A5090924338- Functional Brain Connectivity Studies
- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Genetic Associations and Epidemiology
- Dementia and Cognitive Impairment Research
- Brain Tumor Detection and Classification
- Alzheimer's disease research and treatments
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Machine Learning in Bioinformatics
- Neurological Disease Mechanisms and Treatments
- Medical Image Segmentation Techniques
- Video Surveillance and Tracking Methods
- Industrial Vision Systems and Defect Detection
- Domain Adaptation and Few-Shot Learning
- Image Processing Techniques and Applications
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Face recognition and analysis
- Automated Road and Building Extraction
- Gait Recognition and Analysis
- Pain Mechanisms and Treatments
- Digital Media Forensic Detection
Hebei University of Technology
2018-2025
Nanjing University of Aeronautics and Astronautics
2013-2019
Indiana University – Purdue University Indianapolis
2015-2016
Vaughn College of Aeronautics and Technology
2015
Recently, skeleton-based human action recognition has attracted a lot of research attention in the field computer vision. Graph convolutional networks (GCNs), which model body skeletons as spatial-temporal graphs, have shown excellent results. However, existing methods only focus on local physical connection between joints, and ignore non-physical dependencies among joints. To address this issue, we propose hypergraph neural network (Hyper-GNN) to capture both information high-order for...
Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order detect complex multi-SNP-multi-QT associations, bi-multivariate techniques various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed used studies. However, markers QTs identified by existing methods may not be all...
Neuroimaging genetics identifies the relationships between genetic variants (i.e., single nucleotide polymorphisms) and brain imaging data to reveal associations from genotypes phenotypes. So far, most existing machine-learning approaches are widely used detect effective at one time-point. However, those based on static phenotypes ignore temporal dynamics of phenotypical changes. The across multiple time-points may exhibit patterns that can be facilitate understanding degenerative process....
The fractional amplitude of low-frequency fluctuations (fALFF) has been widely used as potential clinical biomarkers for resting-state functional-magnetic-resonance-imaging-based schizophrenia diagnosis. How-ever, previous studies usually measure the fALFF with specific bands from 0.01 to 0.08 Hz, which cannot fully delineate complex variations spontaneous in brain. In addition, data are intrinsically constrained by brain structure, but most traditional methods have not consider it feature...
Recently, a large meta-analysis of five genome wide association studies (GWAS) identified novel locus (rs2718058) adjacent to NME8 that played preventive role in Alzheimer's disease (AD). However, this link between the single nucleotide polymorphism (SNP) rs2718058 and pathology AD have not been mentioned yet. Therefore, study assessed strength genotypes AD-related measures including cerebrospinal fluid (CSF) amyloid beta, tau, P-tau concentrations, neuroimaging biomarkers cognitive...
Abstract Motivation As a rising research topic, brain imaging genetics aims to investigate the potential genetic architecture of both structure and function. It should be noted that in brain, not all variations are deservedly caused by effect, it is generally unknown which phenotypes promising for analysis. Results In this work, variants (i.e. single nucleotide polymorphism, SNP) can correlated with networks quantitative trait, QT), so connectome (including regions connectivity features)...
Depression, a complex and heritable psychiatric disorder, is associated with alterations in white matter microstructure, yet their shared genetic basis remains largely unclear. Utilizing the largest available genome-wide association study (GWAS) datasets for depression (N = 674,452) microstructure 33,224), assessed through diffusion tensor imaging metrics such as fractional anisotropy (FA) mean diffusivity (MD), we employed linkage disequilibrium score regression method to estimate global...
The domain gap resulting from mismatches in acquisition details like protocol and scanner between training test data hinders the deployment of trained model clinical practice. To address this issue, Continual test-time adaptation (CTTA) has been proposed to adapt source continually changing unlabeled domains without accessing data. Existing methods learn an image-level visual prompt for target inject trainable into input space. However, they either combine with a equal scale or determine...
Alzheimer’s disease (AD) is an irreversible neurodegenerative that severely impairs human thinking and memory. The accurate diagnosis of AD its prodromal stages, such as mild cognitive impairment (MCI), very important for timely treatment or possible interventions AD. Recent studies have shown multiple neuroimaging biological measures contain supplementary information prognosis. Most existing methods are proposed to simply integrate the multimodal data train model using all samples once,...
Recently, functional magnetic resonance imaging (fMRI)-based brain networks have been shown to be an effective diagnostic tool with great potential for accurately detecting autism spectrum disorders (ASD). Meanwhile, the successful use of graph convolution (GCNs) methods based on fMRI information has improved classification accuracy ASD. However, many convolution-based do not fully utilize topological connectivity network (BFCN) or ignore effect non-imaging information. Therefore, we propose...
Ephrin type-A receptor 1 (EPHA1) (11771145) was documented to be one of the most strongly associated locus with Alzheimer's disease (AD) in a recent meta-analysis five genome wide association studies. However, its contribution pathogenesis
Abstract Motivation Neuroimaging genetics is an emerging field to identify the associations between genetic variants [e.g. single-nucleotide polymorphisms (SNPs)] and quantitative traits (QTs) such as brain imaging phenotypes. However, most of current studies focus only on structure variants, while neglecting connectivity information regions. In addition, itself a complex network, higher-order interaction may contain useful for mechanistic understanding diseases [i.e. Alzheimer’s disease...
ABCA7 gene has been identified as a strong genetic locus for Alzheimer's disease (AD) susceptibility in genome wide association studies (GWAS). However, the possible roles of variants AD pathology were not specifically assessed. Using tagger methods, we extracted 15 targeted loci to investigate their associations with cerebrospinal fluid (CSF) and neuroimaging markers Disease Neuroimaging Initiative (ADNI) dataset. Finally, although did detect any significant previously published GWAS SNPs...
The phospholipase D3 (PLD3) gene has shown association with Alzheimer's disease (AD). However, the role of PLD3 common variants in amyloid-β (Aβ) pathology remains unclear. We examined thirteen single nucleotide polymorphisms (SNPs) cerebrospinal fluid (CSF) Aβ 1 - 42 levels and florbetapir retention on 18F amyloid positron emission tomography (AV45-PET) a large population. found that one SNP (rs11667768) was significantly associated CSF normal cognition group. did not observe an any...
Recently, a lot of research has been conducted on diagnosing neurological disorders, such as autism spectrum disorder (ASD). Functional magnetic resonance imaging (fMRI) is the commonly used technique to assist in diagnosis ASD. In past years, some conventional methods have proposed extract low-order functional connectivity network features for ASD diagnosis, which ignore complexity and global brain network. Most deep learning-based generally large number parameters that need be adjusted...