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

Zijin Gu, Keith Jamison, Amy Kuceyeski, Mert R. Sabuncu
Medical Imaging with Deep Learning, PMLR 227:107-118, 2024.

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}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-gu24a, title = {Decoding natural image stimuli from fMRI data with a surface-based convolutional network}, author = {Gu, Zijin and Jamison, Keith and Kuceyeski, Amy and Sabuncu, Mert R.}, booktitle = {Medical Imaging with Deep Learning}, pages = {107--118}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/gu24a/gu24a.pdf}, url = {https://proceedings.mlr.press/v227/gu24a.html}, 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}.} }
Endnote
%0 Conference Paper %T Decoding natural image stimuli from fMRI data with a surface-based convolutional network %A Zijin Gu %A Keith Jamison %A Amy Kuceyeski %A Mert R. Sabuncu %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-gu24a %I PMLR %P 107--118 %U https://proceedings.mlr.press/v227/gu24a.html %V 227 %X 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}.
APA
Gu, Z., Jamison, K., Kuceyeski, A. & Sabuncu, M.R.. (2024). Decoding natural image stimuli from fMRI data with a surface-based convolutional network. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:107-118 Available from https://proceedings.mlr.press/v227/gu24a.html.

Related Material