Attention Network Research Articles

Assessing the causal role of the structural connectome in temporomandibular disorders: A Mendelian randomization study

ABSTRACT Objective We examined the relationships between the structural connectome and temporomandibular disorders (TMDs). Methods Bidirectional Mendelian randomization analyses were conducted using Genome-wide association studies data on the structural connectome and TMDs. Results Positive associations with TMD risk were found for white matter structural connectivity from the left hemisphere limbic network to putamen, left hemisphere salience_ventral attention network to caudate, right hemisphere visual network to thalamus, and right hemisphere salience_ventral attention network to right hemisphere control network, while negative associations were observed for connectivity from the left hemisphere control and somatomotor networks to pallidum, left hemisphere somatomotor network to right hemisphere dorsal attention network, and right hemisphere somatomotor network to hippocampus (p< 0.05). In TMD patients, connectivity from the Left-hemisphere visual network to putamen was reduced, whereas connectivity from the Left-hemisphere limbic network to left-hemisphere control network was increased (p< 0.05). Conclusion Our findings provide insights into the TMD pathogenesis.

Vessel Trajectory Prediction Based on AIS Data: Dual-Path Spatial–Temporal Attention Network with Multi-Attribute Information

With the rapid growth of the global shipping industry, the increasing number of vessels has brought significant challenges to navigation safety and management. Vessel trajectory prediction technology plays a crucial role in route optimization and collision avoidance. However, current prediction methods face limitations when dealing with complex vessel interactions and multi-dimensional attribute information. Most models rely solely on global modeling in the temporal dimension, considering spatial interactions only later, failing to capture dynamic changes in trajectory interactions at different time points. Additionally, these methods do not fully utilize the multi-attribute information in AIS data, and the simple concatenation of attributes limits the model’s potential. To address these issues, this paper proposes a dual spacial–temporal attention network with multi-attribute information (DualSTMA). This network models vessel behavior and interactions through two distinct paths, comprehensively considering individual vessel intentions and dynamic interactions. Moreover, we divide vessel attributes into dynamic and static categories, with dynamic attributes fused during feature preprocessing, and with static attributes being controlled through a gating mechanism during spatial interactions to regulate the importance of neighboring vessel features. Benchmark tests on real AIS data show that DualSTMA significantly outperforms existing methods in prediction accuracy. Ablation studies and visual analyses further validate the model’s reliability and advantages.

Convergent Validity of Experimental Cognitive Tests in a Large Community Sample.

Experimental cognitive tests are designed to measure particular cognitive domains, although evidence supporting test validity is often limited. The Consortium for Neuropsychiatric Phenomics test battery administered 23 experimental and traditional neuropsychological tests to a large sample of community volunteers (n = 1,059) and patients with psychiatric diagnoses (n = 137), providing a unique opportunity to examine convergent validity with factor analysis. Traditional tests included subtests from the Wechsler and Delis-Kaplan batteries, while experimental tests included the Attention Networks Test, Balloon Analogue Risk Task, Delay Discounting Task, Remember-Know, Reversal Learning Task, Scene Recognition, Spatial and Verbal Capacity and Manipulation Tasks, Stop-Signal Task, and Task Switching. Several experimental cognitive measures were insufficiently related to other tests and were excluded from factor analyses. In the remaining 18 tests, exploratory factor analysis and subsequent multigroup confirmatory factor analysis supported a three-factor structure broadly corresponding to domains of verbal/working memory, inhibitory control, and memory. In sum, several experimental measures of inhibitory control had weak relationships with all other tests, while the convergent validity of most tests of working memory and memory was supported.

A light-weight enhanced multi-level attention network for plant disease identification

A light-weight enhanced multi-level attention network for plant disease identification

Brain functional alternation in patients with systemic sclerosis: a resting-state functional magnetic resonance imaging study

BackgroundNeuropsychiatric manifestations, such as cognitive impairment, are relatively prevalent in systemic sclerosis (SSc) patients. This study aimed to investigate the resting state (RS) functional alternations of SSc patients and the potential influenced factors.MethodsForty-four SSc patients (mean age, 46.3 ± 11.4 years; 40 females) and 19 age and sex comparable healthy volunteers (mean age, 42.6 ± 11.3 years; 16 females) were recruited and underwent RS functional MR imaging (fMRI) and neuropsychological assessments. Functional segregation analysis was performed to calculate the amplitude of low frequency fluctuation (ALFF) and regional homogeneity (ReHo). Functional integration analysis was conducted using group independent component analysis to calculate intra-network and inter-network functional connectivity (FC). The fMRI measurements were compared between SSc patients and healthy volunteers using voxel-based pairwise two-sample t-tests. The correlations between clinical characteristics and fMRI measurements were also analyzed.ResultsCompared to healthy volunteers, SSc patients exhibited significantly decreased ALFF and increased ReHo (all P < 0.01, FWE corrected). SSc patients predominantly showed decreased intra-network and inter-network FC in the auditory network, visual network, default mode network, frontoparietal network and attention network (intra-network FC: P < 0.01, uncorrected, cluster size > 30; inter-network FC: P < 0.05, FDR correction). Furthermore, clinical characteristics including disease duration (r value ranged from − 0.31 to 0.36), elevated erythrocyte sedimentation rate (r = 0.35), Montreal Cognitive Assessment score (r = 0.43), and Hamilton Depression Scale score (r = -0.40) were significantly associated with fMRI measurements (all P < 0.05).ConclusionsSpontaneous activity and functional connectivity alternations can be seen in SSc patients, which are partially associated with neuropsychiatric manifestations and tend to aggravate with disease duration.

Processing demands modulate the activities and functional connectivity patterns of the posterior (VWFA-1) and anterior (VWFA-2) VWFA

Previous studies have shown that the visual word form area (VWFA) has structural and intrinsic functional connectivity with both language and attention networks. Nevertheless, it is still unclear how the functional connectivity pattern of the VWFA is regulated by processing demands induced by experimental tasks, and whether processing demands differentially regulate the posterior (VWFA-1) and anterior (VWFA-2) subregions of the VWFA. To address these questions, the present study adopted two tasks varying in processing demands (i.e., verbal and non-verbal tasks), and used generalized psychophysiological interaction (gPPI) and dynamic causal modeling (DCM) analyses to explore the task-dependent functional connectivity patterns of the two subregions of the VWFA. Activation analysis revealed that the VWFA-2 showed higher activation for the verbal task than the non-verbal task, while there were no activation differences in the VWFA-1 after controlling for the stimulus driven effects. Functional and effective connectivity analyses revealed that, for both VWFA-1 and VWFA-2, the verbal task enhanced connections from VWFAs to the ventral language regions (e.g., the left orbital frontal cortex), while the non-verbal task enhanced connections from VWFAs to the dorsal visuospatial regions (e.g., the left intraparietal sulcus). Results of the present study indicate that processing demands induced by tasks modulate both the local activity and functional connectivity patterns of the VWFA, providing new insights for understanding its domain-general function.

Changes in the functional connections of the brain in patients with hypersomnia in acute ischemic stroke

BACKGROUND: The Disorders of cerebral circulation and sleep are inextricably related, since sleep disorders, including hypersomnia, are closely intertwined with cardiovascular diseases and increase the risk of stroke. Research works on visualization of functional brain changes in patients with sleep disorders and acute ischemic stroke are very few and need more study. AIM: to determine the functional connections of the brain in hypersomnia in patients with acute ischemic stroke by performing functional magnetic resonance imaging at rest. A study of 40 patients with acute ischemic stroke and sleep disorders was performed on the basis of the Federal State Budgetary Institution Almazov Research Center of the Ministry of Health of the Russian Federation. All patients underwent neurological examination, assessment of sleepiness, worry and depression, magnetic resonance imaging was performed on tomographs with a magnetic field induction force of 1.5T, using a standard protocol and special pulse sequences of T-gradient echo 3D MPRAGE and BOLD. Functional magnetic resonance imaging of the brain at rest was used to assess functional connections. Postprocessing was performed using specialized CONN-TOOLBOX software with an appropriate graphical representation of quantitative results based on the selection of areas of interest. RESULTS: Among the examined patients, 23 had hypersomnolence; of these, 8 patients were diagnosed with secondary hypersomnia associated with sleep apnea syndrome. Thus, in the examined sample, post-stroke hypersomnolence was detected in 15 patients (34%). Patients with an unspecified subtype of stroke and right-sided lesions showed a high degree of drowsiness (p 0.05). With the help of functional magnetic resonance imaging of the brain at rest, changes in functional connections between the main nodes of the default mode network with the left temporal pole, cerebellum, central cerebral cortex on the left, angular gyrus on the left, with the dorsal attention network on the right are determined (p 0.05). CONCLUSION: The use of complex magnetic resonance imaging, which includes structural and functional magnetic resonance imaging in patients with acute ischemic stroke and sleep disorders, allows us to identify structural changes and changes in functional connectivity and identify neuroimaging markers of this pathology. Hypersomnolence is typical for patients with an unspecified subtype of ischemic stroke and damage to the right hemisphere of the brain.

Brain connectomes in youth at risk for serious mental illness: a longitudinal perspective.

Identifying biomarkers for serious mental illnesses (SMI) has significant implications for prevention and early intervention. In the current study, changes in whole brain structural and functional connectomes were investigated in youth at transdiagnostic risk over a one-year period. Based on clinical assessments, participants were assigned to one of 5 groups: healthy controls (HC; n = 33), familial risk for serious mental illness (stage 0; n = 31), mild symptoms (stage 1a; n = 37), attenuated syndromes (stage 1b; n = 61), or discrete disorder (transition; n = 9). Constrained spherical deconvolution was used to generate whole brain tractography maps, which were then used to calculate connectivity matrices for graph theory analysis. Graph theory was also used to analyze correlations of functional magnetic resonance imaging (fMRI) signal between pairs of brain regions. Linear mixed models revealed structural and functional abnormalities in global metrics of small world lambda, and resting state networks involving the fronto-parietal, default mode, and deep grey matter networks, along with the visual and dorsal attention networks. Machine learning analysis additionally identified changes in nodal metrics of betweenness centrality in the angular gyrus and bilateral temporal gyri as potential features which can discriminate between the groups. Our findings further support the view that abnormalities in large scale networks (particularly those involving fronto-parietal, temporal, default mode,and deep grey matter networks) may underlie transdiagnostic risk for SMIs.

Multiscale attention-over-attention network for retinal disease recognition in OCT radiology images

Retinal disease recognition using Optical Coherence Tomography (OCT) images plays a pivotal role in the early diagnosis and treatment of conditions. However, the previous attempts relied on extracting single-scale features often refined by stacked layered attentions. This paper presents a novel deep learning-based Multiscale Feature Enhancement via a Dual Attention Network specifically designed for retinal disease recognition in OCT images. Our approach leverages the EfficientNetB7 backbone to extract multiscale features from OCT images, ensuring a comprehensive representation of global and local retinal structures. To further refine feature extraction, we propose a Pyramidal Attention mechanism that integrates Multi-Head Self-Attention (MHSA) with Dense Atrous Spatial Pyramid Pooling (DASPP), effectively capturing long-range dependencies and contextual information at multiple scales. Additionally, Efficient Channel Attention (ECA) and Spatial Refinement modules are introduced to enhance channel-wise and spatial feature representations, enabling precise localization of retinal abnormalities. A comprehensive ablation study confirms the progressive impact of integrated blocks and attention mechanisms that enhance overall performance. Our findings underscore the potential of advanced attention mechanisms and multiscale processing, highlighting the effectiveness of the network. Extensive experiments on two benchmark datasets demonstrate the superiority of the proposed network over existing state-of-the-art methods.

Neural bases of social facilitation and inhibition: how peer presence affects elementary eye movements.

Social Facilitation/Inhibition (SFI) refers to how others' presence influences task performance positively or negatively. Our previous study revealed that peer presence modulated saccadic eye movements, a fundamental sensorimotor activity. Pro- and anti-saccades were either facilitated or inhibited depending on trial block complexity (Tricoche et al., 2020). In the present fMRI study, we adapted our paradigm to investigate the neural basis of SFI on saccades. Considering inter- and intra-individual variabilities, we evaluated the shared and distinct neural patterns between social facilitation and inhibition. We predicted an involvement of the saccade-related and attention networks, alongside the Theory-of-Mind (ToM) network, with opposite activity changes between facilitation and inhibition. Results confirmed peer presence modulation in fronto-parietal areas related to saccades and attention, in opposite directions for facilitation and inhibition. Additionally, the ventral attention network was modulated during inhibition. Default mode regions, including ToM areas, were also modulated. Finally, pupil size, often linked to arousal, increased with peers and correlated with dorsal attention regions and anterior insula activities. These results suggest that SFI engages task-specific and domain-general networks, modulated differently based on observed social effect. Attention network seemed to play a central role at both basic (linked to arousal or vigilance) and cognitive control levels.

Enhancing Image Dehazing Efficiency with Dual Colour Space Attentional Deep Networks

Aims and Background: Image dehazing is an essential task in computer-vision, aimed at enhancing the clarity and visibility of images degraded by fog and haze. Traditional methods often struggle with handling the complex scattering effects of haze and maintaining the natural colours of the scene. Objectives and Methodology: To address these challenges, we propose a novel approach termed Dual Colour Space Attentional Deep Network (DCSADN) for efficient image dehazing. Our method leverages the advantages of two-colour spaces: RGB and YCbCr, to boost the network's skill to capture both the luminance and chrominance information, thereby improving the dehazing performance. We employ a multi-stage training strategy to optimize the performance of the DCSADN. This multi-stage approach ensures that the network generalizes well across different types of haze conditions. Extensive experiments demonstrate the superiority of our method over state-of-the-art dehazing techniques. Results: The results indicate that our approach not only achieves higher quantitative scores in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) but also produces dehazed images with more natural colours and details. Conclusion: The findings reveal that the dual colour space processing and attentional modules are crucial for the enhanced performance of our method and providing a valuable tool for improving image quality in hazy conditions.

Attention Network Dysfunctions in Lewy Body Dementia and Alzheimer’s Disease

Background: Attention deficits are notable in Lewy body dementia (LBD) and in Alzheimer’s disease (AD). In this study, we combined functional magnetic resonance imaging (fMRI) and electroencephalograph (EEG) to detect neural correlates of attention dysfunctions in LBD and AD. Methods: We recruited 33 patients with LBD, 15 patients with AD and 19 elderly healthy controls. The participants performed the modified Attention Network Task (ANT) to investigate the attention dysfunctions. Results: We found that LBD had alerting attention deficits and AD showed apparent orienting attention dysfunctions, while LBD and AD maintained relatively normal executive/conflict attention. Based on source-level EEG analyses, LBD had frontal-central deficits for alerting attention while AD showed inferior frontal and precentral impairments for orienting attention. In addition, the insular and inferior frontal areas were hyper-activated in LBD and AD for executive/conflict attention. Apart from these areas, LBD showed activity in the complementary temporal-central-occipital network for the modified ANT task. Furthermore, the oscillational sources for the ANT effects indicated that the alpha and theta bands were partly impaired in dementia patients. Conclusions: In summary, using source-localised EEG, we found that attention dysfunctions in LBD and AD engaged different neural networks.

MFHARFNet: multi-branch feature hybrid and adaptive receptive field network for image segmentation

Abstract Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model’s adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.

Distinct Neural Mechanisms Underlying Dual-Task Priority During Gait Across Cognitive and Motor Networks.

Background: Prioritization strategy during gait significantly influences gait performance and successful gait relies on interactions between cognitive and motor functions. This study aimed to examine the within- and between-network connectivities of cognitive and motor networks associated with dual-task priority during gait. Methods: Twenty-nine healthy individuals (66.86 ± 8.53 years) underwent the timed-up-and-go (TUG) test alone, TUG with a cognitive task, and the cognitive task alone. The cognitive task involved sequentially subtracting three from a random number between 50 and 100. The resting-state functional magnetic resonance imaging was acquired on the same day. Using independent component analysis, the dorsal attention network (DAN), frontoparietal network (FPN), primary motor network (PM), and lateral motor network were assessed. The participants were divided into cognitive and motor priority groups based on the modified attention allocation index (mAAI). Group comparisons of within- and between-network connectivity were conducted using permutation tests. Additionally, correlation analysis was employed to investigate the association between-network connectivity and task priority. Results: The cognitive priority group showed cognitive dual-task facilitation. In comparison to the motor priority group, they also showed comparable motor dual-task costs and lower combined dual-task costs. They exhibited increased within-network connectivity in the left FPN and enhanced between-network connectivity between the right FPN and both the DAN and PM. These between-network connectivities were negatively correlated with mAAI scores. Conclusion: The results suggest distinct neural mechanisms across cognitive and motor networks based on individuals' dual-task strategies. This may have implications for understanding gait performance in complex contexts.

CSTAN: A Deepfake Detection Network with CST Attention for Superior Generalization

With the advancement of deepfake forgery technology, highly realistic fake faces have posed serious security risks to sensor-based facial recognition systems. Recent deepfake detection models mainly use binary classification models based on deep learning. Despite achieving high detection accuracy on intra-datasets, these models lack generalization ability when applied to cross-datasets. We propose a deepfake detection model named Channel-Spatial-Triplet Attention Network (CSTAN), which focuses on the difference between real and fake features, thereby enhancing the generality of the detection model. To enhance the feature-learning ability of the model for image forgery regions, we have designed the Channel-Spatial-Triplet (CST) attention mechanism, which extracts subtle local information by capturing feature channels and the spatial correlation of three different scales. Additionally, we propose a novel feature extraction method, OD-ResNet-34, by embedding ODConv into the feature extraction network to enhance its dynamic adaptability to data features. Trained on the FF++ dataset and tested on the Celeb-DF-v1 and Celeb-DF-v2 datasets, the experimental results show that our model has stronger generalization ability in cross-datasets than similar models.

Changes in resting-state functional connectivity of large-scale brain networks in bulimia nervosa: evidence from causal analysis.

Bulimia nervosa (BN) has been observationally linked to the functional connectivity (FC) of large-scale brain networks, but the biological mechanisms remain unclear. This study used two-sample Mendelian randomization (MR) with genetic variations as instrumental variables (IVs) to explore potential causal relationships between FC and BN. Summary data from genome-wide association studies (GWAS) involving 2,564 individuals were analyzed to identify genetically predicted BN. Functional magnetic resonance imaging parameters and materials were sourced from the UK Biobank. The variables underwent independent component analysis processing by the database to generate the final GWAS dataset. Various methods, including MR Pleiotropy RESidual Sum and Outlier, MR Egger, and weighted median, were employed to detect heterogeneity and pleiotropy, with inverse variance weighting serving as the principal estimation method (P < 0.05). The FC imaging-derived phenotypes revealed that BN exerted a causal influence on the FC between large-scale networks, including the visual network, default mode network (DMN), frontoparietal network, somatosensory network (SSN), and ventral attention network. Additionally, BN had a causal impact on the within-network FC of both the DMN and SSN. The study provides evidence that BN leads to further changes in FC patterns within and between large-scale brain networks.

Text Command Intelligent Understanding for Cybersecurity Testing

Research on named entity recognition (NER) and command-line generation for network security evaluation tools is relatively scarce, and no mature models for recognition or generation have been developed thus far. Therefore, in this study, the aim is to build a specialized corpus for network security evaluation tools by combining knowledge graphs and information entropy for automatic entity annotation. Additionally, a novel NER approach based on the KG-BERT-BiLSTM-CRF model is proposed. Compared to the traditional BERT-BiLSTM model, the KG-BERT-BiLSTM-CRF model demonstrates superior performance when applied to the specialized corpus of network security evaluation tools. The graph attention network (GAT) component effectively extracts relevant sequential content from datasets in the network security evaluation domain. The fusion layer then concatenates the feature sequences from the GAT and BiLSTM layers, enhancing the training process. Upon successful NER execution, in this study, the identified entities are mapped to pre-established command-line data for network security evaluation tools, achieving automatic conversion from textual content to evaluation commands. This process not only improves the efficiency and accuracy of command generation but also provides practical value for the development and optimization of network security evaluation tools. This approach enables the more precise automatic generation of evaluation commands tailored to specific security threats, thereby enhancing the timeliness and effectiveness of cybersecurity defenses.

Polarity-aware deep attention network for aspect-based sentiment analysis

Polarity-aware deep attention network for aspect-based sentiment analysis

A multi-task learning based line parameter identification method for medium-voltage distribution network

Accurate line parameters are critical for and dispatch in distribution systems. External operating condition variations affect line parameters, reducing the accuracy of state estimation and power flow calculations. While many methods have been proposed and obtained results rather acceptable, there is room for improvement as they don’t fully consider line connections in known topologies. Furthermore, inaccuracies in measurement devices and data acquisition systems can introduce noise and outliers, impacting the reliability of parameter identification. To address these challenges, we propose a line parameter identification method based on Graph Attention Networks and Multi-gate Mixture-of-Experts. The topological structure of the power grid and the capabilities of modern data acquisition equipment are utilized to capture. We also introduce a multi-task learning framework to enable joint training of parameter identification across different branches, thereby enhancing computational efficiency and accuracy. Experiments show that the GAT-MMoE model outperforms traditional methods, with notable improvements in both accuracy and robustness.

Retinotopic coding organizes the interaction between internally and externally oriented brain networks.

The human brain seamlessly integrates internally generated thoughts with incoming sensory information, yet the networks supporting internal (default network, DN) and external (dorsal attention network, dATN) processing are traditionally viewed as antagonistic. This raises a crucial question: how does the brain integrate information between these seemingly opposed systems? Here, using precision neuroimaging methods, we show that these internal/external networks are not as dissociated as traditionally thought. Using densely-sampled 7T fMRI data, we defined individualized whole-brain networks from participants at rest and calculated the retinotopic preferences of individual voxels within these networks during an visual mapping task. We show that while the overall network activity between the DN and dATN is independent at rest, considering a latent retinotopic code reveals a complex, voxel-scale interaction stratified by visual responsiveness. Specifically, the interaction between the DN and dATN at rest is structured at the voxel-level by each voxel's retinotopic preferences, such that the spontaneous activity of voxels preferring similar visual field locations is more anti-correlated than that of voxels preferring different visual field locations. Further, this retinotopic scaffold integrates with the domain-specific preferences of subregions within these networks, enabling efficient, parallel processing of retinotopic and domain-specific information. Thus, DN and dATN are not independent at rest: voxel-scale interaction between these networks preserves and encodes information in both positive and negative BOLD responses, even in the absence of visual input or task demands. These findings suggest that retinotopic coding may serve as a fundamental organizing principle for brain-wide communication, providing a new framework for understanding how the brain balances and integrates internal cognition with external perception.