Search Results (157)

Background: The pterygoid plates serve as crucial reference points for posterior maxillary surgery and the placement of pterygoid implants; however, population-specific morphometric reference values remain underexplored for adults of Asir region (Abha city) of Saudi Arabia. Methods: This retrospective cross-sectional cone beam computed tomography (CBCT) study analyzed the archived scans obtained at King Khalid University Dental Hospital. Of 100 randomly selected adult CBCT scans collected between June and October 2025, 50 images met the eligibility criteria. The analyses were conducted using OnDemand3D software to measure the bilateral pterygoid plates’ length, thickness at the maximum diameter, and medial-lateral divergence angle. Styloid process length was measured as an exploratory variable. Three calibrated examiners performed the measurements, and the reliability was assessed using interclass correlation coefficients. Results: Fifty CBCT scans met the inclusion criteria (30 males, 20 females). The mean lateral pterygoid plate length was 14.61 ± 3.69 mm on the right and 13.83 ± 3.93 mm on the left, while the mean medial plate length was 11.27 ± 3.52 mm (right) and 11.98 ± 3.82 mm (left). Side to side paired comparisons showed no significant right–left differences in lateral plate length (mean R–L 0.79 mm, 95% CI −0.48 to 2.06), lateral thickness (mean 0.04 mm, 95% CI −0.14 to 0.22), medial thickness (mean 0.01 mm, 95% CI −0.19 to 0.21), or pterygoid angulation (mean 1.99°, 95% CI −1.07 to 5.05), supporting bilateral symmetry. Bilateral correlations were strong for medial plate length (r = 0.729, p < 0.001) and angulation (r = 0.632, p < 0.001). Males had a longer right lateral plate than females (15.74 ± 3.55 mm vs. 12.93 ± 3.31 mm; mean difference 2.81 mm, 95% CI 0.80–4.82; p = 0.007), whereas other measurements did not differ by sex. Plate thickness ranged from approximately 1.33 to 1.46 mm and left medial plate thickness correlated negatively with left medial plate length (r = −0.399, p = 0.004). Styloid process length averaged 22.99 ± 9.76 mm and showed no significant association with pterygoid plate measures. Conclusions: CBCT-derived findings demonstrated overall bilateral symmetry and limited dimorphism in relation to sex. These region-specific morphometries support individualized preoperative posterior maxillary surgery and pterygoid implant planning. Full article

Hyperspectral unmixing (HU) aims to extract constituent information from mixed pixels and is a fundamental task in hyperspectral remote sensing. Deep non-negative matrix factorization (DNMF) has recently attracted attention for HU due to its hierarchical representation capability. However, existing DNMF-based methods are often sensitive to noise and outliers, and face limitations in incorporating prior knowledge, modeling feature structures, and enforcing sparsity constraints, which restrict their robustness, accuracy, and interpretability. To address these challenges, we propose a sparse deep NMF model with adversarial graph regularization for hyperspectral unmixing, termed DNMF-AG. Specifically, we design an adversarial graph regularizer that integrates local similarity and dissimilarity graphs to promote intraclass consistency and interclass separability in the spatial domain, thereby enhancing structural modeling and robustness. In addition, a Gram-based sparsity constraint is introduced to encourage sparse abundance representations by penalizing inner product correlations. To further improve robustness and computational efficiency, a truncated activation function is incorporated into the iterative update process, suppressing low-amplitude components and promoting zero entries in the abundance matrix. The overall model is optimized using the alternating direction method of multipliers (ADMM). Experimental results on multiple synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of estimation accuracy and robustness. Full article

Scene classification in remote sensing images is one of the urgent tasks that requires an improvement in recognition accuracy due to complex spatial structures and high inter-class similarity. Although feature extraction using convolutional neural networks provides high efficiency, combining deep features obtained from different architectures in a semantically consistent manner remains an important scientific problem. In this study, a DMCCA + SVM model is proposed, in which Discriminative Multiple Canonical Correlation Analysis (DMCCA) is applied to fuse multi-source deep features, and final classification is performed using a Support Vector Machine (SVM). Unlike conventional fusion methods, DMCCA projects heterogeneous features into a unified low-dimensional latent space by maximizing within-class correlation and minimizing between-class correlation, resulting in a more separable and compact feature space. The proposed approach was evaluated on three widely used benchmark datasets—NWPU-RESISC45, AID, and PatternNet—and achieved accuracy scores of 92.75%, 93.92%, and 99.35%, respectively. The results showed that the model outperforms modern individual CNN architectures. Additionally, the model’s stability and generalization capability were confirmed through K-fold cross-validation. Overall, the proposed DMCCA + SVM model was experimentally validated as an effective and reliable solution for high-accuracy classification of remote sensing scenes. Full article

To address the challenges of small-sample rock fine classification—such as overfitting caused by limited sample size and the increased complexity resulting from high inter-class similarity—this study proposes a Stacking ensemble method tailored for small-sample rock image classification. Using a dataset of seven rock categories provided by the BdRace platform, 38 features were extracted across three dimensions—color, texture, and grain size—through grayscale thresholding, HSV color space analysis, gray-level co-occurrence matrix computation, and morphological analysis. The interrelationships among features were evaluated using Spearman correlation analysis and hierarchical clustering, while a voting-based fusion strategy integrated Lasso regularization, gray correlation analysis, and variance filtering for feature dimensionality reduction. The Whale Optimization Algorithm (WOA) was employed to perform global optimization on the base learners, including Random Forest (RF), K-Nearest Neighbors (KNN), Naive Bayes (NBM), and Support Vector Machine (SVM), with Logistic Regression serving as the meta-classifier to construct the final Stacking ensemble model. Experimental results demonstrate that the Stacking method achieves an average classification accuracy of 85.41%, with the highest accuracy for black coal identification (97.16%). Compared to the single models RF, KNN, NBM, and SVM, it improves accuracy by 7.27%, 8.64%, 6.79%, and 6.94%, respectively. Evidently, the Stacking model integrates the strengths of individual models, significantly enhancing recognition accuracy. This research not only improves rock identification accuracy and reduces exploration costs but also advances the intelligent transformation of geological exploration, demonstrating considerable engineering application value. Full article

Few-shot fault diagnosis (FSFD) seeks to build accurate models from scarce labeled data, a frequent challenge in industrial settings with noisy measurements and varying operating conditions. Conventional metric-based meta-learning (MBML) often assumes task-invariant, class-separable feature spaces, which rarely hold in heterogeneous environments. To address this, we propose a Transformer-embedded Task-Adaptive-Regularized Prototypical Network (TETARPN). A tailored Transformer-based Temporal Encoder Module is integrated into MBML to capture long-range dependencies and global temporal correlations in industrial time series. In parallel, a task-adaptive prototype regularization dynamically adjusts constraints according to task difficulty, enhancing intra-class compactness and inter-class separability. This combination improves both adaptability and robustness in FSFD. Experiments on bearing benchmark datasets show that TETARPN consistently outperforms state-of-the-art methods under diverse fault types and operating conditions, demonstrating its effectiveness and potential for real-world deployment. Full article

Background/Objectives: The purpose of this study is to determine the added value of 18F-FDG PET/CT scan in pediatric LCH compared to other imaging modalities (CT and MRI) at initial staging, during assessment of disease reactivation, and after treatment. Methods: This is a retrospective study of children diagnosed with LCH between 1 June 2007 and 8 December 2022 who met the inclusion criteria. 18F-FDG PET CT imaging was compared to CT and/or MRI when available. The interclass correlation coefficient (ICC) was used to assess the agreement between methods. p-Values of less than 0.05 were considered statistically significant. Results: A total of 39 children had undergone 18F-FDG PET/CT studies. Median (range) age at presentation was 10 years (1.3–17 y), with a female-to-male ratio of 0.7:1. Excellent concordance (ICC = 1; p < 0.0001) between 18F-FDG PET/CT and other imaging methods was found. Median SUVmax of the positive FDG-avid lesions at initial staging was 2.7 [range 1.3–16.7]. Conclusions: 18F-FDG PET/CT has been shown to be complementary to diagnostic CT and MRI, with the advantage of demonstrating additional metabolic information at initial staging, during assessment of disease reactivation, and to assess interval changes post therapy. These preliminary findings warrant further investigation. Full article

This study was designed to investigate the variability of renal ultrasound measurements, focusing on the impact of physician experience and patient position. Background: Since decreased kidney length is considered an indicator for chronic renal disease, understanding measurement repeatability and reproducibility is crucial for establishing effective diagnostic guidelines. Methods: Fifty healthy young adults underwent renal ultrasound scans performed by three examiners with varying levels of experience (12 years, 5 years, and 4 weeks). Renal length was measured at the level of the hilum in three patient positions: supine, lateral decubitus, and prone, using a 2–6 MHz convex probe (GE Logiq S8). Results: This study found that examiner experience significantly affected the results of sonographic measurements. However, the Interclass Correlation Coefficient analysis for all examiners demonstrated good reliability in most positions, with the highest values observed for the prone position. Measurements in the lateral decubitus position showed highest values, especially for the most experience examiner. The less experienced sonographers produced more variable results. Conclusions: Standardized patient positioning improves the accuracy and reproducibility of renal ultrasound measurements. The prone position offers a balance of reliability and practicality, especially for less experienced operators. Full article

To address the challenges brought by the high penetration of renewable energy in power systems, such as multi-scale dynamic interactions, high feature dimensionality, and limited model generalization, this paper proposes a transient stability assessment (TSA) method that combines temporal feature selection with deep learning-based modeling. First, a two-stage feature selection strategy is designed using the inter-class Mahalanobis distance and Spearman rank correlation. This helps extract highly discriminative and low-redundancy features from wide-area measurement system (WAMS) time-series data. Then, a parallel LSTM-Transformer architecture is constructed to capture both short-term local fluctuations and long-term global dependencies. A variational inference mechanism based on a Gaussian mixture model (GMM) is introduced to enable dynamic representations fusion and uncertainty modeling. A composite loss function combining improved focal loss and Kullback–Leibler (KL) divergence regularization is designed to enhance model robustness and training stability under complex disturbances. The proposed method is validated on a modified IEEE 39-bus system. Results show that it outperforms existing models in accuracy, robustness, interpretability, and other aspects. This provides an effective solution for TSA in power systems with high renewable energy integration. Full article

Recent advances in very high resolution PlanetScope imagery and deep-learning techniques have enabled effective mapping of small water bodies (SWBs), including ponds and ditches. SWBs typically occupy a minor proportion of remote-sensing imagery. This creates significant class imbalance that introduces bias in trained models. Most existing deep-learning approaches fail to adequately address this imbalance. Such an imbalance introduces bias in trained models. Most existing deep-learning approaches fail to adequately address the inter-class (water vs. non-water) and intra-class (SWBs vs. large water bodies) simultaneously. Consequently, they show poor detection of SWBs. To address these challenges, we propose an area-based weighted binary cross-entropy (AWBCE) loss function. AWBCE dynamically weights water bodies according to their size during model training. We evaluated our approach through large-scale SWB mapping in the middle and east of Hubei Province, China. The models were trained on 14,509 manually annotated PlanetScope image patches (512 × 512 pixels each). We implemented the AWBCE loss function in State-of-the-Art segmentation models (UNet, DeepLabV3+, HRNet, LANet, UNetFormer, and LETNet) and evaluated them using overall accuracy, F1-score, intersection over union, and Matthews correlation coefficient as accuracy metrics. The AWBCE loss function consistently improved performance, achieving better boundary accuracy and higher scores across all metrics. Quantitative and visual comparisons demonstrated AWBCE’s superiority over other imbalance-focused loss functions (weighted BCE, Dice, and Focal losses). These findings emphasize the importance of specialized approaches for comprehensive SWB mapping using high-resolution PlanetScope imagery in low-latitude regions. Full article

This study proposes an asynchronous brain–computer interface (BCI) framework based on steady-state motion visual evoked potentials (SSMVEPs), designed to enhance the accuracy and robustness of control state recognition. The method integrates filter bank common spatial patterns (FBCSPs) and filter bank canonical correlation analysis (FBCCA) to extract complementary spatial and frequency domain features from EEG signals. These multimodal features are then fused and input into a dual-classifier structure consisting of a support vector machine (SVM) and extreme gradient boosting (XGBoost). A weighted fusion strategy is applied to combine the probabilistic outputs of both classifiers, allowing the system to leverage their respective strengths. Experimental results demonstrate that the fused FB(CSP + CCA)-(SVM + XGBoost) model achieves superior performance in distinguishing intentional control (IC) and non-control (NC) states compared to models using a single feature type or classifier. Furthermore, the visualization of feature distributions using UMAP shows improved inter-class separability when combining FBCSP and FBCCA features. These findings confirm the effectiveness of both feature-level and classifier-level fusion in asynchronous BCI systems. The proposed approach offers a promising and practical solution for developing more reliable and user-adaptive BCI applications, particularly in real-world environments requiring flexible control without external cues. Full article

Eye-tracking studies in virtual reality (VR) deliver insights into behavioral function. The gold standard of evaluating gaze behavior is based on manual scoring, which is labor-intensive. Previously proposed automated eye-tracking algorithms for VR head mount display (HMD) were not validated against manual scoring, or tested in dynamic areas of interest (AOIs). Our study validates the accuracy of an automated scoring algorithm, which determines temporal fixation behavior on static and dynamic AOIs in VR, against subjective human annotation. The interclass-correlation coefficient (ICC) was calculated for the time of first fixation (TOFF) and total fixation duration (TFD), in ten participants, each presented with 36 static and dynamic AOIs. High ICC values (≥0.982; p < 0.0001) were obtained when comparing the algorithm-generated TOFF and TFD to the raters’ annotations. In sum, our algorithm is accurate in determining temporal parameters related to gaze behavior when using HMD-based VR. Thus, the significant time required for human scoring among numerous raters can be rendered obsolete with a reliable automated scoring system. The algorithm proposed here was designed to sub-serve a separate study that uses TOFF and TFD to differentiate apathy from depression in those suffering from Alzheimer’s dementia. Full article

The interference of sidelobe often causes different targets to exhibit similar features, diminishing fine-grained classification accuracy. This effect is particularly pronounced when the available data are limited. To address the aforementioned issues, a novel classification framework for sidelobe-affected SAR imagery is proposed. First, a method based on maximum median filtering is adopted to remove sidelobe by exploiting local grayscale differences between the target and sidelobe, constructing a high-quality SAR dataset. Second, a deep metric learning network is constructed for fine-grained classification. To enhance the classification performance of the network on limited samples, a feature extraction module integrating a lightweight attention mechanism is designed to extract discriminative features. Then, a hybrid loss function is proposed to strengthen intra-class correlation and inter-class separability. Experimental results based on the FUSAR-Ship dataset demonstrate that the method exhibits excellent sidelobe suppression performance. Furthermore, the proposed framework achieves an accuracy of 84.18% across five ship target classification categories, outperforming the existing methods, significantly enhancing the classification performance in the context of sidelobe interference and limited datasets. Full article

Wireless sensor networks (WSNs) use distributed nodes for tasks such as environmental monitoring and surveillance. The existing anomaly detection methods fail to fully capture correlations in multi-node, multi-modal time series data, limiting their effectiveness. Additionally, they struggle with small sample scenarios because they do not effectively map features to classes. To address these challenges, this paper presents an anomaly detection approach that integrates deep learning with metric learning. A framework incorporating a graph attention network (GAT) and a Transformer is developed to capture spatial and temporal features. A novel distance measurement module improves similarity learning by considering both intra-class and inter-class relationships. Joint metric-classification training improves model accuracy and generalization. Experiments conducted on public datasets demonstrate that the proposed approach achieves an F1 score of 0.89, outperforming the existing approaches by 7%. Full article

Background: Cardiovascular risk assessment relies heavily on coronary calcium scoring. With an emphasis on varying slice increments, this study investigates the effectiveness of true and virtual non-contrast reconstructions on photon-counting CT. Reconstruction methods’ effects on calcium severity classifications are critical to the improvement in imaging techniques. Methods: This study comprised 77 participants (mean age: 63 ± 10 years, 43% female), of whom 0 had a coronary artery calcium score (CACS) of zero. In contrast to true non-contrast (TNC) 3 × 3 mm, the reconstructions included TNC 3 × 1.5 mm, virtual non-contrast (VNC) 3 × 3 mm, and VNC 3 × 1.5 mm. Agatston units served as the basis for classifications into standard clinical diagnostic categories. Results: High concordance between acquisition types was revealed by interclass correlation values (0.97–0.99). Comparing TNC 3 × 1.5 mm reconstructions to their VNC counterparts, misclassifications were less common (Cohen Kappa = 0.94). (K = 0.83–0.85). Significant differences in the average calcium scores and rates of misclassification highlighted the impact of reconstruction methods on precise evaluations. Conclusions: VNC methods demonstrated high agreement; however, with a small rate of misclassifications as compared to the gold standard method. VNC CACS may help optimize workflows but may need differing cutoffs as compared to traditional methods. Full article

Pest infestations remain a critical threat to global agriculture, significantly compromising crop yield and quality. While accurate pest detection forms the foundation of precision pest management, current approaches face two primary challenges: (1) the scarcity of comprehensive multi-scale, multi-category pest datasets and (2) performance limitations in detection models caused by substantial target scale variations and high inter-class morphological similarity. To address these issues, we present three key contributions: First, we introduce Insect25—a novel agricultural pest detection dataset containing 25 distinct pest categories, comprising 18,349 high-resolution images. This dataset specifically addresses scale diversity through multi-resolution acquisition protocols, significantly enriching feature distribution for robust model training. Second, we propose GC-Faster RCNN, an enhanced detection framework integrating a hybrid attention mechanism that synergistically combines channel-wise correlations and spatial dependencies. This dual attention design enables more discriminative feature extraction, which is particularly effective for distinguishing morphologically similar pest species. Third, we implement an optimized training strategy featuring a cosine annealing scheduler with linear warm-up, accelerating model convergence while maintaining training stability. Experiments have shown that compared with the original Faster RCNN model, GC-Faster RCNN has improved the average accuracy mAP0.5 on the Insect25 dataset by 4.5 percentage points, and mAP0.75 by 20.4 percentage points, mAP0.5:0.95 increased by 20.8 percentage points, and the recall rate increased by 16.6 percentage points. In addition, experiments have also shown that the GC-Faster RCNN detection method can reduce interference from multiple scales and high similarity between categories, improving detection performance. Full article