# Generating synthetic task-based brain fingerprints for population neuroscience using deep learning

## TL;DR

This paper introduces DeepTaskGen, a deep learning method that creates synthetic task-based brain maps from resting-state fMRI data, enabling large-scale studies of individual brain differences.

## Contribution

DeepTaskGen is a novel deep-learning approach that synthesizes task-based fMRI data from resting-state scans, enabling scalable and flexible neuroimaging research.

## Key findings

- DeepTaskGen outperforms existing benchmarks in generating synthetic task-contrast maps while preserving individual variability.
- Synthetic maps perform comparably or better than real maps in predicting demographic, cognitive, and clinical variables.
- The method enables the generation of 47 task-based contrast maps for over 20,000 individuals using UK Biobank data.

## Abstract

Task-based functional magnetic resonance imaging (fMRI) reveals individual differences in neural correlates of cognition but faces scalability challenges due to cognitive demands, protocol variability, and limited task coverage in large datasets. Here, we propose DeepTaskGen, a deep-learning approach that synthesizes non-acquired task-based contrast maps from resting-state (rs-) fMRI. We validate this approach using the Human Connectome Project lifespan data, then generate 47 contrast maps from 7 different cognitive tasks for over 20,000 individuals from UK Biobank. DeepTaskGen outperforms several benchmarks in generating synthetic task-contrast maps, achieving superior reconstruction performance while retaining inter-individual variation essential for biomarker development. We further show comparable or superior predictive performance of synthetic maps relative to actual maps and rs-connectomes across diverse demographic, cognitive, and clinical variables. This approach facilitates the study of individual differences and the generation of task-related biomarkers by enabling the generation of arbitrary functional cognitive tasks from readily available rs-fMRI data.

DeepTaskGen uses deep learning to generate synthetic task-based fMRI maps from resting state data, enabling scalable neuroimaging studies. It preserves individual variation and outperforms benchmarks in biomarker and cognitive prediction.