Published on Tue Apr 20 2021

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

Dushyant Sahoo, Christos Davatzikos
0
0
0
Abstract

The estimation of sparse hierarchical components reflecting patterns of the brain's functional connectivity from rsfMRI data can contribute to our understanding of the brain's functional organization, and can lead to biomarkers of diseases. However, inter-scanner variations and other confounding factors pose a challenge to the robust and reproducible estimation of functionally-interpretable brain networks, and especially to reproducible biomarkers. Moreover, the brain is believed to be organized hierarchically, and hence single-scale decompositions miss this hierarchy. The 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 inter-scanner variations. We write the estimation problem as a minimization problem and solve it using alternating updates. Extensive experiments on simulation and a real-world dataset show high reproducibility of the components compared to other well-known methods.

Thu May 13 2021
Machine Learning
Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies
Resting-state fMRI has been shown to provide surrogate biomarkers for the analyzing of various diseases. To improve the statistical power of biomarkers and the understanding mechanism of the brain, pooling of multi-center studies has become increasingly popular.
1
0
0
Tue Dec 29 2015
Machine Learning
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
Comparing functional connectivity of subjects in two populations is difficult. Sparse penalties enable statistical assurances and interpretable models. The debiased lasso and multi-task fused lasso can be used to obtain confidence intervals on edge differences in GGMs.
0
0
0
Mon Dec 07 2015
Machine Learning
Learning population and subject-specific brain connectivity networks via Mixed Neighborhood Selection
In neuroimaging data analysis, Gaussian graphical models are often used to model statistical dependencies across spatially remote brain regions. We introduce an additional mixed effect component to neighborhood selection in order to simultaneously estimate a graphical model for the population of subjects as well as for each individual subject.
0
0
0
Sat Nov 26 2016
Machine Learning
Machine Learning on Human Connectome Data from MRI
Functional MRI (fMRI) and diffusion MRI (dMRI) are non-invasive imaging technologies that allow in-vivo analysis of a patient's brain network. Use of these technologies has enabled faster and better diagnoses and treatments of neurological disorders. Recently, researchers have been exploring the application of machine learning models to connectome data.
0
0
0
Fri Oct 17 2014
Machine Learning
Randomized Structural Sparsity via Constrained Block Subsampling for Improved Sensitivity of Discriminative Voxel Identification
Stability selection has received a great deal of attention lately, especially due to its finite sample control of false discoveries. However, it fails to make explicit use of the correlation property or structural information of these features. Many relevant but probably correlated discriminative voxels are missed.
0
0
0
Mon Oct 30 2017
Artificial Intelligence
Fast and Scalable Learning of Sparse Changes in High-Dimensional Gaussian Graphical Model Structure
We focus on the problem of estimating the change in the dependency structures of two -dimensional Gaussian Graphical models. We propose a novel method, DIFFEE for estimating DIFFerential networks via an Elementary Estimator.
0
0
0