Data Descriptor: The public cancer radiology imaging collections of The Cancer Imaging Archive

The Cancer Imaging Archive (TCIA) is the U.S. National Cancer Institute's repository for cancer imaging and related information. TCIA contains 30.9 million radiology images representing data collected from approximately 37,568 subjects. This data is organized into collections by tumor-type with many collections also including analytic results or clinical data. TCIA staff carefully de-identify and curate all incoming collections prior to making the information available via web browser or programmatic interfaces. Each published collection within TCIA is assigned a Digital Object Identifier that references the collection. Additionally, researchers who use TCIA data may publish the subset of information used in their analysis by requesting a TCIA generated Digital Object Identifier. This data descriptor is a review of a selected subset of existing publicly available TCIA collections. It outlines the curation and publication methods employed by TCIA and makes available 15 collections of cancer imaging data.