Search Results (3,698)

Multimodal review helpfulness prediction (MRHP) aims to identify the most helpful reviews by leveraging both textual and visual information. However, prior studies have primarily focused on modeling interactions between these modalities, often overlooking the consistency between review content and ratings, which is a key indicator of review credibility. To address this limitation, we propose CRCNet (Content–Rating Consistency Network), a novel MRHP model that jointly captures the semantic consistency between review content and ratings while modeling the complementary characteristics of text and image modalities. CRCNet employs RoBERTa and VGG-16 to extract semantic and visual features, respectively. A co-attention mechanism is applied to capture the consistency between content and rating, and a Gated Multimodal Unit (GMU) is adopted to integrate consistency-aware representations. Experimental results on two large-scale Amazon review datasets demonstrate that CRCNet outperforms both unimodal and multimodal baselines in terms of MAE, MSE, RMSE, and MAPE. Further analysis confirms the effectiveness of content–rating consistency modeling and the superiority of the proposed fusion strategy. These findings suggest that incorporating semantic consistency into multimodal architectures can substantially improve the accuracy and trustworthiness of review helpfulness prediction. Full article

Diacylglycerol-O-acyltransferase 1 (DGAT1, EC 2.3.1.20) is a pivotal enzyme in plant triacylglycerol (TAG) biosynthesis. Previous work identified conserved di-arginine (R) motifs (R-R, R-X-R, and R-X-X-R) in its N-terminal cytoplasmic acyl-CoA binding domain. To elucidate their functional significance, we engineered R-rich sequences in the N-termini of Tropaeolum majus and Zea mays DGAT1s. Comparative analysis with their respective non-mutant constructs showed that deleting or substituting R with glycine in the N-terminal region of DGAT1 markedly reduced lipid accumulation in both Camelina sativa seeds and Saccharomyces cerevisiae cells. Immunofluorescence imaging revealed co-localization of non-mutant and R-substituted DGAT1 with lipid droplets (LDs). However, disruption of an N-terminal di-R motif destabilizes DGAT1, alters LD organization, and impairs recombinant oleosin retention on LDs. Further evidence suggests that the di-R motif mediates DGAT1 retrieval from LDs to the endoplasmic reticulum (ER), implicating its role in dynamic LD–ER protein trafficking. These findings establish the conserved di-R motifs as important regulators of DGAT1 function and LD dynamics, offering insights for the engineering of oil content in diverse biological systems. Full article

Background/Objectives: There is significant interest in using texture features to extract hidden image-based information. In medical imaging applications using radiomics, AI, or personalized medicine, the quest is to extract patient or disease specific information while being insensitive to other system or processing variables. While we use digital breast tomosynthesis (DBT) to show these effects, our results would be generally applicable to a wider range of other imaging modalities and applications. Methods: We examine factors in texture estimation methods, such as quantization, pixel distance offset, and region of interest (ROI) size, that influence the magnitudes of these readily computable and widely used image texture features (specifically Haralick’s gray level co-occurrence matrix (GLCM) textural features). Results: Our results indicate that quantization is the most influential of these parameters, as it controls the size of the GLCM and range of values. We propose a new multi-resolution normalization (by either fixing ROI size or pixel offset) that can significantly reduce quantization magnitude disparities. We show reduction in mean differences in feature values by orders of magnitude; for example, reducing it to 7.34% between quantizations of 8–128, while preserving trends. Conclusions: When combining images from multiple vendors in a common analysis, large variations in texture magnitudes can arise due to differences in post-processing methods like filters. We show that significant changes in GLCM magnitude variations may arise simply due to the filter type or strength. These trends can also vary based on estimation variables (like offset distance or ROI) that can further complicate analysis and robustness. We show pathways to reduce sensitivity to such variations due to estimation methods while increasing the desired sensitivity to patient-specific information such as breast density. Finally, we show that our results obtained from simulated DBT images are consistent with what we see when applied to clinical DBT images. Full article

Accurate identification of predator–pest relationships is essential for implementing effective and sustainable biological control in agriculture. However, existing image-based methods struggle to recognize insect co-occurrence under complex field conditions, limiting their ecological applicability. To address this challenge, we propose a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and Transformer architectures for multi-label recognition of predator–pest combinations. The model leverages a novel co-occurrence attention mechanism to capture semantic relationships between insect categories and employs a pairwise label matching loss to enhance ecological pairing accuracy. Evaluated on a field-constructed dataset of 5,037 images across eight categories, the model achieved an F1-score of 86.5%, mAP50 of 85.1%, and demonstrated strong generalization to unseen predator–pest pairs with an average F1-score of 79.6%. These results outperform several strong baselines, including ResNet-50, YOLOv8, and Vision Transformer. This work contributes a robust, interpretable approach for multi-object ecological detection and offers practical potential for deployment in smart farming systems, UAV-based monitoring, and precision pest management. Full article

Background/Objectives: Magnetic nanoparticles, particularly iron oxide-based materials, such as magnetite (Fe₃O₄), have gained significant attention as contrast agents in medical imaging This study aimsto syntheze and characterize Fe₃O₄-based core–shell nanostructures, including Fe₃O₄@TiO₂ and Fe₃O₄@SiO₂, and to evaluate their potential as tunable contrast agents for diagnostic imaging. Methods: Fe₃O₄, Fe₃O₄@TiO₂, and Fe₃O₄@SiO₂ nanoparticles were synthesized via co-precipitation at varying temperatures from iron salt precursors. Fourier transform infrared spectroscopy (FTIR) was used to confirm the presence of Fe–O bonds, while X-ray diffraction (XRD) was employed to determine the crystalline phases and estimate average crystallite sizes. Morphological analysis and particle size distribution were assessed by scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDX) and transmission electron microscopy (TEM). Magnetic properties were investigated using vibrating sample magnetometry (VSM). Results: FTIR spectra exhibited characteristic Fe–O vibrations at 543 cm⁻¹ and 555 cm⁻¹, indicating the formation of magnetite. XRD patterns confirmed a dominant cubic magnetite phase, with the presence of rutile TiO₂ and stishovite SiO₂ in the coated samples. The average crystallite sizes ranged from 24 to 95 nm. SEM and TEM analyses revealed particle sizes between 5 and 150 nm with well-defined core–shell morphologies. VSM measurements showed saturation magnetization (Ms) values ranging from 40 to 70 emu/g, depending on the synthesis temperature and shell composition. The highest Ms value was obtained for uncoated Fe₃O₄ synthesized at 94 °C. Conclusions: The synthesized Fe₃O₄-based core–shell nanomaterials exhibit desirable structural, morphological, and magnetic properties for use as contrast agents. Their tunable magnetic response and nanoscale dimensions make them promising candidates for advanced diagnostic imaging applications. Full article

Artificial intelligence (AI) techniques—ranging from hybrid mechanistic–machine learning (ML) ensembles to gradient-boosted decision trees, support-vector machines, and deep neural networks—are transforming the management of seasonal influenza, respiratory syncytial virus (RSV), human immunodeficiency virus (HIV), and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Symptom-based triage models using eXtreme Gradient Boosting (XGBoost) and Random Forests, as well as imaging classifiers built on convolutional neural networks (CNNs), have improved diagnostic accuracy across respiratory infections. Transformer-based architectures and social media surveillance pipelines have enabled real-time monitoring of COVID-19. In HIV research, support-vector machines (SVMs), logistic regression, and deep neural network (DNN) frameworks advance viral-protein classification and drug-resistance mapping, accelerating antiviral and vaccine discovery. Despite these successes, persistent challenges remain—data heterogeneity, limited model interpretability, hallucinations in large language models (LLMs), and infrastructure gaps in low-resource settings. We recommend standardized open-access data pipelines and integration of explainable-AI methodologies to ensure safe, equitable deployment of AI-driven interventions in future viral-outbreak responses. Full article

In the wake of the continuous development of the international strategic petroleum reserve system, the tonnage and quantity of oil tankers have been increasing. This trend has driven the expansion of offshore oil exploration and transportation, resulting in frequent incidents of ship oil spills. Catastrophic impacts have been exerted on the marine environment by these accidents, posing a serious threat to economic development and ecological security. Therefore, there is an urgent need for efficient and reliable methods to detect oil spills in a timely manner and minimize potential losses as much as possible. In response to this challenge, a marine radar oil film segmentation method based on feature fusion and the artificial bee colony (ABC) algorithm is proposed in this study. Initially, the raw experimental data are preprocessed to obtain denoised radar images. Subsequently, grayscale adjustment and local contrast enhancement operations are carried out on the denoised images. Next, the gray level co-occurrence matrix (GLCM) features and Tamura features are extracted from the locally contrast-enhanced images. Then, the generalized least squares (GLS) method is employed to fuse the extracted texture features, yielding a new feature fusion map. Afterwards, the optimal processing threshold is determined to obtain effective wave regions by using the bimodal graph direct method. Finally, the ABC algorithm is utilized to segment the oil films. This method can provide data support for oil spill detection in marine radar images. Full article

Visual object tracking is one of the core techniques in human-centered artificial intelligence, which is very useful for human–machine interaction. State-of-the-art tracking methods have shown their robustness and accuracy on many challenges. However, a large amount of videos with precisely dense annotations are required for fully supervised training of their models. Considering that annotating videos frame-by-frame is a labor- and time-consuming workload, reducing the reliance on manual annotations during the tracking models’ training is an important problem to be resolved. To make a trade-off between the annotating costs and the tracking performance, we propose a weakly supervised tracking method based on co-saliency learning, which can be flexibly integrated into various tracking frameworks to reduce annotation costs and further enhance the target representation in current search images. Since our method enables the model to explore valuable visual information from unlabeled frames, and calculate co-salient attention maps based on multiple frames, our weakly supervised methods can obtain competitive performance compared to fully supervised baseline trackers, using only 3.33% of manual annotations. We integrate our method into two CNN-based trackers and a Transformer-based tracker; extensive experiments on four general tracking benchmarks demonstrate the effectiveness of our method. Furthermore, we also demonstrate the advantages of our method on egocentric tracking task; our weakly supervised method obtains 0.538 success on TREK-150, which is superior to prior state-of-the-art fully supervised tracker by 7.7%. Full article

The precise characterization of surface rupture zones and associated co-seismic displacement fields from large earthquakes provides critical insights into seismic rupture mechanisms, earthquake dynamics, and hazard assessments. Stereo-photogrammetric digital elevation models (DEMs), produced from high-resolution satellite stereo imagery, offer reliable global datasets that are suitable for the detailed extraction and quantification of vertical co-seismic displacements. In this study, we utilized pre- and post-event WorldView-2 stereo images of the 2024 Ms7.1 Wushi earthquake in Xinjiang to generate DEMs with a spatial resolution of 0.5 m and corresponding terrain point clouds with an average density of approximately 4 points/m². Subsequently, we applied the Iterative Closest Point (ICP) algorithm to perform differencing analysis on these datasets. Special care was taken to reduce influences from terrain changes such as vegetation growth and anthropogenic structures. Ultimately, by maintaining sufficient spatial detail, we obtained a three-dimensional co-seismic displacement field with a resolution of 15 m within grid cells measuring 30 m near the fault trace. The results indicate a clear vertical displacement distribution pattern along the causative sinistral–thrust fault, exhibiting alternating uplift and subsidence zones that follow a characteristic “high-in-center and low-at-ends” profile, along with localized peak displacement clusters. Vertical displacements range from approximately 0.2 to 1.4 m, with a maximum displacement of ~1.46 m located in the piedmont region north of the Qialemati River, near the transition between alluvial fan deposits and bedrock. Horizontal displacement components in the east-west and north-south directions are negligible, consistent with focal mechanism solutions and surface rupture observations from field investigations. The successful extraction of this high-resolution vertical displacement field validates the efficacy of satellite-based high-resolution stereo-imaging methods for overcoming the limitations of GNSS and InSAR techniques in characterizing near-field surface displacements associated with earthquake ruptures. Moreover, this dataset provides robust constraints for investigating fault-slip mechanisms within near-surface geological contexts. Full article

The development of scalable, non-invasive tools to assess tumor responsiveness to structurally active immunoformulations remains a critical unmet need in solid tumor immunotherapy. Here, we introduce a real-time, ex vivo functional system to classify tumor cell lines exposed to a phospholipoproteomic platform, without relying on cytotoxicity, co-culture systems, or molecular profiling. Tumor cells were monitored using IncuCyte^® S3 (Sartorius) real-time imaging under ex vivo neutral conditions. No dendritic cell components or immune co-cultures were used in this mode. All results are derived from direct tumor cell responses to structurally active formulations. Using eight human tumor lines, we captured proliferative behavior, cell death rates, and secretomic profiles to assign each case into stimulatory, inhibitory, or neutral categories. A structured decision-tree logic supported the classification, and a Functional Stratification Index (FSI) was computed to quantify the response magnitude. Inhibitory lines showed early divergence and high IFN-γ/IL-10 ratios; stimulatory ones exhibited a proliferative gain under balanced immune signaling. The results were reproducible across independent batches. This system enables quantitative phenotypic screening under standardized, marker-free conditions and offers an adaptable platform for functional evaluation in immuno-oncology pipelines where traditional cytotoxic endpoints are insufficient. This approach has been codified into the STIP (Structured Traceability and Immunophenotypic Platform), supporting reproducible documentation across tumor models. This platform contributes to upstream validation logic in immuno-oncology workflows and supports early-stage regulatory documentation. Full article

Novel high-entropy perovskite oxide powders were synthesized using a sol-gel process. The B-site contained five cations: chromium, cobalt, iron, manganese, and nickel. The B-site cations were present on an equiatomic basis. The A-site cation was lanthanum, with calcium doping. The amount of A-site doping varied from 0 to 30 at%, yielding a composition of La_1−xCa_x(Co_0.2Cr_0.2Fe_0.2Mn_0.2Ni_0.2)O_3−δ. The resulting perovskite powders were pressurelessly sintered in air at 1400 °C for 2 h. Sintered densities were measured, and the grain structure was imaged via scanning electron microscopy to investigate the effect of doping. Samples were cut and polished, and their resistance was measured at varying temperatures in air to obtain the electrical conductivity and the mechanism that governs it. Plots of electrical conductivity as a function of composition and temperature indicate that the increased configurational entropy of the perovskite materials has a demonstrable effect. Full article

Background: Often, neoadjuvant therapy, which relies on the induction of double-strand breaks (DSBs), is used prior to surgery to shrink tumors by inducing cancer cell apoptosis. However, recent studies have suggested that this treatment may also induce a fluctuating state between senescence and stemness in PA-1 embryonal carcinoma cells, potentially affecting therapeutic outcomes. Thus, the respective epigenetic pathways are up or downregulated over a time period of days. These fluctuations go hand in hand with changes in spatial DNA organization. Methods: By means of Single-Molecule Localization Microscopy in combination with mathematical evaluation tools for pointillist data sets, we investigated the organization of euchromatin and heterochromatin at the nanoscale on the third and fifth day after etoposide treatment. Results: Using fluorescently labeled antibodies against H3K9me3 (heterochromatin tri-methylation sites) and H3K4me3 (euchromatin tri-methylation sites), we found that the induction of DSBs led to the de-condensation of heterochromatin and compaction of euchromatin, with a peak effect on day 3 after the treatment. On day 3, we also observed the co-localization of euchromatin and heterochromatin, which have marks that usually occur in exclusive low-overlapping network-like compartments. The evaluation of the SMLM data using topological tools (persistent homology and persistent imaging) and principal component analysis, as well as the confocal microscopy analysis of H3K9me3- and H3K4me3-stained PA-1 cells, supported the findings that distinct shifts in euchromatin and heterochromatin organization took place in a subpopulation of these cells during the days after the treatment. Furthermore, by means of flow cytometry, it was shown that the rearrangements in chromatin organization coincided with the simultaneous upregulation of the stemness promotors OCT4A and SOX2 and senescence promotors p21Cip1 and p27. Conclusions: Our findings suggest potential applications to improve cancer therapy by inhibiting chromatin remodeling and preventing therapy-induced senescence. Full article

Objectives: Facial soft tissue imaging is crucial in orthodontic treatment planning, and the structured light scanning technology found in the latest iPhone models constitutes a promising method. Currently, studies which evaluate the accuracy of smartphone-based three-dimensional (3D) facial scanners are scarce. This study compares smartphone scans with cone-beam computed tomography (CBCT) images. Materials and Methods: Three-dimensional images of 23 screened patients were captured with the camera of an iPhone 13 Pro Max and processed with the Scandy Pro application; CBCT scans were also taken as a standard of care. After establishing unique image pairs of the same patient, linear and angular measurements were compared between the images to assess the scanner’s two-dimensional trueness. Following the co-registration of the virtual models, a heat map was generated, and root mean square (RMS) deviations were calculated for quantitative assessment of 3D trueness. Precision was determined by comparing consecutive 3D facial scans of five participants, while intraobserver reliability was assessed by repeating measurements on five subjects after a two-week interval. Results: This study found no significant difference in soft tissue measurements between smartphone and CBCT images (p > 0.05). The mean absolute difference was 1.43 mm for the linear and 3.16° for the angular measurements. The mean RMS value was 1.47 mm. Intraobserver reliability and scanner precision were assessed, and the Intraclass Correlation Coefficients were found to be excellent. Conclusions: Smartphone facial scanners offer an accurate and reliable alternative to stereophotogrammetry systems, though clinicians should exercise caution when examining the lateral sections of those images due to inherent inaccuracies. Full article

In this study, we demonstrated that lrp6a, a co-receptor in the Wnt signaling pathway, is essential for proper median fin formation and somitogenesis in goldfish. We analyzed the gene’s sequence features and expression patterns in both wen-type and egg-type goldfish, uncovering distinct tissue-specific expression differences between the two varieties. To explore the functional role of lrp6a, we performed CRISPR/Cas9-mediated gene knockout using eight designed single-guide RNAs (sgRNAs), of which four showed effective targeting. Three high-efficiency sgRNAs were selected and co-injected into embryos to achieve complete gene disruption. Morphological assessments and X-ray microtomography (μCT) imaging of the resulting mutants revealed various abnormalities, including defects in the dorsal, caudal, and anal fins, as well as skeletal deformities near the caudal peduncle. These results confirm that lrp6a plays a key role in median fin development and axial patterning, offering new insights into the genetic regulation of fin formation in teleost fish. Full article

Image registration constitutes the fundamental basis for the joint interpretation of synthetic aperture radar (SAR) and optical images. However, robust image registration remains challenging due to significant regional heterogeneity in remote sensing scenes (e.g., co-existing urban and marine areas within a single image). To overcome this challenge, this article proposes a novel optical–SAR image registration method named Gradient and Standard Deviation Feature Weighted Fusion (GDWF). First, a Block-local standard deviation (Block-LSD) operator is proposed to extract block-based feature points with regional adaptability. Subsequently, a dual-modal feature description is developed, constructing both gradient-based descriptors and local standard deviation (LSD) descriptors for the neighborhoods surrounding the detected feature points. To further enhance matching robustness, a confidence-weighted feature fusion strategy is proposed. By establishing a reliability evaluation model for similarity measurement maps, the contribution weights of gradient features and LSD features are dynamically optimized, ensuring adaptive performance under varying conditions. To verify the effectiveness of the method, different optical and SAR datasets are used to compare it with the currently advanced algorithms MOGF, CFOG, and FED-HOPC. The experimental results demonstrate that the proposed GDWF algorithm achieves the best performance in terms of registration accuracy and robustness among all compared methods, effectively handling optical–SAR image pairs with significant regional heterogeneity. Full article