MOSAIC: Aggregated fMRI Data for Neural Network Training

MOSAIC aggregates individual functional magnetic resonance imaging datasets using a shared preprocessing and stimulus curation pipeline. The dataset is designed to provide the scale needed for neural network training and the diversity required for generalizable results. It is hosted on AWS Open Data and is licensed under CC-BY-4.0.

Use Cases

• Train neural networks for brain activity prediction based on aggregated fMRI data.
• Develop generalizable computational models of brain function based on the dataset's curated stimulus diversity.
• Benchmark preprocessing pipelines for neuroimaging data based on the shared procedure used.
• Conduct meta-analyses of brain imaging studies based on the aggregated dataset structure.

Strengths

• Data is aggregated using a shared preprocessing pipeline, which may improve consistency.
• Stimulus curation procedure is designed to provide diversity for generalizable results.
• Licensed under the permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, size, and last update date are unknown, which may limit suitability assessment.
• Data may reflect bias inherent to the source datasets aggregated on aws_open_data.

Provenance

Source

aws_open_data

Collection Method

Aggregates individual fMRI datasets via a shared preprocessing and stimulus curation pipeline.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null