idc-index

Programmatic access to NCI Imaging Data Commons - the largest public collection of cancer imaging data

What is Imaging Data Commons?

NCI Imaging Data Commons (IDC) is a cloud-based platform providing researchers with free access to a large and growing collection of cancer imaging data. This includes radiology images (CT, MRI, PET), digital pathology slides, and more - all in standard DICOM format with rich clinical and research metadata.

idc-index is the official Python package for querying IDC metadata and downloading imaging data - no cloud credentials or complex setup required.

Features

Query metadata with SQL - Search across ~100TB of data using DuckDB-powered SQL queries
High-speed downloads - Parallel downloads from AWS and Google Cloud public buckets via s5cmd
Browse hierarchically - Navigate collections → patients → studies → series programmatically
Generate viewer URLs - Create links to view images in OHIF (radiology) or Slim (pathology) web viewers
Command line interface - Download data directly from the terminal with idc commands
No authentication required - All data is publicly accessible

Installation

pip install idc-index

Requires Python 3.10+. Downloads are powered by the bundled s5cmd tool.

Keeping Up to Date

The package version is updated with each new IDC data release. Upgrade regularly to access the latest collections and data:

pip install --upgrade idc-index

Quick Start

Explore and Download a Collection

from idc_index import IDCClient

client = IDCClient.client()

# List all available collections
collections = client.get_collections()
print(f"IDC has {len(collections)} collections")

# Download a small collection (10.5 GB)
client.download_from_selection(collection_id="rider_pilot", downloadDir="./data")

Query with SQL

Find CT scans of the chest and download them:

from idc_index import IDCClient

client = IDCClient.client()

query = """
SELECT
    collection_id,
    PatientID,
    SeriesInstanceUID,
    SeriesDescription,
    series_size_MB
FROM index
WHERE Modality = 'CT'
  AND BodyPartExamined = 'CHEST'
LIMIT 10
"""

results = client.sql_query(query)
print(results)

# Download the matching series
client.download_dicom_series(
    seriesInstanceUID=results["SeriesInstanceUID"].tolist(), downloadDir="./chest_ct"
)

Browse Data Hierarchy and View Images

Navigate from collection to viewable images:

from idc_index import IDCClient

client = IDCClient.client()

# Get patients in a collection
patients = client.get_patients("tcga_luad", outputFormat="list")
print(f"Found {len(patients)} patients")

# Get studies for a patient
studies = client.get_dicom_studies(patients[0])

# Get series in that study
series = client.get_dicom_series(studies[0]["StudyInstanceUID"])

# Generate a viewer URL
viewer_url = client.get_viewer_URL(seriesInstanceUID=series[0]["SeriesInstanceUID"])
print(f"View in browser: {viewer_url}")

Command Line Interface

Download data directly from the terminal using idc download, which auto-detects the input type:

# Download a collection
idc download rider_pilot

# Download a specific series by UID
idc download 1.3.6.1.4.1.14519.5.2.1.6279.6001.100225287222365663678666836860

# Download from a manifest file
idc download manifest.s5cmd

# Specify output directory
idc download rider_pilot --download-dir ./data

# See all options
idc --help

Documentation

Full Documentation - API reference and guides
Tutorial Notebook - Interactive introduction to idc-index

Resources

IDC Portal - Browse IDC data in your web browser
IDC Forum - Community discussions and support
idc-claude-skill - Claude AI skill for querying IDC with natural language
SlicerIDCBrowser - 3D Slicer extension using idc-index
s5cmd - The high-performance S3 client powering downloads

Citation

If idc-index helps your research, please cite:

Fedorov, A., Longabaugh, W. J. R., Pot, D., Clunie, D. A., Pieper, S. D., Gibbs, D. L., Bridge, C., Herrmann, M. D., Homeyer, A., Lewis, R., Aerts, H. J. W., Krishnaswamy, D., Thiriveedhi, V. K., Ciausu, C., Schacherer, D. P., Bontempi, D., Pihl, T., Wagner, U., Farahani, K., Kim, E. & Kikinis, R. National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence. RadioGraphics (2023). https://doi.org/10.1148/rg.230180

Acknowledgment

This software is maintained by the IDC team, which has been funded in whole or in part with Federal funds from the NCI, NIH, under task order no. HHSN26110071 under contract no. HHSN261201500003I.

Metadata

Release files for idc-index 0.13.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for idc-index 0.13.0
File	Size	Uploaded
idc_index-0.13.0.tar.gz	61.5 kB	Oct 7, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for idc-index 0.13.0
File	Interpreter	ABI	Platform	Reset
idc_index-0.13.0-py3-none-any.whl 29.7 kB Oct 7, 2026	Python 3	none	any	Details

Total release size: 91.2 kB

Release files / idc_index-0.13.0.tar.gz

Download URL	idc_index-0.13.0.tar.gz
Size	61.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`641c856d982b4b3a4b11a4970a94ef800ea0ab49bfc52c96f265f917e0862770`
BLAKE2b-256 checksum How to use checksums	`c97255a1f0d6dfb8783960b6cbda4fc80de138d76ab87ce74a388ad65cc7b82e`
Upload date	Oct 7, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/ImagingDataCommons/idc-index
Publishing commit: github.com/ImagingDataCommons/idc-index/tree/6ec7b2db64404f67acc2f9a75882a5ec4c193d3b

Workflow

Publishing configuration: github.com/ImagingDataCommons/idc-index/blob/6ec7b2db64404f67acc2f9a75882a5ec4c193d3b/.github/workflows/cd.yml
Publishing logs: github.com/ImagingDataCommons/idc-index/actions/runs/37700934206/attempts/1

Artifact

Subject: idc_index-0.13.0.tar.gz
SHA-256 checksum: 641c856d982b4b3a4b11a4970a94ef800ea0ab49bfc52c96f265f917e0862770 Verifying attestations

Release files / idc_index-0.13.0-py3-none-any.whl

Download URL	idc_index-0.13.0-py3-none-any.whl
Size	29.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`45e7fdbc6d04f8abda31e39679e342ac15ad5ec510835b3230cc802cc41cd1da`
BLAKE2b-256 checksum How to use checksums	`c2c7b0fe5f131f2581cb711b4a8a440d409264207c4d25c34eb433fa9ff7bfcb`
Upload date	Oct 7, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/ImagingDataCommons/idc-index
Publishing commit: github.com/ImagingDataCommons/idc-index/tree/6ec7b2db64404f67acc2f9a75882a5ec4c193d3b

Workflow

Publishing configuration: github.com/ImagingDataCommons/idc-index/blob/6ec7b2db64404f67acc2f9a75882a5ec4c193d3b/.github/workflows/cd.yml
Publishing logs: github.com/ImagingDataCommons/idc-index/actions/runs/37700934206/attempts/1

Artifact

Subject: idc_index-0.13.0-py3-none-any.whl
SHA-256 checksum: 45e7fdbc6d04f8abda31e39679e342ac15ad5ec510835b3230cc802cc41cd1da Verifying attestations