Zero-shot Learning of Individualized Task Contrast Prediction from Resting-state Functional Connectomes

TL;DR

This paper introduces OPIC, a zero-shot learning method that predicts individual-specific task contrasts from resting-state fMRI by leveraging group-average contrasts, enabling generalization to unseen tasks with limited data.

Contribution

The paper presents OPIC, a novel zero-shot prediction model that generalizes to new tasks using group-average contrasts, reducing the need for extensive task-specific training data.

Findings

OPIC outperforms simple group-averages in predicting novel task contrasts.

OPIC's predictions are competitive with state-of-the-art in-domain models.

The approach enables zero-shot generalization to unseen tasks.

Abstract

Given sufficient pairs of resting-state and task-evoked fMRI scans from subjects, it is possible to train ML models to predict subject-specific task-evoked activity using resting-state functional MRI (rsfMRI) scans. However, while rsfMRI scans are relatively easy to collect, obtaining sufficient task fMRI scans is much harder as it involves more complex experimental designs and procedures. Thus, the reliance on scarce paired data limits the application of current techniques to only tasks seen during training. We show that this reliance can be reduced by leveraging group-average contrasts, enabling zero-shot predictions for novel tasks. Our approach, named OPIC (short for Omni-Task Prediction of Individual Contrasts), takes as input a subject's rsfMRI-derived connectome and a group-average contrast, to produce a prediction of the subject-specific contrast. Similar to zero-shot learning in large language models using special inputs to obtain answers for novel natural language processing tasks, inputting group-average contrasts guides the OPIC model to generalize to novel tasks unseen in training. Experimental results show that OPIC's predictions for novel tasks are not only better than simple group-averages, but are also competitive with a state-of-the-art model's in-domain predictions that was trained using in-domain tasks' data.