Explore the vast range of titles available.

Influence, the ability to change the beliefs and behaviors of others, is the main currency on social media. Extant studies of influence on social media, however, are limited by publicly available data that record expressions (active engagement of users with content, such as likes and comments), but neglect impressions (exposure to content, such as views) and lack “ground truth” measures of influence. To overcome these limitations, we implemented a social media simulation using an original, web-based micro-blogging platform. We propose three influence models, leveraging expressions and impressions to create a more complete picture of social influence. We demonstrate that impressions are much more important drivers of influence than expressions, and our models accurately identify the most influential accounts in our simulation. Impressions data also allow us to better understand important social media dynamics, including the emergence of small numbers of influential accounts and the formation of opinion echo chambers.

Generating general-purpose vector representations of networks allows us to analyze them without the need for extensive feature-engineering. Recent works have shown that the hyperbolic space can naturally represent the structure of networks, and that embedding networks into hyperbolic space is extremely efficient, especially in low dimensions. However, the existing hyperbolic embedding methods apply to static networks and cannot capture the dynamic evolution of the nodes and edges of a temporal network. In this paper, we present an unsupervised framework that uses temporal random walks to obtain training samples with both temporal and structural information to learn hyperbolic embeddings from continuous-time dynamic networks. We also show how the framework extends to attributed and heterogeneous information networks. Through experiments on five publicly available real-world temporal datasets, we show the efficacy of our model in embedding temporal networks in low-dimensional hyperbolic space compared to several other unsupervised baselines. We show that our model obtains state-of-the-art performance in low dimensions, outperforming all baselines, and has competitive performance in higher dimensions, outperforming the baselines in three of the five datasets. Our results show that embedding temporal networks in hyperbolic space is extremely effective when necessitating low dimensions.

This study aimed to develop a deep learning radiomic model using multimodal imaging to differentiate benign and malignant breast tumours. Multimodality imaging data, including ultrasonography (US), mammography (MG), and magnetic resonance imaging (MRI), from 322 patients (112 with benign breast tumours and 210 with malignant breast tumours) with histopathologically confirmed breast tumours were retrospectively collected between December 2018 and May 2023. Based on multimodal imaging, the experiment was divided into three parts: traditional radiomics, deep learning radiomics, and feature fusion. We tested the performance of seven classifiers, namely, SVM, KNN, random forest, extra trees, XGBoost, LightGBM, and LR, on different feature models. Through feature fusion using ensemble and stacking strategies, we obtained the optimal classification model for benign and malignant breast tumours. In terms of traditional radiomics, the ensemble fusion strategy achieved the highest accuracy, AUC, and specificity, with values of 0.892, 0.942 [0.886-0.996], and 0.956 [0.873-1.000], respectively. The early fusion strategy with US, MG, and MRI achieved the highest sensitivity of 0.952 [0.887-1.000]. In terms of deep learning radiomics, the stacking fusion strategy achieved the highest accuracy, AUC, and sensitivity, with values of 0.937, 0.947 [0.887-1.000], and 1.000 [0.999-1.000], respectively. The early fusion strategies of US+MRI and US+MG achieved the highest specificity of 0.954 [0.867-1.000]. In terms of feature fusion, the ensemble and stacking approaches of the late fusion strategy achieved the highest accuracy of 0.968. In addition, stacking achieved the highest AUC and specificity, which were 0.997 [0.990-1.000] and 1.000 [0.999-1.000], respectively. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity of 1.000 [0.999-1.000] under the early fusion strategy. This study demonstrated the potential of integrating deep learning and radiomic features with multimodal images. As a single modality, MRI based on radiomic features achieved greater accuracy than US or MG. The US and MG models achieved higher accuracy with transfer learning than the single-mode or radiomic models. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity under the early fusion strategy, showed higher diagnostic performance, and provided more valuable information for differentiation between benign and malignant breast tumours.

The relative hostile media effect suggests that partisans tend to perceive the bias of slanted news differently depending on whether the news is slanted in favor of or against their sides. To explore the effect of an algorithmic vs. human source on hostile media perceptions, this study conducts a 3 (author attribution: human, algorithm, or human-assisted algorithm) x 3 (news attitude: pro-issue, neutral, or anti-issue) mixed factorial design online experiment (N = 511). This study uses a transformer-based adversarial network to auto-generate comparable news headlines. The framework was trained with a dataset of 364,986 news stories from 22 mainstream media outlets. The results show that the relative hostile media effect occurs when people read news headlines attributed to all types of authors. News attributed to a sole human source is perceived as more credible than news attributed to two algorithm-related sources. For anti-Trump news headlines, there exists an interaction effect between author attribution and issue partisanship while controlling for people’s prior belief in machine heuristics. The difference of hostile media perceptions between the two partisan groups was relatively larger in anti-Trump news headlines compared with pro-Trump news headlines.

Background Breast cancer is one of the most serious diseases threatening women’s health. Early screening based on ultrasound can help to detect and treat tumours in the early stage. However, due to the lack of radiologists with professional skills, ultrasound-based breast cancer screening has not been widely used in rural areas. Computer-aided diagnosis (CAD) technology can effectively alleviate this problem. Since breast ultrasound (BUS) images have low resolution and speckle noise, lesion segmentation, which is an important step in CAD systems, is challenging. Results Two datasets were used for evaluation. Dataset A comprises 500 BUS images from local hospitals, while dataset B comprises 205 open-source BUS images. The experimental results show that the proposed method outperformed its related classic segmentation methods and the state-of-the-art deep learning model RDAU-NET. Its accuracy (Acc), Dice similarity coefficient (DSC) and Jaccard index (JI) reached 96.25%, 78.4% and 65.34% on dataset A, and its Acc, DSC and sensitivity reached 97.96%, 86.25% and 88.79% on dataset B, respectively. Conclusions We proposed an adaptive morphological snake based on marked watershed (AMSMW) algorithm for BUS image segmentation. It was proven to be robust, efficient and effective. In addition, it was found to be more sensitive to malignant lesions than benign lesions. Methods The proposed method consists of two steps. In the first step, contrast limited adaptive histogram equalization (CLAHE) and a side window filter (SWF) are used to preprocess BUS images. Lesion contours can be effectively highlighted, and the influence of noise can be eliminated to a great extent. In the second step, we propose adaptive morphological snake (AMS). It can adjust the working parameters adaptively according to the size of the lesion. Its segmentation results are combined with those of the morphological method. Then, we determine the marked area and obtain candidate contours with a marked watershed (MW). Finally, the best lesion contour is chosen by the maximum average radial derivative (ARD).

Background The rapid development of artificial intelligence technology has improved the capability of automatic breast cancer diagnosis, compared to traditional machine learning methods. Convolutional Neural Network (CNN) can automatically select high efficiency features, which helps to improve the level of computer-aided diagnosis (CAD). It can improve the performance of distinguishing benign and malignant breast ultrasound (BUS) tumor images, making rapid breast tumor screening possible. Results The classification model was evaluated with a different dataset of 100 BUS tumor images (50 benign cases and 50 malignant cases), which was not used in network training. Evaluation indicators include accuracy, sensitivity, specificity, and area under curve (AUC) value. The results in the Fus2Net model had an accuracy of 92%, the sensitivity reached 95.65%, the specificity reached 88.89%, and the AUC value reached 0.97 for classifying BUS tumor images. Conclusions The experiment compared the existing CNN-categorized architecture, and the Fus2Net architecture we customed has more advantages in a comprehensive performance. The obtained results demonstrated that the Fus2Net classification method we proposed can better assist radiologists in the diagnosis of benign and malignant BUS tumor images. Methods The existing public datasets are small and the amount of data suffer from the balance issue. In this paper, we provide a relatively larger dataset with a total of 1052 ultrasound images, including 696 benign images and 356 malignant images, which were collected from a local hospital. We proposed a novel CNN named Fus2Net for the benign and malignant classification of BUS tumor images and it contains two self-designed feature extraction modules. To evaluate how the classifier generalizes on the experimental dataset, we employed the training set (646 benign cases and 306 malignant cases) for tenfold cross-validation. Meanwhile, to solve the balance of the dataset, the training data were augmented before being fed into the Fus2Net. In the experiment, we used hyperparameter fine-tuning and regularization technology to make the Fus2Net convergence.

With the increasing capacity of wind turbines, key components including the rotor diameter, tower height, and tower radius expand correspondingly. This heightened inertia extends the response time of pitch actuators during rapid wind speed variations occurring above the rated wind speed. Consequently, wind turbines encounter significant output power oscillations and complex structural loading challenges. To address these issues, this paper proposes a novel pitch control strategy combining an effective wind speed estimation with the inverse system method. The developed control system aims to stabilize the power output and rotational speed despite wind speed fluctuations. Central to this approach is the estimation of the aerodynamic rotor torque using an extended Kalman filter (EKF) applied to the drive train model. The estimated torque is then utilized to compute the effective wind speed at the rotor plane via a differential method. Leveraging this wind speed estimate, the inverse system technique transforms the nonlinear wind turbine dynamics into a linearized, decoupled pseudo-linear system. This linearization facilitates the design of a more agile pitch controller. Simulation outcomes demonstrate that the proposed strategy markedly enhances the pitch response speed, diminishes output power oscillations, and alleviates structural loads, notably at the tower base. These improvements bolster operational safety and stability under the above-rated wind speed conditions.

[This corrects the article DOI: 10.3389/fmed.2024.1402967.].

As an important imaging tool for diagnosing and treating cerebrovascular diseases, the low-dose imaging technology of digital subtraction angiography (DSA) can effectively reduce radiation exposure risks for both patients and operators. To ensure clinical demand while minimizing radiation dose, this study proposed SAVE-Net, which integrates deep learning with optical flow estimation. The model is designed to synthesize intermediate frames in DSA sequences, thereby reducing the number of scans required in clinical practice and directly decreasing the radiation dose. SAVE-Net was developed to generate subsequent frames following any given real DSA frame. A total of 17,335 DSA sequences from one hospital were used for model training, fine-tuning, and internal validation. For external validation, an additional 3,255 DSA sequences from two other hospitals were utilized. Image similarity between generated and real frames was quantitatively evaluated using the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR). Furthermore, five interventional radiologists independently performed a visual Turing test and quality assessment on the generated sequences. Inter-rater agreement for the Turing test results was assessed using Fleiss' Kappa, while the Wilcoxon Signed-Rank test was employed to analyze significant differences in the quality ratings. Internal validation results demonstrated that SAVE-Net achieved DSA sequences highly consistent with real clinical data using only 1/7 of the standard radiation dose and maintained stable performance across multiple scenarios. External validation results illustrated that SAVE-Net achieved an effective performance [SSIM: 0.951, 95% CI: (0.948, 0.956); PSNR: 40.764, 95% CI: (40.673, 40.798); and generation time: 0.04 s/frame]. Assessment results showed no significant difference between the generated sequences and the real ones. Additionally, the generated results exhibited high consistency with real data in terms of overall image quality (4.919 vs. 4.940) and diagnostic confidence (4.838 vs. 4.910). SAVE-Net enables the generation of clinically diagnostic DSA sequences using only 1/7 of the standard radiation dose, with image quality and diagnostic confidence comparable to real clinical data. Its superior performance across multi-center validation demonstrates a practical and effective approach to reducing radiation exposure in cerebrovascular imaging.

(1) Background and Purpose: Ebola virus (EBOV) is the causative agent of Ebola virus disease (EVD), which causes extremely high mortality and widespread epidemics. The only glycoprotein (GP) on the surface of EBOV particles is the key to mediating viral invasion into host cells. DNA vaccines for EBOV are in development, but their effectiveness is unclear. The lack of immune characteristics resides in antigenic MHC class II reactivity. (2) Methods: We selected MHC-II molecules from four human leukocyte antigen II (HLA-II) superfamilies with 98% population coverage and eight mouse H2-I alleles. IEDB, NetMHCIIpan, SYFPEITHI, and Rankpep were used to screen MHC-II-restricted epitopes with high affinity for EBOV GP. Further immunogenicity and conservation analyses were performed using VaxiJen and BLASTp, respectively. EpiDock was used to simulate molecular docking. Cluster analysis and binding affinity analysis of EBOV GP epitopes and selected MHC-II molecules were performed using data from NetMHCIIpan. The selective GP epitopes were verified by the enzyme-linked immunospot (ELISpot) assay using splenocytes of BALB/c (H2d), C3H, and C57 mice after DNA vaccine pVAX-GPEBO immunization. Subsequently, BALB/c mice were immunized with Protein-GPEBO, plasmid pVAX-GPEBO, and pVAX-LAMP/GPEBO, which encoded EBOV GP. The dominant epitopes of BALB/c (H-2-I-AdEd genotype) mice were verified by the enzyme-linked immunospot (ELISpot) assay. It is also used to evaluate and explore the advantages of pVAX-LAMP/GPEBO and the reasons behind them. (3) Results: Thirty-one HLA-II-restricted and 68 H2-I-restricted selective epitopes were confirmed to have high affinity, immunogenicity, and conservation. Nineteen selective epitopes have cross-species reactivity with good performance in MHC-II molecular docking. The ELISpot results showed that pVAX-GPEBO could induce a cellular immune response to the synthesized selective peptides. The better immunoprotection of the DNA vaccines pVAX-LAMP/GPEBO coincides with the enhancement of the MHC class II response. (4) Conclusions: Promising MHC-II-restricted candidate epitopes of EBOV GP were identified in humans and mice, which is of great significance for the development and evaluation of Ebola vaccines.