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

Journal Article · · Frontiers in Neuroscience (Online)
; ; ; ; ; ; ; ; ; ; ; ;

Introduction Recent 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. Methods We 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). Results The 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. Discussion Our 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 .

Sponsoring Organization:
USDOE Office of Electricity (OE), Advanced Grid Research & Development. Power Systems Engineering Research
OSTI ID:
1963970
Journal Information:
Frontiers in Neuroscience (Online), Journal Name: Frontiers in Neuroscience (Online) Vol. 17; ISSN 1662-453X
Publisher:
Frontiers Media SACopyright Statement
Country of Publication:
Switzerland
Language:
English

References (55)

Single‐subject morphological brain networks: connectivity mapping, topological characterization and test–retest reliability journal March 2016
Diagnosing schizophrenia with network analysis and a machine learning method journal February 2020
Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain journal January 2002
Brain Networks in Schizophrenia journal February 2014
DPABI: Data Processing & Analysis for (Resting-State) Brain Imaging journal April 2016
TE-HI-GCN: An Ensemble of Transfer Hierarchical Graph Convolutional Networks for Disorder Diagnosis journal November 2021
3D-CNN based discrimination of schizophrenia using resting-state fMRI journal July 2019
Cortical Brain Abnormalities in 4474 Individuals With Schizophrenia and 5098 Control Subjects via the Enhancing Neuro Imaging Genetics Through Meta Analysis (ENIGMA) Consortium journal November 2018
Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI journal March 2007
Classification of schizophrenia patients using a graph convolutional network: A combined functional MRI and connectomics analysis journal February 2023
Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction journal December 2020
Size of burden of schizophrenia and psychotic disorders journal August 2005
Measuring individual morphological relationship of cortical regions journal November 2014
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis journal December 2021
Regional homogeneity approach to fMRI data analysis journal May 2004
Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls journal January 2017
Divergent Alterations of Structural–Functional Connectivity Couplings in First-episode and Chronic Schizophrenia Patients journal April 2021
Neuroimaging in Schizophrenia journal February 2020
Overview of Machine Learning: Part 2 journal November 2020
How do abnormalities in the brain’s spontaneous activity translate into symptoms in schizophrenia? From an overview of resting state activity findings to a proposed spatiotemporal psychopathology journal October 2016
Effects of randomness in the development of machine learning models in neuroimaging studies of schizophrenia journal February 2023
Puzzling over schizophrenia: Schizophrenia, social environment and the brain journal February 2012
Systematic misestimation of machine learning performance in neuroimaging studies of depression journal May 2021
A neuroimaging biomarker for striatal dysfunction in schizophrenia journal March 2020
Evolving functional network properties and synchronizability during human epileptic seizures
  • Schindler, Kaspar A.; Bialonski, Stephan; Horstmann, Marie-Therese
  • Chaos: An Interdisciplinary Journal of Nonlinear Science, Vol. 18, Issue 3 https://doi.org/10.1063/1.2966112
journal September 2008
EEG functional connectivity and deep learning for automatic diagnosis of brain disorders: Alzheimer’s disease and schizophrenia journal April 2022
The Human Brainnetome Atlas: A New Brain Atlas Based on Connectional Architecture journal May 2016
Beyond the disconnectivity hypothesis of schizophrenia journal August 2019
Graph Convolutional Networks Reveal Network-Level Functional Dysconnectivity in Schizophrenia journal May 2022
A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity journal April 2021
Classification of First-Episode Schizophrenia, Chronic Schizophrenia and Healthy Control Based on Brain Network of Mismatch Negativity by Graph Neural Network journal January 2021
Graph U-Nets journal January 2021
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends journal January 2018
Explainability Methods for Graph Convolutional Neural Networks conference June 2019
A Multi-Domain Connectome Convolutional Neural Network for Identifying Schizophrenia From EEG Connectivity Patterns journal May 2020
Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network conference October 2021
Explainability in Graph Neural Networks: A Taxonomic Survey journal January 2022
node2vec: Scalable Feature Learning for Networks conference January 2016
Medial prefrontal cortex in neurological diseases journal September 2019
Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach journal January 2022
Structural and functional brain abnormalities in drug-naive, first-episode, and chronic patients with schizophrenia: a multimodal MRI study journal October 2018
Multimodal Magnetic Resonance Imaging Reveals Aberrant Brain Age Trajectory During Youth in Schizophrenia Patients journal March 2022
GRETNA: a graph theoretical network analysis toolbox for imaging connectomics journal June 2015
Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients: A Multimodal MRI Study journal July 2021
Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study journal January 2022
Mild cognitive impairment and fMRI studies of brain functional connectivity: the state of the art journal August 2015
EEG Source Network for the Diagnosis of Schizophrenia and the Identification of Subtypes Based on Symptom Severity—A Machine Learning Approach journal December 2020
Abnormal Degree Centrality of Bilateral Putamen and Left Superior Frontal Gyrus in Schizophrenia with Auditory Hallucinations journal December 2015
Semi-Supervised Classification with Graph Convolutional Networks preprint January 2016
Representation Learning on Graphs with Jumping Knowledge Networks preprint January 2018
Towards Sparse Hierarchical Graph Classifiers preprint January 2018
Pitfalls of Graph Neural Network Evaluation preprint January 2018
Self-Attention Graph Pooling preprint January 2019
Explainability Techniques for Graph Convolutional Networks preprint January 2019
On random graphs. I. journal July 2022

Similar Records

Related Subjects