From Connectomic to Task-evoked Fingerprints: Individualized Prediction of Task Contrasts from Resting-state Functional Connectivity

TL;DR

This paper introduces BrainSurfCNN, a surface-based neural network that predicts individual task contrasts from resting-state fMRI fingerprints, improving accuracy and subject identification over existing methods.

Contribution

The paper presents a novel surface-based CNN with a reconstructive-contrastive loss for personalized brain activity prediction from resting-state data.

Findings

Significantly improved prediction accuracy over baseline methods.

Outperforms test-retest benchmarks in subject identification.

Demonstrates the effectiveness of the proposed model in individual-specific brain mapping.

Abstract

Resting-state functional MRI (rsfMRI) yields functional connectomes that can serve as cognitive fingerprints of individuals. Connectomic fingerprints have proven useful in many machine learning tasks, such as predicting subject-specific behavioral traits or task-evoked activity. In this work, we propose a surface-based convolutional neural network (BrainSurfCNN) model to predict individual task contrasts from their resting-state fingerprints. We introduce a reconstructive-contrastive loss that enforces subject-specificity of model outputs while minimizing predictive error. The proposed approach significantly improves the accuracy of predicted contrasts over a well-established baseline. Furthermore, BrainSurfCNN's prediction also surpasses test-retest benchmark in a subject identification task.