FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation

  title={FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation},
  author={Xuan Kan and Hejie Cui and Joshua D Lukemire and Ying Guo and Carl Yang},
Functional magnetic resonance imaging (fMRI) is one of the most common imaging modalities to investigate brain functions. Recent studies in neuroscience stress the great potential of functional brain networks constructed from fMRI data for clinical predictions. Traditional functional brain networks, however, are noisy and unaware of downstream prediction tasks, while also incompatible with the deep graph neural network (GNN) models. In order to fully unleash the power of GNNs in network-based… 

Figures and Tables from this paper

BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
BrainGB is presented, a benchmark for brain network analysis with GNNs and standardizes the process by summarizing brain network construction pipelines for both functional and structural neuroimaging modalities and modularizing the implementation of GNN designs.
Controllable Data Generation by Deep Learning: A Review
This article provides a systematic review of this promising research area, commonly known as controllable deep data generation, and formally defined, a taxonomy on various techniques is proposed and the evaluation metrics in this specific domain are summarized.
Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
This work proposes an interpretable framework to analyze disorder-specific Regions of Interest (ROIs) and prominent connections and conducts experiments on three real-world datasets of brain disorders to verify that the framework can obtain outstanding performance and also identify meaningful biomarkers.
Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning
This paper proposes to meta-train the model on datasets of large sample sizes and transfer the knowledge to small datasets and explores two brain-network-oriented designs, including atlas transformation and adaptive task reweighing.
A Survey on Graph Structure Learning: Progress and Opportunities
A general pipeline of GSL is formulated and state-of-the-art methods classified by the way of modeling graph structures, followed by applications of GSL across domains are reviewed, point out some issues in current studies and discuss future directions.


Learning Discrete Structures for Graph Neural Networks
This work proposes to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph.
Linked Sex Differences in Cognition and Functional Connectivity in Youth.
It is demonstrated for the first time that sex differences in patterns of cognition are in part represented on a neural level through divergent patterns of brain connectivity through rsfc-MRI.
Semi-Supervised Classification with Graph Convolutional Networks
A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
Network modelling methods for FMRI
Graph Attention Networks
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior
The Effect of Gray Matter ICA and Coefficient of Variation Mapping of BOLD Data on the Detection of Functional Connectivity Changes in Alzheimer’s Disease and bvFTD
A coefficient of variation (CV) map is used to highlight artifacts in the data, followed by analysis of gray matter voxels in order to minimize brain volume effects between groups to yield results suiting previous findings both in AD and bvFTD.
An Efficient and Reliable Statistical Method for Estimating Functional Connectivity in Large Scale Brain Networks Using Partial Correlation
The proposed partial correlation method is applied to investigate resting state functional connectivity using rs-fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC) study and shows that partial correlation analysis removed considerable between-module marginal connections identified by full correlation analysis, suggesting these connections were likely caused by global effects or common connection to other nodes.
Noise Reduction in BOLD-Based fMRI Using Component Analysis
A comparison of PCA and ICA revealed significant differences in their treatment of both structured and random noise, while PCA was superior for isolation and removal of random noise.
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
  • Liushuai Shi, Le Wang, G. Hua
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
A Sparse Graph Convolution Network for pedestrian trajectory prediction that explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians and can capture adaptive interactions between pedestrians and their effective motion tendencies.
Discrete Graph Structure Learning for Forecasting Multiple Time Series
This work proposes learning the structure simultaneously with the GNN if the graph is unknown, and casts the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution.