NCI Imaging Data Commons

Area of Science:

• Oncology
• Medical Informatics
• Bioinformatics

Background:

• The National Cancer Institute (NCI) is developing the Cancer Research Data Commons (CRDC) as a national cloud-based data science infrastructure.
• The Imaging Data Commons (IDC) is a new component of the CRDC, funded by the Cancer Moonshot initiative.

Purpose of the Study:

• To provide cancer researchers, regardless of imaging expertise, with accessible deidentified imaging data.
• To facilitate integrated analyses of imaging and non-imaging cancer data.
• To support cloud-based cancer imaging research through a data commons framework.

Main Methods:

• Colocating diverse imaging collections with cloud computing resources.
• Integrating data exploration, visualization, and analysis tools.
• Populating the IDC with radiology and histopathology collections since its pilot release in October 2020.

Main Results:

• The IDC pilot was launched in October 2020 and is continuously updated with imaging data.
• The IDC offers curated imaging collections, documentation, a user forum, and analysis use cases.
• The framework demonstrates the value of a data commons for cancer imaging research.

Conclusions:

• The NCI Imaging Data Commons is a significant new repository within the CRDC.
• The IDC will enhance cancer imaging research by providing cloud-based data access and analysis tools.
• This initiative supports integrated data science approaches in oncology research.