ICA-based sparse feature recovery from fMRI datasets

TL;DR

This paper introduces a novel ICA-based method for extracting sparse, specific features from fMRI data, improving accuracy over existing techniques by controlling deviation from isotropy.

Contribution

A new thresholding procedure for ICA that guarantees exact specificity in feature detection, enhancing the interpretability of brain network components.

Findings

Outperforms current state-of-the-art methods in synthetic data

Achieves higher sensitivity and specificity in fMRI datasets

Provides a controlled, conservative feature detection level

Abstract

Spatial Independent Components Analysis (ICA) is increasingly used in the context of functional Magnetic Resonance Imaging (fMRI) to study cognition and brain pathologies. Salient features present in some of the extracted Independent Components (ICs) can be interpreted as brain networks, but the segmentation of the corresponding regions from ICs is still ill-controlled. Here we propose a new ICA-based procedure for extraction of sparse features from fMRI datasets. Specifically, we introduce a new thresholding procedure that controls the deviation from isotropy in the ICA mixing model. Unlike current heuristics, our procedure guarantees an exact, possibly conservative, level of specificity in feature detection. We evaluate the sensitivity and specificity of the method on synthetic and fMRI data and show that it outperforms state-of-the-art approaches.