Deep image reconstruction from human brain activity
Version 16 2024-08-08, 02:56
Version 15 2024-08-07, 05:43
Version 14 2024-08-06, 02:05
Version 13 2022-10-14, 01:09
Version 12 2022-10-13, 13:13
Version 11 2022-01-27, 02:00
Version 10 2020-09-09, 02:31
Version 9 2020-09-08, 02:55
Version 8 2020-08-05, 08:34
Version 7 2020-05-18, 09:46
Version 6 2019-04-12, 08:22
Version 5 2019-04-12, 07:42
Version 4 2019-04-09, 10:06
Version 3 2019-03-29, 08:03
Version 2 2018-10-24, 01:12
Version 1 2018-09-11, 13:52
dataset
posted on 2024-08-08, 02:56 authored by Kamitani LabKamitani Lab, Guohua Shen, Tomoyasu Horikawa, Kei Majima, Yukiyasu Kamitani<p><a href="https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006633" target="_blank">Shen, Horikawa, Majima, and Kamitani (2019) Deep image reconstruction from human brain activity. PLos Comput Biol.</a> (<a href="https://www.biorxiv.org/content/10.1101/240317v1" target="_blank">bioRxiv preprint</a>)</p>
<p>Here we provide DNN features decoded from human brain activity (decodedfeatures-*.mat files) as well as preprocessed fMRI data used for the decoding (sub-*.h5 files).<br>
Raw fMRI data are available at <a href="https://openneuro.org/datasets/ds001506" target="_blank">OpenNeuro</a>.</p>
<p>Demo code is available at <a href="https://github.com/KamitaniLab/DeepImageReconstruction" target="_blank">GitHub</a>.</p>
<h2>History</h2>
<p>2022-10-14: Add fMRI data (sub-03) preprocessed by fmriprep (*_fmriprep_volume_native.h5)</p>
<p>2022-10-13: Add fMRI data (sub-01, sub-02) preprocessed by fmriprep (*_fmriprep_volume_native.h5)<br>
2022-01-27: Minor update on fMRI data (v2; "stimulus_name" was added).<br>
2020-09-09: True DNN features (unit activations) of VGG19 for natural image training and test images were added.</p>
<p>2020-09-08: True DNN features (unit activations) of VGG19 (except conv1) for natural image training images were added.</p>
<p>2020-08-05: fMRI data version 2, which applied slightly different preprocessng and ROIs from the original study, were added (for the natural image experiment only; *_perceptionNaturalImageTraining/Test_VC_v2.h5).</p>
<p>2020-05-18: The following fMRI data files of artificial images, letters, and imagery experiments contained incorrect samples and were fixed.</p>
<ul>
<li>sub-01_perceptionLetterImage_original_VC.h5</li>
<li>sub-02_perceptionArtificialImage_original_VC.h5</li>
<li>sub-02_perceptionLetterImage_original_VC.h5</li>
<li>sub-02_imagery_original_VC.h5</li>
<li>sub-03_perceptionArtificialImage_original_VC.h5</li>
<li>sub-03_perceptionLetterImage_original_VC.h5</li>
<li>sub-03_imagery_original_VC.h5</li>
</ul>
<p><br></p>
