• Corpus ID: 234680508

Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies

  title={Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies},
  author={Dushyant Sahoo and Christos Davatzikos},
Multi-site fMRI studies face the challenge that the pooling introduces systematic non-biological site-specific variance due to hardware, software, and environment. In this paper, we propose to reduce site-specific variance in the estimation of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data via a simple yet effective matrix factorization while preserving biologically relevant variations. Our method leverages unsupervised adversarial learning to improve the reproducibility of… 

Robust Hierarchical Patterns for identifying MDD patients: A Multisite Study

This work proposes a novel model based on hierarchical Sparse Connectivity Patterns (hSCPs) to predict MDD patients from functional connectivity matrices extracted from resting-state fMRI data and shows that the proposed model can robustly identify clinically relevant patterns characteristic of MDD with high reproducibility.

Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data

A set of novel self-supervised learning frameworks for neuroimaging data based on prominent learning frameworks in NLP show that the pre-trained models transfer well, outperforming baseline models when adapted to the data of only a few individuals, while models pre- trained in a learning framework based on causal language modeling clearly outperform the others.



Extraction of Hierarchical Functional Connectivity Components in human brain using Adversarial Learning

This paper aims to use current advancements in adversarial learning to estimate interpretable hierarchical patterns in the human brain using rsfMRI data, which are robust to “adversarial effects” such as interscanner variations.

GPU accelerated extraction of sparse Granger causality patterns

This work introduces an efficient method for the extraction of shared causality patterns, and it is demonstrated its performance by processing the rs-fMRI scans of the hundred unrelated Human Connectome Project subjects.

Latent source mining in FMRI via restricted Boltzmann machine

The proposed method not only interprets fMRI time courses explicitly to take advantages of deep learning models in latent feature learning but also substantially reduces model complexity and increases the scale of training set to improve training efficiency.

Modeling Task fMRI Data Via Deep Convolutional Autoencoder

A new neural network structure based on CNN is developed, called deep convolutional auto-encoder (DCAE), in order to take the advantages of both data-driven approach and CNN’s hierarchical feature abstraction ability for the purpose of learning mid-level and high-level features from complex, large-scale tfMRI time series in an unsupervised manner.

A Data-Driven Sparse GLM for fMRI Analysis Using Sparse Dictionary Learning With MDL Criterion

A new data driven fMRI analysis that is derived solely based upon the sparsity of the signals is proposed that enables estimation of spatially adaptive design matrix as well as sparse signal components that represent synchronous, functionally organized and integrated neural hemodynamics.

Statistical power and prediction accuracy in multisite resting-state fMRI connectivity

A resting state fMRI analysis pipeline for pooling inference across diverse cohorts: an ENIGMA rs-fMRI protocol

This work proposes an initial pipeline for multi-site rsfMRI analysis to allow research groups around the world to analyze scans in a harmonized way, and to perform coordinated statistical tests.

Statistical harmonization corrects site effects in functional connectivity measurements from multi‐site fMRI data

The proposed ComBat harmonization approach for fMRI‐derived connectivity measures facilitates reliable and efficient analysis of retrospective and prospective multi‐site fMRI neuroimaging studies and increased the power to detect age associations when using optimal combinations of connectivity metrics and brain atlases.

Bayesian Structure Learning for Dynamic Brain Connectivity

A novel Bayesian model is proposed which estimates covariances which vary smoothly over time, with an instantaneous decomposition into a collection of spatially sparse components – resulting in parsimonious and highly interpretable estimates of dynamic brain connectivity.