We demonstrate the possibility of reconstructing images from fNIRS brain activity and start building a prototype to match the required specs. By training an image reconstruction model on downsampled fMRI data, we discovered that cm-scale spatial resolution is sufficient for image generation. We obtained 71% retrieval accuracy with 1-cm resolution, compared to 93% on the full-resolution fMRI, and 20% with 2-cm resolution. With simulations and high-density tomography, we found that time-domain fNIRS can achieve 1-cm resolution, compared to 2-cm resolution for continuous-wave fNIRS. Lastly, we share designs for a prototype time-domain fNIRS device, consisting of a laser driver, a single photon detector, and a time-to-digital converter system.
@article{arxiv.2406.07662,
title = {Progress Towards Decoding Visual Imagery via fNIRS},
author = {Michel Adamic and Wellington Avelino and Anna Brandenberger and Bryan Chiang and Hunter Davis and Stephen Fay and Andrew Gregory and Aayush Gupta and Raphael Hotter and Grace Jiang and Fiona Leng and Stephen Polcyn and Thomas Ribeiro and Paul Scotti and Michelle Wang and Marley Xiong and Jonathan Xu},
journal= {arXiv preprint arXiv:2406.07662},
year = {2024}
}