Multimodal Healthy Control Dataset: 100 Volunteers for Medical Imaging Research

100 healthy control volunteers (80 train, 20 test) provide data for the Big Cross-Modal Attenuation Correction Challenge (BIC-MAC) held in conjunction with MICCAI 2026. The dataset is released by DEPICT-RH and was last updated in July 2026. It includes PET readouts and is associated with a GitHub repository for the project.

Use Cases

• Developing cross-modal attenuation correction algorithms based on the multimodal PET data.
• Training and testing machine learning models for medical image analysis based on the provided train/test split.
• Benchmarking neuroimaging analysis tools using a dataset of healthy control subjects.
• Studying the characteristics of healthy control data for use in clinical research comparisons.

Strengths

• 100 healthy control volunteers provide a defined subject pool.
• An explicit 80/20 train/test split is defined for model development.
• The dataset is associated with a formal MICCAI 2026 challenge (BIC-MAC), suggesting a research context.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited; actual data quality and completeness require manual inspection after download.
• The dataset size is very large (301 GB full, 71 GB subset), which may pose storage and processing challenges.

Provenance

Source

DEPICT-RH

Collection Method

Likely collected from medical imaging studies of healthy volunteers.

Freshness

Last updated 2026-07-10 08:30:02; freshness should be verified.