Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease

Abstract

Graphs are widely used as a natural framework that captures interactions between individual elements represented as nodes in a graph. In medical applications, specifically, nodes can represent individuals within a potentially large population (patients or healthy controls) accompanied by a set of features, while the graph edges incorporate associations between subjects in an intuitive manner. This representation allows to incorporate the wealth of imaging and non-imaging information as well as individual subject features simultaneously in disease classification tasks. Previous graph-based approaches for supervised or unsupervised learning in the context of disease prediction solely focus on pairwise similarities between subjects, disregarding individual characteristics and features, or rather rely on subject-specific imaging feature vectors and fail to model interactions between them. In this paper, we present a thorough evaluation of a generic framework that leverages both imaging and non-imaging information and can be used for brain analysis in large populations. This framework exploits Graph Convolutional Networks (GCNs) and involves representing populations as a sparse graph, where its nodes are associated with imaging-based feature vectors, while phenotypic information is integrated as edge weights. The extensive evaluation explores the effect of each individual component of this framework on disease prediction performance and further compares it to different baselines. The framework performance is tested on two large datasets with diverse underlying data, ABIDE and ADNI, for the prediction of Autism Spectrum Disorder and conversion to Alzheimer's disease, respectively. Our analysis shows that our novel framework can improve over state-of-the-art results on both databases, with 70.4% classification accuracy for ABIDE and 80.0% for ADNI.

in Press at Medical Image Analysis, MICCAI 2017 Special Issue

References in corpus (13)

• Scikit-learn: Machine Learning in Python
• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Brain Tumor Segmentation with Deep Neural Networks
• Spectral Networks and Locally Connected Networks on Graphs
• Learning Convolutional Neural Networks for Graphs
• Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example
• Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Deep Feature Learning for Graphs
• Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks
• Deep neural networks on graph signals for brain imaging analysis

Cited by in corpus (46)

• Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• SIGN: Scalable Inception Graph Neural Networks
• FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis
• Ensemble manifold based regularized multi-modal graph convolutional network for cognitive ability prediction
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Latent-Graph Learning for Disease Prediction
• BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck
• MADE-for-ASD: A Multi-Atlas Deep Ensemble Network for Diagnosing Autism Spectrum Disorder
• Longitudinal Speech Biomarkers for Automated Alzheimer's Detection
• Deep Learning for Neuroimaging-based Diagnosis and Rehabilitation of Autism Spectrum Disorder: A Review
• Prediction of Thrombectomy Functional Outcomes using Multimodal Data
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• Zoom in to where it matters: a hierarchical graph based model for mammogram analysis
• A deep learning model for data-driven discovery of functional connectivity
• Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)
• Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes
• Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
• Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review
• MGN-Net: a multi-view graph normalizer for integrating heterogeneous biological network populations
• Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning
• GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference
• Fake News Detection using Semi-Supervised Graph Convolutional Network
• Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
• Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK Biobank
• DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease
• AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction
• A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Disease
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• Deep Dynamic Effective Connectivity Estimation from Multivariate Time Series
• Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosis
• Deep sr-DDL: Deep Structurally Regularized Dynamic Dictionary Learning to Integrate Multimodal and Dynamic Functional Connectomics data for Multidimensional Clinical Characterizations
• Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network
• A Hybrid 3DCNN and 3DC-LSTM based model for 4D Spatio-temporal fMRI data: An ABIDE Autism Classification study
• DeepAtrophy: Teaching a Neural Network to Differentiate Progressive Changes from Noise on Longitudinal MRI in Alzheimer's Disease
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Brain dynamics via Cumulative Auto-Regressive Self-Attention
• DS-GCNs: Connectome Classification Using Dynamic Spectral Graph Convolution Networks with Assistant Task Training
• U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction