imaging-data-commons

Query NCI Imaging Data Commons metadata and download selected DICOM series.

4|Updated Mar 2, 2026
One-click install
npx skills add https://github.com/shushuzn/Rairos --skill imaging-data-commons-shushuzn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: imaging-data-commons
Source: https://github.com/shushuzn/Rairos/tree/main/skills/imaging-data-commons
Command: npx skills add https://github.com/shushuzn/Rairos --skill imaging-data-commons-shushuzn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the manual burden of discovering, selecting, and downloading large public cancer imaging cohorts by letting you query IDC metadata and retrieve exactly the series you need.

Core Features & Use Cases

  • Metadata-first discovery: Query IDC by collection, modality, anatomy/body part, manufacturer, patient/study/series identifiers, and derived attributes using the idc-index mini-index.
  • Targeted downloads & reproducible selection: Download selected DICOM series (by collection/series UIDs) and organize outputs with deterministic directory templates and CRDC UUID-versioned file paths.
  • Browser visualization & license checks: Generate viewer links for quick QA before download and inspect licensing fields so you can use data correctly.
  • Use Case: You are building an AI training dataset and need a CC BY CT chest cohort—filter by collection, modality, body part, and license, then download only the matching series and verify via the web viewer.

Quick Start

Use the imaging-data-commons skill to query IDC for CC BY CT chest series from a chosen collection and download the selected DICOM series into a local folder.

Frequently Asked Questions about imaging-data-commons

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download public cancer imaging DICOM cohorts from the NCI Imaging Data Commons?

You can download public cancer imaging DICOM cohorts by querying IDC metadata by collection, modality, or body part, then selecting specific series UIDs for retrieval using the idc-index client without requiring authentication.

Can I filter IDC datasets by license before downloading DICOM series?

Yes, you can filter IDC datasets by license before downloading DICOM series. The skill inspects licensing fields during metadata queries, enabling license-aware dataset selection and ensuring you retrieve only correctly licensed cohorts like CC BY.

How do I generate viewer URLs for DICOM series before downloading?

You generate viewer URLs for DICOM series before downloading by using the skill's optional viewer URL generation feature. This produces browser visualization links for quick QA, letting you verify selected series on the web prior to initiating the download.

Do I need authentication to query and download cancer imaging data from IDC?

No, you do not need authentication to query and download cancer imaging data from IDC. The skill uses the idc-index client for version-aware querying and selection-based downloads, handling license and citation requirements without requiring login credentials.

What is the best way to build an AI training set from public cancer imaging data?

To build an AI training set from public cancer imaging data, query IDC metadata by modality and anatomy, filter by specific licenses, download only the matching DICOM series, and organize outputs using deterministic directory templates with CRDC UUID-versioned file paths.