Decoding natural image stimuli from fMRI data with a surface-based convolutional network

Zijin Gu, Keith Jamison, Amy Kuceyeski, Mert R. Sabuncu

Keywords: functional MRI, neural decoding, image reconstruction

TL;DR: We propose a novel approach to decode visual stimuli from fMRI with high semantic fidelity and rich fine-grained detail.

Abstract:

Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we propose a novel approach for this task, which we call Cortex2Image, to decode visual stimuli with high semantic fidelity and rich fine-grained detail. In particular, we train a surface-based convolutional network model that maps from brain response to semantic image features first (Cortex2Semantic).
We then combine this model with a high-quality image generator (Instance-Conditioned GAN) to train another mapping from brain response to fine-grained image features using a variational approach (Cortex2Detail). Image reconstructions obtained by our proposed method achieve state-of-the-art semantic fidelity, while yielding good fine-grained similarity with the ground-truth stimulus. Our code is available on \url{https://github.com/zijin-gu/meshconv-decoding.git}.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2212.02409/code)