Search Results (326)

This paper presents ACTD-Net (Attention-Convolutional Transformer Denoising Network), a novel hybrid deep learning approach for speckle noise reduction from differential synthetic aperture radar (SAR) interferometric phase maps. Differential interferometric SAR (DInSAR) is a powerful technique for detecting and quantifying surface deformations, but the obtained phase maps are corrupted by speckle noise, topographic contributions, and atmospheric artifacts. Effective speckle denoising is crucial for accurate extraction of the desired deformation information. ACTD-Net combines the strengths of convolutional neural networks (CNNs) and vision transformers (ViTs) in a two-stage architecture. First, a modified U-Net model with residual connections performs initial despeckling of the input DInSAR phase map. Then, the denoised phase map is fed into a Swin Transformer adapted with a masked self-attention mechanism, which further refines the denoising while preserving fine details and discontinuities related to surface deformations. Experimental results on simulated and real DInSAR data, including from the September 2023 Morocco earthquake region, demonstrate the effectiveness of ACTD-Net, outperforming traditional techniques and current deep learning methods in terms of quantitative metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and edge preservation index (EPI). The comprehensive evaluation shows that ACTD-Net achieves up to 33.55 dB PSNR, 0.96 SSIM, and 0.94 EPI on simulated data, and 33.62 ± 2.75 dB PSNR on 388 real Morocco earthquake patches, with significant improvements in preserving phase discontinuities and reducing unwrapping errors by approximately 62% on real earthquake data. Full article

Artificial intelligence (AI) shows great promise for transforming the agriculture sector and can enable the development of many modern farming practices over conventional methods. Nowadays, AI agents and agentic AI have attained popularity due to their autonomous structure and working mechanism. This research work proposes an agentic AI framework that integrates multiple agents developed for farming land to promote climate-smart agriculture and support United Nations (UN) sustainable development goals (SDGs). The developed structure has four agents: Agent A for monitoring soil properties, Agent B for weather sensing, Agent C for disease detection vision sensing in rice crops, and Agent D, a multi-agent supervisor agent chatbot connected with the other agents. The overall objective was to connect all agents on a single platform to obtain sensor data and perform a predictive analysis. This will help farmers and landowners obtain information about weather conditions, soil properties, and vision-based disease detection so that appropriate measures can be taken on agricultural land for rice crops. For soil properties (nitrogen, phosphorus, and potassium) from Agent A and climate data (temperature and humidity) from Agent B, we deployed the long short-term memory (LSTM), gated recurrent unit (GRU), and one-dimensional convolutional neural network (1D-CNN) predictive models, which achieved an accuracy of 93.4%, 94%, and 96% for Agent A; a 0.27 mean absolute error (MAE) for temperature; and a 2.9 MAE for humidity on the Agent B data. For Agent C, we used vision transformer (ViT), MobileViT, and RiceNet (with a diffusion model layer as a feature extractor) models to detect disease. The models achieved accuracies of 95%, 98.5%, and 85.4% during training respectively. Overall, the proposed framework demonstrates how agentic AI can be used to transform conventional farming practices into a digital process, thereby supporting smart agriculture. Full article

Background and Objectives: Reduced bone quality due to osteoporosis significantly complicates oral rehabilitation and bone regeneration therapies. While Vitamin D (Vit. D3) is crucial for osteogenesis, systemic administration often lacks local efficacy. This study aimed to evaluate the osteoregenerative potential of a novel Chitosan-based nanostructured scaffold (NS) loaded with Vit. D3, underlining its efficacy in vitro and in an ovariectomized (OVX) rat model of osteoporosis. Materials and Methods: Chitosan NSs were fabricated with varying Vit. D3 concentrations. In vitro assessments included cytotoxicity (MTT assay), cell viability (Alamar Blue), and mineralization (Alizarin Red) using human dental follicle stem cells. In vivo, 30 Wistar rats were ovariectomized to induce osteoporosis (confirmed by biomarkers Osteocalcin and β-CTX) and were divided into three groups (n = 10). Bilateral maxillary bone defects were treated with (1) a Control (clot only), (2) a Hemostatic Sponge with Vit. D3 (HS/Vit. D3), or (3) an NS loaded with Vit. D3 (NS/Vit. D3-6.25 ng/mL). Histological and morphometric analyses were performed at 4 and 8 weeks. Results: In vitro, the NS loaded with 6.25 ng/mL Vit. D3 demonstrated superior cytocompatibility, achieving a cell viability of 117.77% at 72 h and significantly enhanced calcium nodule deposition compared to controls. In vivo, a total of 44 defect sites were analyzed following the exclusion of compromised samples (Control: 16 sites; HS/Vit. D3: 16 sites; NS/Vit. D3: 12 sites). The NS/Vit. D3-6.25 ng/mL group exhibited the highest degree of mature bone formation and vascularization (p < 0.05) compared to the Control and HS/Vit. D3 groups. While cellular activity (osteoblasts/osteocytes) was initially higher in the HS/Vit. D3 group, the NS/Vit. D3-6.25 ng/mL group achieved superior structural integration and scaffold replacement by mature bone tissue over time. Conclusions: The novel Vit. D3-loaded Chitosan NS effectively promotes bone regeneration in osteoporotic conditions. It supports osteogenic differentiation in vitro and enhances bone matrix maturation in vivo, suggesting its potential as a bioactive scaffold for regenerative dentistry. Full article

Background/aim: Vitamin D (VitD) has been implicated in neuroprotection, yet its role in Parkinson’s disease (PD) remains unclear. This systematic review and meta-analysis aimed to evaluate the association between VitD status, supplementation, and vitamin D receptor (VDR) gene polymorphisms with PD risk and outcomes. Methodology: Following PRISMA guidelines, we searched PubMed, Scopus, and Google Scholar through August 2025 for observational studies, clinical trials, and genetic association studies. Primary outcomes included serum VitD levels in PD versus healthy controls (HCs), prevalence of VitD insufficiency/deficiency, and effects of VitD supplementation on motor symptoms. Secondary outcomes assessed associations between VDR polymorphisms and PD susceptibility. Data were synthesized using random- and fixed-effects models, with heterogeneity and publication bias evaluated. PROSPERO (CRD420251133875). Results: Sixty-three studies (n ≈ 10,700 participants) met inclusion criteria. PD patients exhibited significantly lower VitD levels (SMD = −0.46; 95% CI: −0.51 to −0.41) and higher odds of insufficiency (OR = 1.52) and deficiency (OR = 2.20) compared to HC. Cohort data suggested sufficient VitD may reduce PD risk (HR = 0.83). Supplementation yielded modest, non-significant improvements in motor outcomes. Among 20 genetic studies, FokI (rs2228570) was most consistently associated with PD, while other VDR SNPs showed variable or null associations. Conclusions: VitD deficiency is common in PD and may influence disease risk and motor function. Current evidence indicates limited benefit of supplementation for motor outcomes, and genetic associations remain inconsistent. Full article

Background: Dysphagia from aging, neurodegeneration, structural anomalies, or cognitive decline harms quality of life. The videofluoroscopic swallowing study (VFSS) is the diagnostic gold standard but manual interpretation is labor-intensive and costly, motivating automation. Methods: We introduce a Vision Transformer (ViT) using a temporal sliding window and 3D patch tokenization to capture spatio-temporal dependencies in variable-length VFSS via attention. Training/evaluation used 1154 VFSS sequences from 107 individuals (548 abnormal, 606 normal) with 5-fold cross-validation and comparisons to VGG-16, ResNet-50, EfficientNet-V1/V2, and MobileNet. Results: The ViT achieved 84.37 ± 1.15% accuracy, 90.81 ± 2.11% sensitivity, 79.49 ± 1.66% specificity, 82.94 ± 2.76% precision, 85.68 ± 1.54% F1-score, and AUC 0.878 (5-fold). It outperformed all CNN baselines across metrics; paired t-tests confirmed significant gains (p < 0.05). Conclusions: The pure ViT’s attention-based spatio-temporal modeling yields robust VFSS classification and is well-suited for screening workflows requiring timely abnormality detection, providing a foundation for clinically deployable VFSS analysis. Full article

Low-dose computed tomography (LDCT) has become a widely adopted protocol to reduce radiation exposure during clinical imaging. However, dose reduction inevitably amplifies noise and artifacts, compromising image quality and diagnostic confidence. To address this challenge, this study introduces De-TransGAN, a transformer-augmented Generative Adversarial Network specifically designed for high-fidelity LDCT image denoising. Unlike conventional CNN-based denoising models, De-TransGAN combines convolutional layers with transformer blocks to jointly capture local texture details and long-range anatomical dependencies. To further guide the network toward diagnostically critical structures, we embed channel–spatial attention modules based on the Convolutional Block Attention Module (CBAM). On the discriminator side, a hybrid design integrating PatchGAN and vision transformer (ViT) components enhances both fine-grained texture discrimination and global structural consistency. Training stability is achieved using the Wasserstein GAN with Gradient Penalty (WGAN-GP), while a composite objective function—L1 loss, SSIM loss, and VGG perceptual loss—ensures pixel-level fidelity, structural similarity, and perceptual realism. De-TransGAN was trained on the TCIA LDCT and Projection Data dataset and validated on two additional benchmarks: the AAPM Mayo Clinic Low Dose CT Grand Challenge dataset and a private clinical chest LDCT dataset comprising 524 scans (used for qualitative assessment only, as no NDCT ground truth is available). Across these datasets, the proposed method consistently outperformed state-of-the-art CNN- and transformer-based denoising models. On the LDCT and Projection dataset head images, it achieved a PSNR of 44.9217 dB, SSIM of 0.9801, and RMSE of 1.001, while qualitative evaluation on the private dataset confirmed strong generalization with clear noise suppression and preservation of fine anatomical details. These findings establish De-TransGAN as a clinically viable approach for LDCT denoising, enabling radiation reduction without compromising diagnostic quality. Full article

The intelligent fault detection of power plant equipment in industrial settings often grapples with challenges such as insufficient real-time performance and interference from complex backgrounds. To address these issues, this paper proposes an image recognition and classification model based on the VMamba architecture. At the core of our feature extraction module, we have improved and optimized the two-dimensional state space (SS2D) algorithm to replace the traditional convolution operation. Rooted in State-Space Models (SSMs), the SS2D module possesses a global receptive field by design, enabling it to effectively capture long-range dependencies and establish comprehensive contextual relationships between local and global features. Crucially, unlike the self-attention mechanism in Vision Transformers (ViT) that suffers from quadratic computational complexity, VMamba achieves this global modeling with linear complexity, significantly enhancing computational efficiency. Furthermore, we employ an enhanced PAN-FPN multi-scale feature fusion strategy integrated with the Squeeze-and-Excitation (SE) attention mechanism. This combination optimizes the spatial distribution of feature representations through channel-wise attention weighting, facilitating the effective integration of cross-level spatial features and the suppression of background noise. This study thus presents a solution for industrial equipment fault diagnosis that achieves a superior balance between high accuracy and low latency. Full article

Accurate, high-throughput estimation of Above-Ground Biomass (AGB), a key predictor of yield, is a critical goal in rapeseed breeding. However, this is constrained by two key challenges: (1) traditional measurement is destructive and laborious, and (2) modern deep learning approaches require vast, costly labeled datasets. To address these issues, we present a data-efficient deep learning framework using smartphone-captured top-down RGB images for AGB estimation (Fresh Weight, FW, and Dry Weight, DW). Our approach utilizes a two-stage strategy where a Vision Transformer (ViT) backbone is first pre-trained on a large, aggregated dataset of diverse, non-rapeseed public plant datasets using the DINOv2 self-supervised learning (SSL) method. Subsequently, this pre-trained model is fine-tuned on a small, custom-labeled rapeseed dataset (N = 833) using a Multi-Task Learning (MTL) framework to simultaneously regress both FW and DW. This MTL approach acts as a powerful regularizer, forcing the model to learn robust features related to the 3D plant structure and density. Through rigorous 5-fold cross-validation, our proposed model achieved strong predictive performance for both Fresh Weight (Coefficient of Determination, R² = 0.842) and Dry Weight (R² = 0.829). The model significantly outperformed a range of baselines, including models trained from scratch and those pre-trained on the generic ImageNet dataset. Ablation studies confirmed the critical and synergistic contributions of both domain-specific SSL (vs. ImageNet) and the MTL framework (vs. single-task training). This study demonstrates that an SSL+MTL framework can effectively learn to infer complex 3D plant attributes from 2D images, providing a robust and scalable tool for non-destructive phenotyping to accelerate the rapeseed breeding cycle. Full article

Background/Objectives: Postpartum depression (PPD) represents a major public health issue, with a direct impact on the quality of life of the mother–infant dyad. 25-hydroxyvitamin D (25(OH)D), hereafter referred to as VitD, has been suggested to exert protective effects on mood regulation. However, current findings remain inconsistent. This study aimed to assess the association between gestational VitD deficiency (≤19.9 µg/mL) and the diagnosis of PPD three months after delivery. Methods: This longitudinal study followed mother–child dyads in the city of Pelotas, RS, Brazil. A total of 983 pregnant women were initially recruited, of whom 713 had complete data available for this analysis. Blood samples were collected up to 24 weeks of gestation for subsequent measurement of serum VitD levels using chemiluminescence, and PPD diagnosis was established using the Mini International Neuropsychiatric Interview (M.I.N.I. Plus). Logistic regression models were applied and adjusted for potential confounders, such as maternal age, socioeconomic status, and history of depression during pregnancy. Results: In the adjusted model, deficient serum VitD levels were associated with a two-fold-higher likelihood of PPD diagnosis compared to insufficient/sufficient VitD levels (≥20 µg/mL) (OR = 2.0; 95% CI 1.0–4.2; p = 0.049). Conclusions: These findings highlight the potential role of VitD in maternal mental health and support the importance of monitoring VitD status during pregnancy. From a public health standpoint, ensuring adequate vitamin D levels in prenatal care may contribute to reducing the burden of postpartum depression. Full article

Accurate 3D hand pose estimation remains a key challenge due to the scarcity of annotated training data. While 2D studies have shown that incorporating additional modalities like language can mitigate data limitations, leveraging such strategies in the 3D domain remains underexplored. Inspired by the success of CLIP in vision-language tasks, we propose TriPose, a tri-modal framework that integrates image, text, and point cloud data for robust 3D hand pose estimation. Recognizing that CLIP is not optimized for spatial localization, we design structured textual representations for hand poses and employ CLIP visual encoder to extract global semantic features. To address CLIP’s spatial limitations, we introduce a spatial-awareness module tailored to ViT’s architecture. The model is pre-trained on image–text–point cloud triplets, enabling precise pose localization through multi-modal alignment. Experiments on MSRA, ICVL, and NYU datasets show that TriPose consistently outperforms state-of-the-art methods, especially on the low-resource ICVL dataset, demonstrating the effectiveness of our structured language supervision and tri-modal fusion strategy in enhancing 3D hand pose understanding. Full article

(1) Background: this study aimed to determine whether a serum parathyroid hormone (PTH) threshold of 40 pg/mL represents a clinically relevant risk factor for vitamin D (VitD) deficiency and reduced bone mineral density (BMD). It also investigated potential genetic interactions influencing PTH regulation and skeletal health in patients with periodontitis. (2) Methods: a cross-sectional analysis was conducted on 1038 periodontitis patients (35–75 years). Serum PTH, VitD, calcium (Ca), phosphate (P), and urinary parameters were assessed. Dual-energy X-ray absorptiometry (DXA) was used to evaluate BMD in 261 subjects. Vitamin D Receptor (VDR) and estrogen receptor alpha (ERα) polymorphisms were genotyped, and composite genetic risk scores were calculated. Statistical analyses included correlation tests, subgroup comparisons, and regression models. (3) Results: sixty-two percent of individuals had PTH > 40 pg/mL, which was associated with significantly lower 25(OH)D and Ca levels and reduced T-scores (p < 0.05). PTH levels negatively correlated with BMD (Pearson’s r = –0.159, p = 0.0105). Patients with higher ERα polymorphism scores showed increased PTH values (p < 0.05), while VDR variants demonstrated a positive but no significant trend. (4) Conclusions: a PTH threshold of 40 pg/mL identifies individuals at higher risk of VitD deficiency and skeletal fragility, even without overt hypercalcemia. Genetic factors, particularly ERα variants, may contribute to elevated PTH levels, suggesting value in integrating biochemical, densitometric, and genetic screening for early bone health risk stratification. Full article

Background/Objectives: Vitamin D deficiency contributes to pathological vertebral fragility (path-VF), including fragility fractures and early pedicle screw loosening after posterior instrumented spinal fusion (PISF). Supplementation practices remain inconsistent. This retrospective study evaluated whether patients with path-VF receive appropriate vitamin D3 (Vit.D3) supplementation and assessed the dose–response relationship between daily intake and path-VF risk, particularly in older adults. Methods: A total of 210 patients treated with kyphoplasty or PISF (2022–2023) were classified into a path-VF or control group. Daily oral Vit.D3 intake was categorised as Zero- (0 IU), Low- (<2000 IU), or High-Dose (≥2000 IU). Statistical analyses were performed for each dosage group, including subgroup analyses for patients aged ≥67.5 years. Vertebral BMD was estimated using mean Hounsfield Units (HU) from T11–L5. Results: Patients in the path-VF group received significantly lower Vit.D3 doses than controls (1431.4 ± 1055.7 vs. 2366.7 ± 1186.7 IU/day, p < 0.001). Low-dose supplementation was associated with a markedly increased risk of path-VF compared with high-dose in the overall cohort (OR = 6.5, p = 0.003) and in patients aged ≥67.5 years (OR = 8.6, p = 0.008). Logistic regression identified a threshold of 1900 IU/day (AUC = 0.805). Mean vertebral HU values were significantly lower in the path-VF group than in controls (71.9 ± 29.1 vs. 133.5 ± 52.6, p < 0.001), and no consistent HU gains were observed with increasing Vit.D3 dosage. Conclusions: Low-dose Vit.D3 supplementation was associated with increased path-VF risk, especially in patients aged >67.5 years. Patients without path-VF had received significantly higher doses, suggesting broader benefits of adequate Vit.D3 beyond bone density. A daily intake above 1900 IU may serve as a practical threshold for at-risk elderly patients. Full article

Accurate food mass estimation is a key component of automated calorie estimation tools, and there is growing interest in leveraging image analysis for this purpose due to its ease of use and scalability. However, current methods face important limitations. Some rely on 3D sensors for depth estimation, which are not widely accessible to all users, while others depend on camera intrinsic parameters to estimate volume, reducing their adaptability across different devices. Furthermore, AI-based approaches that bypass these parameters often struggle with generalizability when applied to images captured using diverse sensors or camera settings. To overcome these challenges, we introduce a three-stage, transformer-based method for estimating food mass from RGB images, balancing accuracy, computational efficiency, and scalability. The first stage applies the Segment Anything Model (SAM 2) to segment food items in images from the SUECFood dataset. Next, we use the Global-Local Path Network (GLPN) to perform monocular depth estimation (MDE) on the Nutrition5k dataset, inferring depth information from a single image. These outputs are then combined through alpha compositing to generate enhanced composite images with precise object boundaries. Finally, a Vision Transformer (ViT) model processes the composite images to estimate food mass by extracting relevant visual and spatial features. Our method achieves notable improvements in accuracy compared to previous approaches, with a mean squared error (MSE) of 5.61 and a mean absolute error (MAE) of 1.07. Notably, this pipeline does not require specialized hardware like depth sensors or multi-view imaging, making it well-suited for practical deployment. Future work will explore the integration of ingredient recognition to support a more comprehensive dietary assessment system. Full article

There have been significant breakthroughs in developing models for segmenting 3D medical images, with many promising results attributed to the incorporation of Vision Transformers (ViT). However, the fundamental mechanism of transformers, known as self-attention, has quadratic complexity, which significantly increases computational requirements, especially in the case of 3D medical images. In this paper, we investigate the UNETR++ model and propose a voxel-focused attention mechanism inspired by TransNeXt pixel-focused attention. The core component of UNETR++ is the Efficient Paired Attention (EPA) block, which learns from two interdependent branches: spatial and channel attention. For spatial attention, we incorporated the voxel-focused attention mechanism, which has linear complexity with respect to input sequence length, rather than projecting the keys and values into lower dimensions. The deficiency of UNETR++ lies in its reliance on dimensionality reduction for spatial attention, which reduces efficiency but risks information loss. Our contribution is to replace this with a voxel-focused attention design that achieves linear complexity without low-dimensional projection, thereby reducing parameters while preserving representational power. This effectively reduces the model’s parameter count while maintaining competitive performance and inference speed. On the Synapse dataset, the enhanced UNETR++ model contains 21.42 M parameters, a 50% reduction from the original 42.96 M, while achieving a competitive Dice score of 86.72%. Full article

Corneal fibrosis, a significant source of visual impairment, can result from keratocyte-to-myofibroblast transdifferentiation during wound healing. This study investigated the antifibrotic role of 1,25-dihydroxyvitamin D₃ (1,25 Vit D) and the lesser-known vitamin D, 24,25-dihydroxyvitamin D₃ (24,25 Vit D), in human and mouse corneal stromal cells (HSCs and MSCs) and in a Vit D receptor knockout (VDR KO) mouse model. Cells were treated with TGF-β1 ± Vit D metabolites and the expression of fibrotic and antifibrotic genes and proteins was evaluated. Both metabolites significantly reduced α-smooth muscle actin levels in HSCs, MSCs and organ-cultured mouse corneas (p < 0.05). They also upregulated the mRNA expression of BMP2, BMP6, BMPR2, and TGF-β3, as well as the protein expression of BMP6 and TGF-β3. VDR KO corneas subjected to alkali injury exhibited increased fibrotic responses and reduced CD45+ immune cell infiltration compared to wild-type controls. Notably, 24,25 Vit D exerted antifibrotic effects even in VDR KO cells, and the alternative 24,25 Vit D receptor FAM57B was expressed in all corneal cell layers. These results reveal consistent antifibrotic effects of both 1,25 and 24,25 Vit D across species, support the existence of VDR-independent mechanisms in the cornea, and offer new insights into potential therapeutic strategies for preventing corneal fibrosis. Full article