Functional brain-to-brain transformation without shared stimuli

Abstract

Combining Functional MRI (fMRI) data across different subjects and datasets is crucial for many neuroscience tasks. Relying solely on shared anatomy for brain-to-brain mapping is inadequate. Existing functional transformation methods thus depend on shared stimuli across subjects and fMRI datasets, which are often unavailable. In this paper, we propose an approach for computing functional brain-to-brain transformations without any shared data (stimuli), a feat not previously achieved in functional transformations. This presents exciting research prospects for merging and enriching diverse datasets, even when they involve distinct stimuli that were collected using different fMRI machines of varying resolutions (e.g., 3-Tesla and 7-Tesla). Our approach combines brain-to-brain transformation with Image-to-fMRI encoders, thus enabling to learn functional transformations on visual stimuli to which subjects were never exposed. Furthermore, we demonstrate the applicability of our method for improving Image-to-fMRI encoding of subjects scanned on older low-resolution 3T fMRI datasets, by using a new high-resolution 7T fMRI dataset (scanned on different subjects and different stimuli). Altogether, we provide a general framework for functional alignment across individuals and datasets without any shared stimuli, opening new possibilities for integrating and leveraging the diversity of many existing fMRI collections.