Unprecedented collections of large-scale brain imaging data, such as MRI, PET, fMRI, M/EEG, DTI, etc. provide a unique opportunity to deepen our understanding of the brain working mechanisms, improve prognostic predictions for mental disorders, and tailor personalized treatment plans for brain diseases. Recent advances in machine learning and large-scale brain imaging data collection, storage, and sharing lead to a series of novel interdisciplinary approaches among the fields of computational neuroscience, signal processing, deep learning, brain imaging, cognitive science, and computational psychiatry, among which graph learning provides a valuable means to address important questions in brain imaging.
Graph learning refers to designing effective machine learning and deep learning methods extracting important information from graphs or exploiting the graph structure in the data to guide the knowledge discovery. Given the complex data structure in different imaging modalities as well as networked organizational structure of the human brain, novel learning methods based on graphs inferred from imaging data, graph regularizations for the data, and graph embedding of the recorded data, have shown great promise in modeling the interactions of multiple brain regions, information fusion among networks derived from different brain imaging modalities, latent space modeling of the high dimensional brain networks, and quantifying topological neurobiomarkers. The goal of this Research Topic is to synergize the start-of-the-art discoveries in terms of new computational brain imaging models and insights of brain mechanisms through the lens of brain networks and graph learning.
We are looking for original, high-quality submissions on innovative research and developments in the analysis of brain imaging using graph learning techniques. Topics of interest include (but are not limited to):
• Graph neural networks (GNN) for network neuroscience applications
• Graph neural network for brain mapping and data integration
• Graph convolution network (GCN) for brain disorder classification
• (Dynamic) Functional brain networks
• Brain networks development trajectories
• Graphical model for brain imaging data analysis
• Spatial-temporal brain network modeling
• Graph embedding and graph representation learning
• Information fusion for brain networks from multiple modalities or scales (fMRI, M/EEG, DTI, PET, genetics)
• Generative graph models in brain imaging
• Brain network inference: scalable, online, and from non-linear relationships
• Machine learning over graphs: kernel-based techniques, clustering methods, scalable algorithms for brain imaging
• A few-shot learning for learning from limited brain data
• Graph federated learning for brain imaging
Unprecedented collections of large-scale brain imaging data, such as MRI, PET, fMRI, M/EEG, DTI, etc. provide a unique opportunity to deepen our understanding of the brain working mechanisms, improve prognostic predictions for mental disorders, and tailor personalized treatment plans for brain diseases. Recent advances in machine learning and large-scale brain imaging data collection, storage, and sharing lead to a series of novel interdisciplinary approaches among the fields of computational neuroscience, signal processing, deep learning, brain imaging, cognitive science, and computational psychiatry, among which graph learning provides a valuable means to address important questions in brain imaging.
Graph learning refers to designing effective machine learning and deep learning methods extracting important information from graphs or exploiting the graph structure in the data to guide the knowledge discovery. Given the complex data structure in different imaging modalities as well as networked organizational structure of the human brain, novel learning methods based on graphs inferred from imaging data, graph regularizations for the data, and graph embedding of the recorded data, have shown great promise in modeling the interactions of multiple brain regions, information fusion among networks derived from different brain imaging modalities, latent space modeling of the high dimensional brain networks, and quantifying topological neurobiomarkers. The goal of this Research Topic is to synergize the start-of-the-art discoveries in terms of new computational brain imaging models and insights of brain mechanisms through the lens of brain networks and graph learning.
We are looking for original, high-quality submissions on innovative research and developments in the analysis of brain imaging using graph learning techniques. Topics of interest include (but are not limited to):
• Graph neural networks (GNN) for network neuroscience applications
• Graph neural network for brain mapping and data integration
• Graph convolution network (GCN) for brain disorder classification
• (Dynamic) Functional brain networks
• Brain networks development trajectories
• Graphical model for brain imaging data analysis
• Spatial-temporal brain network modeling
• Graph embedding and graph representation learning
• Information fusion for brain networks from multiple modalities or scales (fMRI, M/EEG, DTI, PET, genetics)
• Generative graph models in brain imaging
• Brain network inference: scalable, online, and from non-linear relationships
• Machine learning over graphs: kernel-based techniques, clustering methods, scalable algorithms for brain imaging
• A few-shot learning for learning from limited brain data
• Graph federated learning for brain imaging
