Estimation of functional connectivity in fMRI data using stability selection-based sparse partial correlation with elastic net penalty

By Srikanth Ryali, Tianwen Chen, Kaustubh Supekar, Vinod Menon. 2011

242 citations recorded by the source corpus.

Characterizing interactions between multiple brain regions is important for understanding brain function. Functional connectivity measures based on partial correlation provide an estimate of the linear conditional dependence between brain regions after removing the linear influence of other regions. Estimation of partial correlations is, however, difficult when the number of regions is large, as is now increasingly the case with a growing number of large-scale brain connectivity studies. To address this problem, we develop novel methods for estimating sparse partial correlations between multiple regions in fMRI data using elastic net penalty (SPC-EN), which combines L1- and L2-norm regularization We show that L1-norm regularization in SPC-EN provides sparse interpretable solutions while L2-norm regularization improves the sensitivity of the method when the number of possible connections between regions is larger than the number of time points, and when pair-wise correlations between brain regions are high. An issue with regularization-based methods is choosing the regularization parameters which in turn determine the selection of connections between brain regions. To address this problem, we deploy novel stability selection methods to infer significant connections between brain regions. We also compare the performance of SPC-EN with existing methods which use only L1-norm regularization (SPC-L1) on simulated and experimental datasets. Detailed simulations show that the performance of SPC-EN, measured in terms of sensitivity and accuracy is superior to SPC-L1, especially at higher rates of feature prevalence. Application of our methods to resting-state fMRI data obtained from 22 healthy adults show that SPC-EN reveals a modular architecture characterized by strong inter-hemispheric links, distinct ventral and dorsal stream pathways, and a major hub in the posterior medial cortex- features that were missed by conventional methods. Taken together, our findings suggest that SPC-EN provides a powerful tool for characterizing connectivity involving a large number of correlated regions that span the entire brain.

Subfields: Cognitive Neuroscience, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Interval Coded Scoring: a toolbox for interpretable scoring systems (2018, background): “More recently, Ryali et al. (2012) applied the elastic net to estimate functional connectivity from fMRI data, whereas Greene et al. (2015) exploited it to detect mobility parameters progression of early multiple sclerosis and to discriminate patients from a control population based on…”
Modeling disease progression via multi-task learning (2013, unknown): “…selection has been successfully applied to bioinformatics applications especially in genome-related biomarker selection problems where sample size is much smaller than feature dimension (n ≪ d) (Eleftherohorinou et al., 2011; Ryali et al., 2012; Stekhoven et al., 2011; Vounou et al., 2012).”
The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features (2018, unknown): “Notably, LASSO can only select a maximum of N-1 features in the final model, where N is the sample size (Efron et al., 2004; Ryali et al., 2012).”
Communication-Avoiding Optimization Methods for Distributed Massive-Scale Sparse Inverse Covariance Estimation (2017, methodology): “The work of [44] applies the “SPACE” estimator of [40], except augmented with an additional squared `2-norm penalty, to low-dimensional fMRI data; while certainly related to our approach, this method unfortunately suffers from all three of the aforementioned issues.”
Clinical applications of the functional connectome (2013, unknown): “This can be addressed in part using regularization methods (Ryali et al., 2012; Smith et al., 2011; Varoquaux et al., 2010).”
Task-Based Core-Periphery Organization of Human Brain Dynamics (2012, background): “Future studies could employ multiple estimates of statistical associations in the form of diagnostics [67–69] and/or models [70,71] that might uncover other sets of interactions that Core-Periphery Organization of Brain Dynamics”