significant features because those features play the most important roles in the treatment process. This study addresses this challenge by evaluating and comparing the performance of ten state-of-the-art machine learning classifiers for breast cancer detection using image-derived features. Initially, 30 features were extracted from a novel tertiary hospital dataset, and models were evaluated based on accuracy, precision, recall, and F-measure. To enhance model performance and reduce dimensionality, the Correlation-based Feature Selection (CFS) method was applied, leading to the identification of 11 highly informative features. Our experimental results demonstrate that, while models such as SVM and Logistic Regression achieved the highest accuracy (97.7%) on the full feature set, the Neural Network exhibited a superior performance (97.2%) on the reduced feature set, with a substantial reduction in training time. Most classifiers maintained comparable or improved accuracy with fewer features, indicating effective dimensionality reduction. Furthermore, pairwise statistical significance testing confirmed that ensemble and kernel-based classifiers achieved a statistically superior performance over simpler models. These findings highlight the importance of effective feature selection in developing accurate, efficient, and scalable breast cancer prediction systems. Full article

The solar system is a Basic Competency for grade VI students at SDN 06 Taluak IV Suku. This material encourages students to recognize planets and their characteristics in the solar system, thus requiring interactive learning media. This research develops solar system flashcard learning media based on AR technology to enhance learning interactivity. Using the MDLC method, the application was built with Unity Editor and Vuforia SDK for Android and iOS devices. The application utilizes marker-based and markerless tracking technology to display 3D models of the planets. Flashcards are equipped with engaging images and brief information, as well as a quiz feature for evaluation. Testing showed that the application successfully displayed 3D objects and interactive quiz features. The application is considered to have an attractive appearance, appropriate material, ease of use, and provides an in-depth learning experience about the solar system. Full article

Background: The purpose of this study was to investigate the value of machine learning models for preoperative non-invasive prediction of International Society of Urological Pathology (ISUP) grading in clear cell renal cell carcinoma (ccRCC) based on CT urography (CTU)-related peritumoral area (PAT) radiomics features. Methods: We retrospectively analysed 328 ccRCC patients from our institution, along with an external validation cohort of 175 patients from The Cancer Genome Atlas. A total of 1218 radiomics features were extracted from contrast-enhanced CT images, with LASSO regression used to select the most predictive features. We employed four machine learning models, namely, Logistic Regression (LR), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost), for training and evaluation using Receiver Operating Characteristic (ROC) analysis. The model performance was assessed in training, internal validation, and external validation sets. Results: The XGBoost model demonstrated consistently superior discriminative ability across all datasets, achieving AUCs of 0.95 (95% CI: 0.92–0.98) in the training set, 0.93 (95% CI: 0.89–0.96) in the internal validation set, and 0.92 (95% CI: 0.87–0.95) in the external validation set. The model significantly outperformed LR, MLP, and SVM (p < 0.001) and demonstrated prognostic value (Log-rank p = 0.018). Transcriptomic analysis of model-stratified groups revealed distinct biological signatures, with high-grade predictions showing significant enrichment in metabolic pathways (DPEP3/THRSP) and immune-related processes (lymphocyte-mediated immunity, MHC complex activity). These findings suggest that peritumoral imaging characteristics provide valuable biological insights into tumor aggressiveness. Conclusions: The machine learning models based on PAT radiomics features of CTU demonstrated significant value in the non-invasive preoperative prediction of ISUP grading for ccRCC, and the XGBoost modeling had the best predictive ability. This non-invasive approach may enhance preoperative risk stratification and guide clinical decision-making, reducing reliance on invasive biopsy procedures. Full article

Metastatic breast cancer (MBC) remains one of the most aggressive and fatal malignancies in women, primarily due to tumor heterogeneity, multidrug resistance, and the limitations of conventional therapeutic approaches. Aim: This review aims to evaluate recent advances in nanomaterial-based photothermal therapy (PTT) platforms and their potential in the treatment of metastatic breast cancer. Method: A comprehensive analysis of current literature was conducted to examine how various nanomaterials are engineered for targeted PTT, with particular emphasis on their mechanisms of action, synergistic applications with chemotherapy, immunotherapy, and photodynamic therapy, as well as their capacity to overcome challenges associated with targeting metastatic niches. Results: The findings indicate that nanotechnology-enabled PTT provides spatiotemporal precision, efficient tumor ablation, and reduced systemic toxicity, while significantly enhancing therapeutic outcomes when integrated into multimodal treatment strategies. Recent preclinical studies and early clinical trials further underscore advancements in imaging guidance, thermal efficiency, and site-specific drug delivery; however, issues related to biocompatibility, safety, and large-scale clinical translation remain unresolved. Conclusions: Nanomaterial-assisted PTT holds substantial promise for improving therapeutic efficacy against metastatic breast cancer. Future research should prioritize optimizing imaging resolution, minimizing adverse effects, and addressing translational challenges to accelerate clinical integration and ultimately enhance health outcomes for women. Full article

The Puruogangri Ice Field (PIF) in the central Tibetan Plateau, known as the world’s Third Pole, is the largest modern ice field in the Tibetan Plateau and a crucial indicator of climate change. Although it was thought to be quiet, recent studies identified possible surging behaviors. But comprehensive velocity fields remain largely unknown. Here we present the first comprehensive and high spatiotemporal resolution 3D displacement field of the PIF from 2017 to 2024 using synthetic aperture radar (SAR) imaging geodesy. Using time-series InSAR and time-series pixel offset tracking and integrating ascending and descending Sentinel-1 SAR images, we invert the time-series 3D displacement over eight years. Our results reveal significant seasonal variations and three surging glaciers, with peak displacements exceeding 110 m in 12 days. Combined with ERA5 reanalysis and SAR backscatter coefficients analysis, we demonstrate that these surges are hydrologically controlled, likely initiated by damaged subglacial drainage systems. This study enhances our understanding of glacier dynamics in the central Tibetan Plateau and highlights the potential of using SAR imaging geodesy to monitor glacial hazards in High Mountain Asia. Full article

Turbidity is a crucial and reliable indicator that is extensively utilized in water quality monitoring through remote sensing technology. The development of accurate and applicable models for turbidity estimation is essential. While many existing studies rely on uniform models based on statistical regression or traditional machine learning techniques, the application of deep learning models for turbidity estimation remains limited. This study proposed deep learning models for turbidity estimation based on optical classification of inland waters using Sentinel-2 data. Specifically, the fuzzy c-means (FCM) clustering method was employed to classify optical water types (OWTs) based on their spectral reflectance characteristics. A weighted sum of the turbidity prediction results was generated by the OWT-based convolutional neural network-random forest (CNN-RF) model, with weights derived from the FCM membership degrees. Turbidity for four typical waters was mapped by the proposed method using Sentinel-2 images. The FCM method efficiently classified waters into three OWTs. The OWT-based weighted CNN-RF model demonstrated strong robustness and generalization performance, achieving a high prediction accuracy (R² = 0.900, RMSE = 11.698 NTU). The turbidity maps preserved the spatial continuity of the turbidity distribution and accurately reflected water quality conditions. These findings facilitate the application of deep learning models based on optical classification in turbidity estimation and enhance the capabilities of remote sensing for water quality monitoring. Full article

In this work, we investigate advanced photocatalyst Bi₃TiNbO₉ as promising piezophotocatalyst in terms of the effect of synthesis methods on the surface chemistry, structure, and catalytic performance in process of contaminant removal. Samples were prepared via solid-state reaction (BTNO-900) and molten salt synthesis (BTNO-800), leading to distinct morphologies and defect distributions. SEM imaging revealed that BTNO-900 consists of agglomerated, irregular particles, while BTNO-800 exhibits well-faceted, plate-like grains. Nitrogen adsorption analysis showed that the molten-synthesized sample possesses a significantly higher specific surface area (5.9 m²/g vs. 1.4 m²/g) and slightly larger average pore diameter (2.8 nm vs. 2.6 nm). High-resolution XPS revealed systematic shifts in binding energies for Bi 4f, Ti 2p, Nb 3d, and O 1s peaks in BTNO-900, accompanied by a higher content of adsorbed oxygen species (57% vs. 7.2%), indicating an increased concentration of oxygen vacancies and surface hydroxylation due to the solid-state synthesis route. Catalytic testing demonstrated that BTNO exhibits enhanced piezocatalytic efficiency of Methylene Blue degradation (~78% for both samples), whereas BTNO-800 shows significantly reduced photocatalytic activity (45.6%) compared to BTNO-900 (84.1%), suggesting recombination effects dominate in the more defective material. Synergism of light and mechanical stress results in piezophotocatalytic degradation for both samples (92.4% and 93.4%, relatively). These findings confirm that synthesis-controlled defect engineering is a key parameter for optimizing the photocatalytic behavior of Bi₃TiNbO₉-based layered oxides and crucial role of its piezocatalytic activity. Full article

Text recognition on coffee bean package labels is of great importance for product tracking and brand verification, but it poses a challenge due to variations in image quality, packaging materials, and environmental conditions. In this paper, we propose a pipeline that combines several image enhancement techniques and is followed by an Optical Character Recognition (OCR) model based on vision–language (VL) Qwen VL variants, conditioned by structured prompts. To facilitate the evaluation, we construct a coffee bean package image set containing two subsets, namely low-resolution (LRCB) and high-resolution coffee bean image sets (HRCB), enclosing multiple real-world challenges. These cases involve various packaging types (bottles and bags), label sides (front and back), rotation, and different illumination. To address the image quality problem, we design a dedicated preprocessing pipeline for package label situations. We develop and evaluate four Qwen-VL OCR variants with prompt engineering, which are compared against four baselines: DocTR, PaddleOCR, EasyOCR, and Tesseract. Extensive comparison using various metrics, including the Levenshtein distance, Cosine similarity, Jaccard index, Exact Match, BLEU score, and ROUGE scores (ROUGE-1, ROUGE-2, and ROUGE-L), proves significant improvements upon the baselines. In addition, the public POIE dataset validation test proves how well the framework can generalize, thus demonstrating its practicality and reliability for label recognition. Full article

Road cracks represent a significant challenge that impacts the long-term performance and safety of transportation infrastructure. Early identification of these cracks is crucial for effective road maintenance management. However, traditional crack recognition methods that rely on visible light images often experience substantial performance degradation in weak-light environments, such as at night or within tunnels. This degradation is characterized by blurred or deficient image textures, indistinct target edges, and reduced detection accuracy, which hinders the ability to achieve reliable all-weather target detection. To address these challenges, this study introduces a dual-modal crack detection method named YOLOv11-DCFNet. This method is based on an enhanced YOLOv11 architecture and incorporates a Cross-Modality Fusion Transformer (CFT) module. It establishes a dual-branch feature extraction structure that utilizes both infrared and visible light within the original YOLOv11 framework, effectively leveraging the high contrast capabilities of thermal infrared images to detect cracks under weak- or no-light conditions. The experimental results demonstrate that the proposed YOLOv11-DCFNet method significantly outperforms the single-modal model (YOLOv11-RGB) in both weak-light and no-light scenarios. Under weak-light conditions, the fusion model effectively utilizes the weak texture features of RGB images alongside the thermal radiation information from infrared (IR) images. This leads to an improvement in Precision from 83.8% to 95.3%, Recall from 81.5% to 90.5%, mAP@0.5 from 84.9% to 92.9%, and mAP@0.5:0.95 from 41.7% to 56.3%, thereby enhancing both detection accuracy and quality. In no-light conditions, the RGB single modality performs poorly due to the absence of visible light information, with an mAP@0.5 of only 67.5%. However, by incorporating IR thermal radiation features, the fusion model enhances Precision, Recall, and mAP@0.5 to 95.3%, 90.5%, and 92.9%, respectively, maintaining high detection accuracy and stability even in extreme no-light environments. The results of this study indicate that YOLOv11-DCFNet exhibits strong robustness and generalization ability across various low illumination conditions, providing effective technical support for night-time road maintenance and crack monitoring systems. Full article

Background: Mango seed kernels, an agro-industrial waste byproduct, constitute approximately 40–50% of the fruit’s weight and serve as a substantial source of starch. There are only a few reported studies on the pharmaceutical applications of Mango Seed Kernel Starch (MSKS) and drug carriers produced from this source. This study aims to isolate starch from mango seed kernels (MSKS), prepare drug-loaded mango seed kernel starch nanoparticles (MSKSNPs), and study the in vitro transdermal permeation. Methods: The MSKS was prepared using the alkaline method and freeze-dried. The prepared starch was analyzed for physicochemical properties relative to corn starch. The mango seed kernel starch nanoparticles (MSKSNPs) were prepared using mild alkali hydrolysis and the ultrasonication method. The model drug selected for this study was diclofenac sodium (DS), a commonly prescribed non-steroidal anti-inflammatory drug. Results: The average particle size of the drug-loaded nanoparticles was 140.0 ± 3.6 nm, with a PDI of 0.42 ± 0.03. The Transmission Electron Microscopy images confirmed the globular structure of MSKSNPs. X-ray Diffraction revealed that the diclofenac crystal size decreased to 14 nm from 33 nm in the pure drug, confirming the amorphous nature of MSKSNPs. The drug-loaded MSKSNPs showed a % encapsulation efficiency of 92.4 ± 3.7 and % drug loading of 31.08 ± 0.96. The cumulative drug released from MSKSNPs after 6 h, 12 h, and 24 h was found to be 25.58 ± 1.30, 59.68 ± 2.98, and 127.5 ± 6.4 μg/cm^2, respectively, which was more than the ethanolic drug solution with statistical significance (p-value < 0.01) along with enhanced skin retention. Conclusions: MSKSNPs were efficiently synthesized using mild alkali hydrolysis and ultrasonication, showing enhanced transdermal delivery. Skin retention was significantly higher in MSKSNPs (p-value < 0.05). The cytotoxic studies revealed that both formulations exhibit similar dose-dependent cytotoxicity, with no significant difference (p > 0.05) in their potency under the tested conditions. Full article

The unique hollowed-out catamaran hulls and complex environmental conditions in lake areas hinder traditional ranging algorithms (combining target detection and stereo matching) from accurately obtaining depth information near the center of ships. This not only impairs the navigation of electric tourist boats but also leads to high computing resource consumption. To address this issue, this study proposes a ranging method integrating improved ORB (Oriented FAST and Rotated BRIEF) with stereo vision technology. Combined with traditional optimization techniques, the proposed method calculates target distance and angle based on the triangulation principle, providing a rough alternative solution for the “gap period” of stereo matching-based ranging. The method proceeds as follows: first, it acquires ORB feature points with relatively uniform global distribution from preprocessed binocular images via a local feature weighting approach; second, it further refines feature points within the ROI (Region of Interest) using a quadtree structure; third, it enhances matching accuracy by integrating the FLANN (Fast Library for Approximate Nearest Neighbors) and PROSAC (Progressive Sample Consensus) algorithms; finally, it applies the screened matching point pairs to the triangulation method to obtain the position and distance of the target ship. Experimental results show that the proposed algorithm improves processing speed by 6.5% compared with the ORB-PROSAC algorithm. Under ideal conditions, the ranging errors at 10m and 20m are 2.25% and 5.56%, respectively. This method can partially compensate for the shortcomings of stereo matching in ranging under the specified lake area scenario. Full article

Background: Lumbar foraminal stenosis (LFS) is a prevalent degenerative condition associated with significant radicular pain and impaired quality of life. Advances in minimally invasive and fusion-based surgical techniques have introduced new strategies for decompressing the neural elements. However, comparative data correlating volumetric foraminal expansion with functional outcomes remain limited. Methods: This retrospective cohort study analyzed 256 patients treated surgically for symptomatic LFS between December 2017 and December 2023. Patients were categorized into four surgical subgroups: endoscopic decompression, anterior lumbar interbody fusion (ALIF), microsurgical decompression, and transforaminal lumbar interbody fusion (TLIF). Preoperative and postoperative assessments included magnetic resonance imaging (MRI) to calculate foraminal volume and standardized clinical scales: the Oswestry Disability Index (ODI), Visual Analogue Scale (VAS) for back and leg pain, and SF-36 health-related quality-of-life scores. Statistical significance was determined using p-values, and inter-observer agreement was evaluated via κ-statistics. Results: Postoperative imaging demonstrated a significant increase in foraminal canal volume across all surgical groups: endoscopy (29.9%), ALIF (71.8%), microsurgery (48.06%), and TLIF (67.0%). ODI scores improved from a preoperative mean of 55.25 to 18.27 at 24 months post-surgery (p < 0.001). VAS scores for back pain decreased from 6.37 to 2.1 (p < 0.001), while leg pain scores declined from 6.85 to 2.05 (p < 0.001). Functional improvement reached or exceeded the minimal clinically important difference (MCID) threshold in over 66% of patients. Conclusions: Modern surgical strategies for LFS, particularly fusion-based techniques, yield significant volumetric decompression and durable clinical improvement. Volumetric gain in the foraminal canal is closely associated with pain reduction and enhanced functional outcomes. These findings support a tailored surgical approach based on anatomical pathology and segmental stability. Full article

The tire-road friction coefficient (TRFC) is a critical parameter that significantly influences vehicle safety, handling stability, and driving comfort. Existing estimation methods based on vehicle dynamics suffer from a substantial decline in accuracy under conditions with insufficient excitation, while vision-based approaches are often limited by the generalization ability of their datasets, making them less effective in complex and variable real-driving environments. To address these challenges, this paper proposes a novel, low-cost fusion method for TRFC estimation that integrates weather conditions and road image data. The proposed approach begins by employing semantic segmentation to partition the input images into distinct regions—sky and road. The segmented images will be fed into the road recognition network and the weather recognition network for road type and weather classification. Furthermore, a fusion decision tree incorporating an uncertainty modeling mechanism is introduced to dynamically integrate these multi-source features, thereby enhancing the robustness of the estimation. Experimental results demonstrate that the proposed method maintains stable and reliable estimation performance even on unseen road surfaces, outperforming single-modality methods significantly. This indicates its high practical value and promising potential for broad application. Full article

Tea is one of the most consumed beverages in the world. However, tea plants are often susceptible to various diseases, especially leaf diseases. Currently, most tea farms identify leaf diseases through manual inspection. Due to its time-consuming and resource-intensive nature, manual inspection is impractical for large-scale applications. This study proposes a novel convolutional neural network model designated as YOLOv5 Bi-HIC for detecting tea leaf diseases, including algal leaf spot, tea brown blight, and tea grey blight. The model enhances the conventional YOLOv5 object detection model by incorporating instance and context information to improve the detection performance. A total of 1091 raw images of tea leaves affected by algal leaf spots, tea brown blight, and tea grey blight were captured at Wenhua Tea Farm, Miaoli City, Taiwan. The results indicate that the proposed model achieves precision, recall, F1 Score, and mAP values of 0.977, 0.943, 0.968, and 0.96, respectively, during training. Furthermore, it exhibits a detection confidence score of 0.94, 0.98, and 0.92 for algal leaf spot, tea brown blight, and tea grey blight, respectively. Overall, the results indicate that YOLOv5 Bi-HIC provides an accurate approach for real-time detection of leaf diseases and can serve as a valuable tool for timely intervention and management in tea plantations. Full article