From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
This work addresses the problem of limited labeled data in fMRI-to-image reconstruction for neuroscience and medical imaging researchers, offering an incremental improvement through self-supervision.
The paper tackles the challenge of reconstructing natural images from fMRI brain recordings by introducing a self-supervised approach that leverages both labeled and unlabeled data, including test-fMRI data, to adapt the reconstruction network to new input statistics, achieving improved performance without specifying concrete numbers.
Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons. We present a novel approach which, in addition to the scarce labeled data (training pairs), allows to train fMRI-to-image reconstruction networks also on "unlabeled" data (i.e., images without fMRI recording, and fMRI recording without images). The proposed model utilizes both an Encoder network (image-to-fMRI) and a Decoder network (fMRI-to-image). Concatenating these two networks back-to-back (Encoder-Decoder & Decoder-Encoder) allows augmenting the training with both types of unlabeled data. Importantly, it allows training on the unlabeled test-fMRI data. This self-supervision adapts the reconstruction network to the new input test-data, despite its deviation from the statistics of the scarce training data.