L1-Regularized ICA: A Novel Method for Analysis of Task-related fMRI Data

TL;DR

This paper introduces an L1-regularized ICA method that enhances feature interpretability in high-dimensional fMRI data by incorporating sparsity constraints and optimizing via a difference of convex functions algorithm.

Contribution

The paper presents a novel sparse ICA approach with L1-regularization, improving interpretability of features in high-dimensional neuroimaging data.

Findings

Effective feature extraction from synthetic data

Successful application to real fMRI data

Improved interpretability of ICA components

Abstract

We propose a new method of independent component analysis (ICA) in order to extract appropriate features from high-dimensional data. In general, matrix factorization methods including ICA have a problem regarding the interpretability of extracted features. For the improvement of interpretability, it is considered that sparse constraint on a factorized matrix is helpful. With this background, we construct a new ICA method with sparsity. In our method, the L1-regularization term is added to the cost function of ICA, and minimization of the cost function is performed by difference of convex functions algorithm. For the validity of our proposed method, we apply it to synthetic data and real functional magnetic resonance imaging data.