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

Published: 04 Apr 2023, Last Modified: 22 Oct 2023MIDL 2023 OralReaders: Everyone
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: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2212.02409/code)
4 Replies

Loading