Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network

Sebenius, Isaac; Campbell, Alexander; Morgan, Sarah E.; Bullmore, Edward T.; Lió, Píetro

doi:10.1109/mlsp52302.2021.9690626

Cited by 11 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structural and functional abnormalities of the occipital cortices were highly related to visual hallucinations, one of the main symptoms of SZ patients, which was consistent with previous studies (Wu et al, 2018;Keshavan et al, 2020). Additionally, as shown in Figure 5, the salient brain regions were highly symmetrical and spatially coherent, consistent with the previous finding that ROI relevance should be distributed across the brain cortex (Sebenius et al, 2021).…”

Section: Discussionsupporting

confidence: 90%

“…There were three improvements in this study, compared with our previous study ( Chen et al, 2023 ). First, previous studies have indicated that multimodal MRI was more useful than that single-modal MRI data in the discriminative analyses of SZ patients ( Wu et al, 2018 ; Sebenius et al, 2021 ; Zang et al, 2021 ; Wang et al, 2022 ). In this study, we computed nodal and edge features by the analysis of multimodal MRI data.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

Chen

Ke²,

Huang³

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionRecent studies in human brain connectomics with multimodal magnetic resonance imaging (MRI) data have widely reported abnormalities in brain structure, function and connectivity associated with schizophrenia (SZ). However, most previous discriminative studies of SZ patients were based on MRI features of brain regions, ignoring the complex relationships within brain networks.MethodsWe applied a graph convolutional network (GCN) to discriminating SZ patients using the features of brain region and connectivity derived from a combined multimodal MRI and connectomics analysis. Structural magnetic resonance imaging (sMRI) and resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 140 SZ patients and 205 normal controls. Eighteen types of brain graphs were constructed for each subject using 3 types of node features, 3 types of edge features, and 2 brain atlases. We investigated the performance of 18 brain graphs and used the TopK pooling layers to highlight salient brain regions (nodes in the graph).ResultsThe GCN model, which used functional connectivity as edge features and multimodal features (sMRI + fMRI) of brain regions as node features, obtained the highest average accuracy of 95.8%, and outperformed other existing classification studies in SZ patients. In the explainability analysis, we reported that the top 10 salient brain regions, predominantly distributed in the prefrontal and occipital cortices, were mainly involved in the systems of emotion and visual processing.DiscussionOur findings demonstrated that GCN with a combined multimodal MRI and connectomics analysis can effectively improve the classification of SZ at an individual level, indicating a promising direction for the diagnosis of SZ patients. The code is available at https://github.com/CXY-scut/GCN-SZ.git.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 99%

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

Chen

Ke²,

Huang³

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…In studies such as [43,63,119], TopK pooling was used to coarsen the graph. Li et al [61] used two layers of hierarchical pooling based on TopK pooling, with each reducing the number of nodes by half.…”

Section: Hierarchical Poolingmentioning

confidence: 99%

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Zhang,

Yang,

Zhang

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Neurological disorders (NDs), such as Alzheimer’s disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.

show abstract

“…Gupta et al [58] demonstrated that biomarkers can be generated via deep learning models by using saliency scores from DeepLIFT. Recent works based on GNNs have also proposed using pooling layers for model interpretability [59,60]. Overall, these works typically only generate general biomarkers applicable across the entire disease class, but there are often significant variations within a single class due to disease heterogeneity.…”

Section: Biomarker Discoverymentioning

confidence: 99%

Encoding and decoding multimodal brain images for disease biomarker discovery

Chan

View full text Add to dashboard Cite

I would like to thank my supervisor, Prof Jagath, for providing me with this opportunity to fulfill one of my key life goals -conducting and contributing to research in the intersection of AI and Neuroscience. Through his supervision and guidance over these years, I've benefitted immensely from this experience: writing research papers, conducting lessons, mentoring undergraduate students, developing software tools for neuroscience applications and translating our research from lab to market. Throughout this journey, I have been fortunate to work with and learn from many collaborators. Sukrit has guided me since my time as an undergraduate student working on my final year project. Picking up both AI and Neuroscience is a huge and daunting task, but his mentorship has greatly accelerated my learning and made it possible to deliver these papers that I summarise in this thesis. Thank you Chamara, Conghao, Charlene, Victor, Chun Hung, Yanteng for many hours, days and months of discussions, debugging sessions, collaborations, marking marathons.

show abstract

Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network

Cited by 11 publications

References 15 publications

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Encoding and decoding multimodal brain images for disease biomarker discovery

Contact Info

Product

Resources

About