Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example

Abstract

Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropatholo-gies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes to compensate for this complexity, at the cost of uncontrolled heterogeneity. This heterogeneity raises new challenges, akin to those face in realistic diagnostic applications. Here, we demonstrate the feasibility of inter-site classification of neuropsychiatric status, with an application to the Autism Brain Imaging Data Exchange (ABIDE) database, a large (N=871) multi-site autism dataset. For this purpose, we investigate pipelines that extract the most predictive biomarkers from the data. These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas. Connectomes are then compared across participants to learn patterns of connectivity that differentiate typical controls from individuals with autism. We predict this neuropsychiatric status for participants from the same acquisition sites or different, unseen, ones. Good choices of methods for the various steps of the pipeline lead to 67% prediction accuracy on the full ABIDE data, which is significantly better than previously reported results. We perform extensive validation on multiple subsets of the data defined by different inclusion criteria. These enables detailed analysis of the factors contributing to successful connectome-based prediction. First, prediction accuracy improves as we include more subjects, up to the maximum amount of subjects available. Second, the definition of functional brain areas is of paramount importance for biomarker discovery: brain areas extracted from large R-fMRI datasets outperform reference atlases in the classification tasks.

arXiv commentin NeuroImage, Elsevier, 2016

References in corpus (4)

• Scikit-learn: Machine Learning in Python
• Learning and comparing functional connectomes across subjects
• A group model for stable multi-subject ICA on fMRI datasets
• Detection of brain functional-connectivity difference in post-stroke patients using group-level covariance modeling

Cited by in corpus (24)

• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
• Statistical power and prediction accuracy in multisite resting-state fMRI connectivity
• Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
• MADE-for-ASD: A Multi-Atlas Deep Ensemble Network for Diagnosing Autism Spectrum Disorder
• Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI
• Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks
• InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction
• Functional connectivity patterns of autism spectrum disorder identified by deep feature learning
• Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis
• GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference
• Combining Anatomical and Functional Networks for Neuropathology Identification: A Case Study on Autism Spectrum Disorder
• Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning
• STARFormer: A Novel Spatio-Temporal Aggregation Reorganization Transformer of FMRI for Brain Disorder Diagnosis
• Edge-variational Graph Convolutional Networks for Uncertainty-aware Disease Prediction
• AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction
• Spectral Graph Convolutions for Population-based Disease Prediction
• Computational and informatics advances for reproducible data analysis in neuroimaging
• Ensemble learning with 3D convolutional neural networks for connectome-based prediction
• Deep Markov Spatio-Temporal Factorization
• Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity
• Deep Dynamic Effective Connectivity Estimation from Multivariate Time Series
• Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies
• A Hybrid 3DCNN and 3DC-LSTM based model for 4D Spatio-temporal fMRI data: An ABIDE Autism Classification study