AI skill for querying and downloading public cancer imaging data from the National Cancer Institute's Imaging Data Commons. Benefits researchers and healthcare professionals by automating data retrieval for analysis and study.
git clone https://github.com/ImagingDataCommons/idc-claude-skill.gitThe IDC Claude Skill enables researchers and healthcare professionals to programmatically access public cancer imaging datasets from the National Cancer Institute's Imaging Data Commons. The skill allows you to search imaging data by cancer type, imaging modality (CT, MR, PET), and anatomy, then generate download commands and citations automatically. It provides links to DICOM viewers for data preview and answers questions about IDC data structure and metadata. This automation reduces manual data retrieval work and helps ensure proper licensing and attribution of datasets used in research and analysis.
Load the skill in Claude Desktop or via the API using the setup instructions in USAGE.md. Once loaded, ask questions like 'Find CT scans of lung cancer in IDC' or 'How do I download all breast MRI data with commercial-use licenses?' The skill requires the idc-index Python package.
Find and download CT scans of specific cancer types for research analysis
Retrieve breast MRI datasets with commercial-use licenses
Generate proper citations for IDC collections in publications
Preview DICOM imaging data before downloading full datasets
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/ImagingDataCommons/idc-claude-skillCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Retrieve the latest imaging datasets from the National Cancer Institute's Imaging Data Commons for [COMPANY] focusing on [CANCER_TYPE] research. Provide a summary of the datasets including collection dates, imaging modalities, and patient demographics. Download the top 3 most relevant datasets for [INDUSTRY] analysis.
# Imaging Data Summary for Breast Cancer Research ## Top 3 Datasets 1. **TCIA-BRCA-01** - Collection Date: 2020-2022 - Imaging Modalities: MRI, CT - Patient Demographics: 500 female patients, age range 30-75 - Relevance: High relevance for breast cancer screening and diagnosis 2. **TCIA-BRCA-02** - Collection Date: 2018-2020 - Imaging Modalities: Mammography, Ultrasound - Patient Demographics: 300 female patients, age range 40-80 - Relevance: Moderate relevance for breast cancer detection and monitoring 3. **TCIA-BRCA-03** - Collection Date: 2015-2017 - Imaging Modalities: PET, MRI - Patient Demographics: 200 female patients, age range 25-65 - Relevance: Low relevance for breast cancer research due to older data ## Download Links - [TCIA-BRCA-01 Dataset](https://example.com/dataset1) - [TCIA-BRCA-02 Dataset](https://example.com/dataset2) - [TCIA-BRCA-03 Dataset](https://example.com/dataset3)
Automate your browser workflows effortlessly
AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan