Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies
This work addresses the challenge of pooling fMRI data from multiple sites for better biomarker analysis and brain understanding, though it is incremental as it builds on existing methods to handle site effects.
The paper tackled the problem of site-related variations in multi-center fMRI data by introducing a matrix factorization method with adversarial learning to estimate hierarchical sparsity connectivity patterns, resulting in improved accuracy and reproducibility of components on both simulated and real datasets.
Resting-state fMRI has been shown to provide surrogate biomarkers for the analysis of various diseases. In addition, fMRI data helps in understanding the brain's functional working during resting state and task-induced activity. To improve the statistical power of biomarkers and the understanding mechanism of the brain, pooling of multi-center studies has become increasingly popular. But pooling the data from multiple sites introduces variations due to hardware, software, and environment. In this paper, we look at the estimation problem of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data acquired on multiple sites. We introduce a simple yet effective matrix factorization based formulation to reduce site-related effects while preserving biologically relevant variations. We leverage adversarial learning in the unsupervised regime to improve the reproducibility of the components. Experiments on simulated datasets display that the proposed method can estimate components with improved accuracy and reproducibility. We also demonstrate the improved reproducibility of the components while preserving age-related variation on a real dataset compiled from multiple sites.