Open-fMIND is a uniformly preprocessed, openly accessible corpus of parcellated fMRI timeseries and functional connectivity matrices, built from public OpenNeuro studies. Every run is processed with fMRIPrep and parcellated under 52 atlases, ready for self-supervised pretraining and connectivity analyses at scale.
fMRIPrep output projected onto each atlas, nothing else; shipped with the fMRIPrep confounds, frame-aligned, so you can apply your own denoising.
The same timeseries after a fixed recipe: confound regression, scrubbing, detrending, band-pass filtering and z-scoring.
| quasiraw | preproc | |
|---|---|---|
| Datasets | 322 | 320 |
| Subjects (counted per dataset) | 11,379 | 11,320 |
| Runs | 45,731 | 45,019 |
| Resting-state runs | 8,756 | 8,704 |
| Task runs | 36,975 | 36,315 |
| Atlases | 52 | 52 |
| Timeseries (runs × atlases) | 2.38 M | 2.34 M |
| Volumes (3D time points) | 11.39 M | 10.92 M |
Every run is available for every atlas, with one connectivity matrix per timeseries. preproc
counts the volumes kept after scrubbing. Each file has a JSON sidecar with the full provenance
(download, fMRIPrep, parcellation, denoising, connectivity), and qc.tsv gives per-run motion.
Brain BOLD datasets from OpenNeuro, at the snapshot recorded in each dataset description.
One job per subject, without surface reconstruction; output in MNI152NLin2009cAsym at 2 mm.
Mean signal per region with nilearn (NiftiLabelsMasker, or NiftiMapsMasker for probabilistic atlases). This is quasiraw.
One nilearn.signal.clean call: 24 motion parameters plus white-matter and CSF signals, scrubbing above 0.5 mm FD, detrending, 0.01–0.1 Hz band-pass, z-scoring. Runs with fewer than 50 volumes left are dropped. This is preproc.
Correlation per run with nilearn's ConnectivityMeasure (default settings), stored as float32.
Every atlas is applied to every run under identical processing, so representations are comparable across granularities and atlas families.
A Brain-Semantoks encoder pretrained on Open-fMIND alone matches the published checkpoint pretrained on UK Biobank on HCP-YA, with frozen features and identical folds and classifiers.
Files are packed into ~3 GB tar shards that keep their BIDS paths, split by atlas and by
rest / task. A parquet index locates every file, so you can filter, stream whole shards,
or fetch a single run with an HTTP range request.
import gzip, json import pandas as pd, nibabel as nib, webdataset as wds base = "https://huggingface.co/datasets/cbarbano/open-fmind/resolve/main" idx = pd.read_parquet(f"{base}/index/preproc_timeseries.parquet", filters=[("atlas", "==", "schaefer400"), ("task_type", "==", "rest")]) urls = [f"{base}/{s}" for s in sorted(idx.shard.unique())] for sample in wds.WebDataset(urls, shardshuffle=False): img = nib.Nifti1Image.from_bytes(gzip.decompress(sample["nii.gz"])) ts = img.get_fdata().squeeze().T # (n_timepoints, n_rois) meta = json.loads(sample["json"]) # RepetitionTime, ROILabels, TaskType, ...
hf download cbarbano/open-fmind --repo-type dataset \
--include "preproc/timeseries/atlas-schaefer400/*" --local-dir open-fmind
cat open-fmind/preproc/timeseries/atlas-schaefer400/*/shard-*.tar | tar -xf - -i
Licenses. Derived from public OpenNeuro datasets, each under its own license (251 CC0, 34 PDDL,
30 not stated, 5 CC-BY / CC-BY-SA, 1 CC-BY-NC, 1 other). LICENSES.tsv lists the license, authors, DOI
and requested acknowledgement of every source dataset; please cite the datasets you use.
Built on OpenNeuro, fMRIPrep and nilearn.
Barbano, C. A., Marraffini, G., Wassermann, D. Open-fMIND: A Large-Scale Open-Access fMRI Corpus for Pretraining Brain Foundation Models. arXiv preprint arXiv:2611.21215, 2026.
@article{barbano2026openfmind,
title = {Open-fMIND: A Large-Scale Open-Access fMRI Corpus for Pretraining Brain Foundation Models},
author = {Barbano, Carlo Alberto and Marraffini, Giovanni and Wassermann, Demian},
journal = {arXiv preprint arXiv:2611.21215},
year = {2026}
}