BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

Li, Xiaoxiao; Zhou, Yuan; Dvornek, Nicha C.; Zhang, Muhan; Gao, Siyuan; Zhuang, Jian; Scheinost, Dustin; Staib, Lawrence H.; Ventola, Pamela; Duncan, James S.

doi:10.1016/j.media.2021.102233

Cited by 311 publications

(162 citation statements)

References 58 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Next, they interpret the importance of each sub-graph identified by performing an extensive comparison between their GNN and existing classifiers. On the other hand, (78,80) proposed a GAT-based architecture to predict the most discriminative ROIs for identifying a disease. They specifically proposed a pooling layer along with a regularization loss term to soften the distribution of the node pooling scores generated by the network.…”

Section: Biomarker Identificationmentioning

confidence: 99%

Graph Neural Networks in Network Neuroscience

Bessadok¹,

Mahjoub²,

Rekik³

2021

Preprint

View full text Add to dashboard Cite

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road map of neuronal activities in the human brain -namely brain graph. Relying on its non-Euclidean data type, graph neural network (GNN) provides a clever way of learning the deep graph structure and it is rapidly becoming the state-of-the-art leading to enhanced performance in various network neuroscience tasks. Here we review current GNN-based methods, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification. We conclude by charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration.

show abstract

Section: Biomarker Identificationmentioning

confidence: 99%

Graph Neural Networks in Network Neuroscience

Bessadok¹,

Mahjoub²,

Rekik³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In other words, the GCN is trained on the whole graph and tested on subgraphs, such that they could determine the importance of subgraphs and nodes. In both works from Li et al [23], [88], the authors also improved their individual graph level analysis by proposing a BrainGNN and a pooling regularized GNN model to investigate the brain region related to a neurological disorder from t-f MRI data for ASD or HC classification.…”

Section: A Functional Connectivity Analysismentioning

confidence: 99%

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Ahmedt-Aristizabal,

Armin,

Denman

et al. 2021

Preprint

View full text Add to dashboard Cite

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.

show abstract

“…GNNs are designed to generate embeddings for a node by aggregating features of its neighboring nodes, for either a node classification, graph classification, or link prediction task ( Zhou et al, 2020 ). In recent years, neuroimaging studies have employed task-specific variants of graph convolution networks (GCNs), which is a popular GNN model that generalizes the convolution neural network (CNN) architecture on graph-structured data ( Parisot et al, 2018 ; Zhang et al, 2018 ; Jansson and Sandström, 2020 ; Jiang et al, 2020 ; Li X. et al, 2020 ; Goli, 2021 ; Liu et al, 2021 ; Qu et al, 2021 ; Wang et al, 2021 ; Yao et al, 2021 ). The graph attention network (GAT) is another powerful GNN model which generates node embeddings by employing a self-attention mechanism, where certain nodes in the neighborhood are given more attention over others, thereby focusing on the most relevant part of the graph ( Veličković et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Multimodal Brain Connectomics-Based Prediction of Parkinson’s Disease Using Graph Attention Networks

et al. 2022

View full text Add to dashboard Cite

BackgroundA multimodal connectomic analysis using diffusion and functional MRI can provide complementary information on the structure–function network dynamics involved in complex neurodegenerative network disorders such as Parkinson’s disease (PD). Deep learning-based graph neural network models generate higher-level embeddings that could capture intricate structural and functional regional interactions related to PD.ObjectiveThis study aimed at investigating the role of structure–function connections in predicting PD, by employing an end-to-end graph attention network (GAT) on multimodal brain connectomes along with an interpretability framework.MethodsThe proposed GAT model was implemented to generate node embeddings from the structural connectivity matrix and multimodal feature set containing morphological features and structural and functional network features of PD patients and healthy controls. Graph classification was performed by extracting topmost node embeddings, and the interpretability framework was implemented using saliency analysis and attention maps. Moreover, we also compared our model with unimodal models as well as other state-of-the-art models.ResultsOur proposed GAT model with a multimodal feature set demonstrated superior classification performance over a unimodal feature set. Our model demonstrated superior classification performance over other comparative models, with 10-fold CV accuracy and an F1 score of 86% and a moderate test accuracy of 73%. The interpretability framework highlighted the structural and functional topological influence of motor network and cortico-subcortical brain regions, among which structural features were correlated with onset of PD. The attention maps showed dependency between large-scale brain regions based on their structural and functional characteristics.ConclusionMultimodal brain connectomic markers and GAT architecture can facilitate robust prediction of PD pathology and provide an attention mechanism-based interpretability framework that can highlight the pathology-specific relation between brain regions.

show abstract

BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

Cited by 311 publications

References 58 publications

Graph Neural Networks in Network Neuroscience

Graph Neural Networks in Network Neuroscience

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Multimodal Brain Connectomics-Based Prediction of Parkinson’s Disease Using Graph Attention Networks

Contact Info

Product

Resources

About