Interpretable Multimodality Embedding of Cerebral Cortex Using Attention Graph Network for Identifying Bipolar Disorder

Yang, Huzheng; Li, Xiaoxiao; Wu, Yifan; Li, Siyi; Lu, Shan; Duncan, James S.; Gee, James C.; Gu, Shi

doi:10.1007/978-3-030-32248-9_89

Cited by 41 publications

(40 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though some kinds of graph neural network models have been developed to process brain network data ( Ktena et al, 2018 ; Parisot et al, 2018 ; Yang et al, 2019 ; Kim and Ye, 2020 ), our proposed graph neural network is novel in the following aspect. As opposed to these graph neural networks ( Ktena et al, 2018 ; Parisot et al, 2018 ; Yang et al, 2019 ; Kim and Ye, 2020 ) that either impose feature transformation parameters on node features or use graph attentions that utilize node features to construct network propagation coefficients, our graph neural network directly imposes parameters on the connectivity network matrix instead. Imposing parameters on the connectivity network matrix is especially beneficial when the dimension of node features is very low, as it is the case that the node feature, i.e., the brain activation statistic, has only one dimension in our study.…”

Section: Discussionmentioning

confidence: 99%

Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

Feng

2021

Front. Neurosci.

View full text Add to dashboard Cite

Brain connectivity plays an important role in determining the brain region’s function. Previous researchers proposed that the brain region’s function is characterized by that region’s input and output connectivity profiles. Following this proposal, numerous studies have investigated the relationship between connectivity and function. However, this proposal only utilizes direct connectivity profiles and thus is deficient in explaining individual differences in the brain region’s function. To overcome this problem, we proposed that a brain region’s function is characterized by that region’s multi-hops connectivity profile. To test this proposal, we used multi-hops functional connectivity to predict the individual face activation of the right fusiform face area (rFFA) via a multi-layer graph neural network and showed that the prediction performance is essentially improved. Results also indicated that the two-layer graph neural network is the best in characterizing rFFA’s face activation and revealed a hierarchical network for the face processing of rFFA.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

Feng

2021

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…The multi-layers graph neural network perfectly matches our proposal, since the multi-layers convolution computations characterize the propagation of functional information among the brain connectivity network. Though some kinds of graph neural network models have been developed to process brain network data Parisot et al 2018;Yang et al 2019), our proposed graph neural network is novel in the following aspect. As opposed to these graph neural networks (Ktena et al 2018;Parisot et al 2018;Yang et al 2019) that impose parameters on node features, our graph neural network directly imposes parameters on connectivity features instead.…”

Section: Discussionmentioning

confidence: 99%

Multi-hops functional connectivity improves individual prediction of fusiform face activation via a graph neural network

Wu¹,

Feng

2020

Preprint

View full text Add to dashboard Cite

Brain connectivity plays an important role in determining the brain region's function. Previous researchers proposed that the brain region's function is characterized by that region's input and output connectivity profiles. Following this proposal, numerous studies have investigated the relationship between connectivity and function. However, based on a preliminary analysis, this proposal is deficient in explaining individual differences in the brain region's function. To overcome this problem, we proposed that a brain region's function is characterized by that region's multi-hops connectivity profile. To test this proposal, we used multi-hops functional connectivity to predict the individual face response of the right fusiform face area (rFFA) via a multi-layers graph neural network and showed that the prediction performance is essentially improved. Results also indicated that the 2-layers graph neural network is the best in characterizing rFFA's face response and revealed a hierarchical network for the face processing of rFFA.

show abstract

“…46 A preliminary version of this work explored the regularization on the pooling layer of standards GNN for fMRI analysis is provisionally accepted but have not 48 published at the 22st International Conference on Medical Image Computing 49 and Computer Assisted Intervention. This paper extends this work by designing 50 novel graph convolutional layers, justifying the loss terms regarding the pooling 51 layer, and testing our methods on additional datasets. 52 Fig.…”

mentioning

confidence: 83%

“…Due to their 25 high performance and interpretability, GNNs have been a widely applied graph 26 analysis method. [26,25,49,28,50]. Most existing GNNs are built on graphs that 27 do not have correspondence between the nodes of different instances, such as 28 social networks and protein networks, limiting interpretability.…”

mentioning

confidence: 99%

BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

Zhou

Gao

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The brain is an exceptionally complex system and understanding it's functional 2 organization is the goal of modern neuroscience. Using fMRI, large strides in 3 understanding this organization have been made by modeling the brain as a 4 graph-a mathematical construct describing the connections or interactions (i.e. 5 edges) between different discrete objects (i.e. nodes). To create these graphs, 6 nodes are defined as brain regions of interest (ROIs) and edges are defined as the 7 functional connectivity between those ROIs, computed as the pairwise correla-8 tions of functional magnetic resonance imaging (fMRI) time series, as illustrated 9 in Fig. 1. Traditional graph-based analyses for fMRI have focused on using graph 10 theoretical metrics to summarize the functional connectivity for each node into 11 a single number [45,23]. However, these methods do not consider higher-order 12 interactions between ROIs, as these interactions cannot be preserved in a sin-13 gle number. Additionally, due to the high dimensionality of fMRI data, usually 14 ROIs are clustered into highly connected communities to reduce dimensionality. 15Then, features are extracted from these smaller communities for further analysis 16 [31,12]. For these two-stage methods, if the results from the first stage are not 17 reliable, significant errors can be induced in the second stage. 18The past few years have seen the growing prevalence of the use of graph 19 neural networks (GNN) for end-to-end graph learning applications. GNNs are 20 the state-of-the-art deep learning methods for most graph-structured data anal-21 ysis problems. They combine node features, edge features, and graph structure 22 by using a neural network to embed node information and pass information 23 through edges in the graph. As such, they can be viewed as a generalization of 24 the traditional convolutional neural networks (CNN) for images. Due to their 25 high performance and interpretability, GNNs have been a widely applied graph 26 analysis method. [26,25,49,28,50]. Most existing GNNs are built on graphs that 27 do not have correspondence between the nodes of different instances, such as 28 social networks and protein networks, limiting interpretability. These methods 29-including the current GNN methods for fMRI analysis -use the same ker-30 nel over different nodes, which implicitly assumes brain graphs are translation 31 invariant. However, nodes in the same brain graph have distinct locations and 32 unique identities. Thus, applying the same kernel over all nodes is problematic. 33In addition, few GNN studies have explored both individual-level and group-level 34 explanations, which are critical in neuroimaging research. 35In this work, we propose a graph neural network-based framework for map-36 ping regional and cross-regional functional activation patterns for classification 37 tasks, such as classifying neurodisorder patients versus healthy control subjects 38 and performing cognitive task decoding. Our framework jointly learns ROI clus-39 tering and the downstr...

show abstract

Interpretable Multimodality Embedding of Cerebral Cortex Using Attention Graph Network for Identifying Bipolar Disorder

Cited by 41 publications

References 17 publications

Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

Multi-hops functional connectivity improves individual prediction of fusiform face activation via a graph neural network

BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

Contact Info

Product

Resources

About