Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis
Abstract
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 10more »
- Authors:
- Publication Date:
- Sponsoring Org.:
- USDOE Office of Electricity (OE), Advanced Grid Research & Development. Power Systems Engineering Research
- OSTI Identifier:
- 1963970
- Grant/Contract Number:
- 2018B030335001; 2020B0101130020; 2020B0404010002; 2019A1515110427; 201903010032; 202103000032; 202206060005; 202206080005; 202206010077; 202206010034; 2020KSYS001
- Resource Type:
- Published Article
- Journal Name:
- Frontiers in Neuroscience (Online)
- Additional Journal Information:
- Journal Name: Frontiers in Neuroscience (Online) Journal Volume: 17; Journal ID: ISSN 1662-453X
- Publisher:
- Frontiers Media SA
- Country of Publication:
- Switzerland
- Language:
- English
Citation Formats
Chen, Xiaoyi, Ke, Pengfei, Huang, Yuanyuan, Zhou, Jing, Li, Hehua, Peng, Runlin, Huang, Jiayuan, Liang, Liqin, Ma, Guolin, Li, Xiaobo, Ning, Yuping, Wu, Fengchun, and Wu, Kai. Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis. Switzerland: N. p., 2023.
Web. doi:10.3389/fnins.2023.1140801.
Chen, Xiaoyi, Ke, Pengfei, Huang, Yuanyuan, Zhou, Jing, Li, Hehua, Peng, Runlin, Huang, Jiayuan, Liang, Liqin, Ma, Guolin, Li, Xiaobo, Ning, Yuping, Wu, Fengchun, & Wu, Kai. Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis. Switzerland. https://doi.org/10.3389/fnins.2023.1140801
Chen, Xiaoyi, Ke, Pengfei, Huang, Yuanyuan, Zhou, Jing, Li, Hehua, Peng, Runlin, Huang, Jiayuan, Liang, Liqin, Ma, Guolin, Li, Xiaobo, Ning, Yuping, Wu, Fengchun, and Wu, Kai. Thu .
"Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis". Switzerland. https://doi.org/10.3389/fnins.2023.1140801.
@article{osti_1963970,
title = {Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis},
author = {Chen, Xiaoyi and Ke, Pengfei and Huang, Yuanyuan and Zhou, Jing and Li, Hehua and Peng, Runlin and Huang, Jiayuan and Liang, Liqin and Ma, Guolin and Li, Xiaobo and Ning, Yuping and Wu, Fengchun and Wu, Kai},
abstractNote = {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 .},
doi = {10.3389/fnins.2023.1140801},
journal = {Frontiers in Neuroscience (Online)},
number = ,
volume = 17,
place = {Switzerland},
year = {Thu Mar 30 00:00:00 EDT 2023},
month = {Thu Mar 30 00:00:00 EDT 2023}
}
https://doi.org/10.3389/fnins.2023.1140801
Works referenced in this record:
Systematic misestimation of machine learning performance in neuroimaging studies of depression
journal, May 2021
- Flint, Claas; Cearns, Micah; Opel, Nils
- Neuropsychopharmacology, Vol. 46, Issue 8
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis
journal, December 2021
- Li, Xiaoxiao; Zhou, Yuan; Dvornek, Nicha
- Medical Image Analysis, Vol. 74
Medial prefrontal cortex in neurological diseases
journal, September 2019
- Xu, Pan; Chen, Ai; Li, Yipeng
- Physiological Genomics, Vol. 51, Issue 9
Effects of randomness in the development of machine learning models in neuroimaging studies of schizophrenia
journal, February 2023
- Sun, Huaiqiang; Lui, Su; Huang, Xiaoqi
- Schizophrenia Research, Vol. 252
A neuroimaging biomarker for striatal dysfunction in schizophrenia
journal, March 2020
- Li, Ang; Zalesky, Andrew; Yue, Weihua
- Nature Medicine, Vol. 26, Issue 4
Classification of First-Episode Schizophrenia, Chronic Schizophrenia and Healthy Control Based on Brain Network of Mismatch Negativity by Graph Neural Network
journal, January 2021
- Chang, Qi; Li, Cancheng; Tian, Qing
- IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 29
node2vec: Scalable Feature Learning for Networks
conference, January 2016
- Grover, Aditya; Leskovec, Jure
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
A Multi-Domain Connectome Convolutional Neural Network for Identifying Schizophrenia From EEG Connectivity Patterns
journal, May 2020
- Phang, Chun-Ren; Noman, Fuad; Hussain, Hadri
- IEEE Journal of Biomedical and Health Informatics, Vol. 24, Issue 5
Single‐subject morphological brain networks: connectivity mapping, topological characterization and test–retest reliability
journal, March 2016
- Wang, Hao; Jin, Xiaoqing; Zhang, Ye
- Brain and Behavior, Vol. 6, Issue 4
Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction
journal, December 2020
- Jiang, Hao; Cao, Peng; Xu, MingYi
- Computers in Biology and Medicine, Vol. 127
Towards Sparse Hierarchical Graph Classifiers
preprint, January 2018
- Cangea, Cătălina; Veličković, Petar; Jovanović, Nikola
- arXiv
EEG Source Network for the Diagnosis of Schizophrenia and the Identification of Subtypes Based on Symptom Severity—A Machine Learning Approach
journal, December 2020
- Kim, Jeong-Youn; Lee, Hyun Seo; Lee, Seung-Hwan
- Journal of Clinical Medicine, Vol. 9, Issue 12
Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network
conference, October 2021
- Sebenius, Isaac; Campbell, Alexander; Morgan, Sarah E.
- 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
Diagnosing schizophrenia with network analysis and a machine learning method
journal, February 2020
- Jo, Young Tak; Joo, Sung Woo; Shon, Seung‐Hyun
- International Journal of Methods in Psychiatric Research, Vol. 29, Issue 1
Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls
journal, January 2017
- Arbabshirani, Mohammad R.; Plis, Sergey; Sui, Jing
- NeuroImage, Vol. 145
Beyond the disconnectivity hypothesis of schizophrenia
journal, August 2019
- Rolls, Edmund T.; Cheng, Wei; Gilson, Matthieu
- Cerebral Cortex, Vol. 30, Issue 3
Classification of schizophrenia patients using a graph convolutional network: A combined functional MRI and connectomics analysis
journal, February 2023
- Chen, Xiaoyi; Zhou, Jing; Ke, Pengfei
- Biomedical Signal Processing and Control, Vol. 80
Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain
journal, January 2002
- Tzourio-Mazoyer, N.; Landeau, B.; Papathanassiou, D.
- NeuroImage, Vol. 15, Issue 1
Puzzling over schizophrenia: Schizophrenia, social environment and the brain
journal, February 2012
- Tost, Heike; Meyer-Lindenberg, Andreas
- Nature Medicine, Vol. 18, Issue 2
Brain Networks in Schizophrenia
journal, February 2014
- van den Heuvel, Martijn P.; Fornito, Alex
- Neuropsychology Review, Vol. 24, Issue 1
Semi-Supervised Classification with Graph Convolutional Networks
preprint, January 2016
- Kipf, Thomas N.; Welling, Max
- arXiv
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
- van Erp, Theo G. M.; Walton, Esther; Hibar, Derrek P.
- Biological Psychiatry, Vol. 84, Issue 9
3D-CNN based discrimination of schizophrenia using resting-state fMRI
journal, July 2019
- Qureshi, Muhammad Naveed Iqbal; Oh, Jooyoung; Lee, Boreom
- Artificial Intelligence in Medicine, Vol. 98
Overview of Machine Learning: Part 2
journal, November 2020
- Le, William Trung; Maleki, Farhad; Romero, Francisco Perdigón
- Neuroimaging Clinics of North America, Vol. 30, Issue 4
Measuring individual morphological relationship of cortical regions
journal, November 2014
- Kong, Xiang-zhen; Wang, Xu; Huang, Lijie
- Journal of Neuroscience Methods, Vol. 237
Graph U-Nets
journal, January 2021
- Gao, Hongyang; Ji, Shuiwang
- IEEE Transactions on Pattern Analysis and Machine Intelligence
EEG functional connectivity and deep learning for automatic diagnosis of brain disorders: Alzheimer’s disease and schizophrenia
journal, April 2022
- Alves, Caroline L.; Pineda, Aruane M.; Roster, Kirstin
- Journal of Physics: Complexity, Vol. 3, Issue 2
The Human Brainnetome Atlas: A New Brain Atlas Based on Connectional Architecture
journal, May 2016
- Fan, Lingzhong; Li, Hai; Zhuo, Junjie
- Cerebral Cortex, Vol. 26, Issue 8
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
- Northoff, Georg; Duncan, Niall W.
- Progress in Neurobiology, Vol. 145-146
Pitfalls of Graph Neural Network Evaluation
preprint, January 2018
- Shchur, Oleksandr; Mumme, Maximilian; Bojchevski, Aleksandar
- arXiv
Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients: A Multimodal MRI Study
journal, July 2021
- Zang, Jinyu; Huang, Yuanyuan; Kong, Lingyin
- Frontiers in Neuroscience, Vol. 15
Explainability Techniques for Graph Convolutional Networks
preprint, January 2019
- Baldassarre, Federico; Azizpour, Hossein
- arXiv
Regional homogeneity approach to fMRI data analysis
journal, May 2004
- Zang, Yufeng; Jiang, Tianzi; Lu, Yingli
- NeuroImage, Vol. 22, Issue 1
DPABI: Data Processing & Analysis for (Resting-State) Brain Imaging
journal, April 2016
- Yan, Chao-Gan; Wang, Xin-Di; Zuo, Xi-Nian
- Neuroinformatics, Vol. 14, Issue 3
A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity
journal, April 2021
- Yao, Dongren; Sui, Jing; Wang, Mingliang
- IEEE Transactions on Medical Imaging, Vol. 40, Issue 4
Graph Convolutional Networks Reveal Network-Level Functional Dysconnectivity in Schizophrenia
journal, May 2022
- Lei, Du; Qin, Kun; Pinaya, Walter H. L.
- Schizophrenia Bulletin, Vol. 48, Issue 4
GRETNA: a graph theoretical network analysis toolbox for imaging connectomics
journal, June 2015
- Wang, Jinhui; Wang, Xindi; Xia, Mingrui
- Frontiers in Human Neuroscience, Vol. 9
Divergent Alterations of Structural–Functional Connectivity Couplings in First-episode and Chronic Schizophrenia Patients
journal, April 2021
- Kong, Ling-yin; Huang, Yuan-yuan; Lei, Bing-ye
- Neuroscience, Vol. 460
Mild cognitive impairment and fMRI studies of brain functional connectivity: the state of the art
journal, August 2015
- Farràs-Permanyer, Laia; Guàrdia-Olmos, Joan; Peró-Cebollero, Maribel
- Frontiers in Psychology, Vol. 6
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends
journal, January 2018
- Hatcher, William Grant; Yu, Wei
- IEEE Access, Vol. 6
Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach
journal, January 2022
- Oh, Kang-Han; Oh, Il-Seok; Tsogt, Uyanga
- BMC Neuroscience, Vol. 23, Issue 1
Representation Learning on Graphs with Jumping Knowledge Networks
preprint, January 2018
- Xu, Keyulu; Li, Chengtao; Tian, Yonglong
- arXiv
Multimodal Magnetic Resonance Imaging Reveals Aberrant Brain Age Trajectory During Youth in Schizophrenia Patients
journal, March 2022
- Huang, Jiayuan; Ke, Pengfei; Chen, Xiaoyi
- Frontiers in Aging Neuroscience, Vol. 14
Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study
journal, January 2022
- Wang, Jing; Ke, Pengfei; Zang, Jinyu
- Frontiers in Neuroscience, Vol. 15
TE-HI-GCN: An Ensemble of Transfer Hierarchical Graph Convolutional Networks for Disorder Diagnosis
journal, November 2021
- Li, Lanting; Jiang, Hao; Wen, Guangqi
- Neuroinformatics, Vol. 20, Issue 2
Size of burden of schizophrenia and psychotic disorders
journal, August 2005
- Rössler, Wulf; Joachim Salize, Hans; van Os, Jim
- European Neuropsychopharmacology, Vol. 15, Issue 4
Evolving functional network properties and synchronizability during human epileptic seizures
journal, September 2008
- Schindler, Kaspar A.; Bialonski, Stephan; Horstmann, Marie-Therese
- Chaos: An Interdisciplinary Journal of Nonlinear Science, Vol. 18, Issue 3
On random graphs. I.
journal, July 2022
- Erdős, P.; Rényi, A.
- Publicationes Mathematicae Debrecen, Vol. 6, Issue 3-4
Abnormal Degree Centrality of Bilateral Putamen and Left Superior Frontal Gyrus in Schizophrenia with Auditory Hallucinations
journal, December 2015
- Chen, Cheng; Wang, Hui-Ling; Wu, Shi-Hao
- Chinese Medical Journal, Vol. 128, Issue 23
Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI
journal, March 2007
- Yu-Feng, Zang; Yong, He; Chao-Zhe, Zhu
- Brain and Development, Vol. 29, Issue 2
Neuroimaging in Schizophrenia
journal, February 2020
- Keshavan, Matcheri S.; Collin, Guusje; Guimond, Synthia
- Neuroimaging Clinics of North America, Vol. 30, Issue 1