Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence

TL;DR

This study demonstrates that incorporating temporal variability in fMRI data through a bi-LSTM neural network significantly improves the prediction of intelligence scores, outperforming static functional connectivity methods.

Contribution

The paper introduces a novel deep learning pipeline that leverages bi-LSTM to model temporal dynamics in fMRI data for better intelligence prediction, validated on a large adolescent dataset.

Findings

Dynamic FC and region-level time series outperform static FC in prediction accuracy.

The proposed bi-LSTM model identifies key brain regions associated with intelligence.

Features show high reliability across test-retest analyses.

Abstract

Neuroimaging-based prediction methods for intelligence and cognitive abilities have seen a rapid development in literature. Among different neuroimaging modalities, prediction based on functional connectivity (FC) has shown great promise. Most literature has focused on prediction using static FC, but there are limited investigations on the merits of such analysis compared to prediction based on dynamic FC or region level functional magnetic resonance imaging (fMRI) times series that encode temporal variability. To account for the temporal dynamics in fMRI data, we propose a deep neural network involving bi-directional long short-term memory (bi-LSTM) approach that also incorporates feature selection mechanism. The proposed pipeline is implemented via an efficient GPU computation framework and applied to predict intelligence scores based on region level fMRI time series as well as dynamic FC. We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals. Our detailed analysis illustrates that static FC consistently has inferior prediction performance compared to region level time series or dynamic FC for unimodal rest and task fMRI experiments, and in almost all cases using a combination of task and rest features. In addition, the proposed bi-LSTM pipeline based on region level time series identifies several shared and differential important brain regions across task and rest fMRI experiments that drive intelligence prediction. A test-retest analysis of the selected features shows strong reliability across cross-validation folds. Given the large sample size from ABCD study, our results provide strong evidence that superior prediction of intelligence can be achieved by accounting for temporal variations in fMRI.