Each Collection TCIA publishes is issued a Digital Object Identifier (DOI) through DataCite.  The DataCite Commons is a web search interface for the PID Graph, the graph formed by the collection of scholarly resources such as publications, datasets, people and research organizations, and their connections. 

The DataCite REST API can be used to programmatically access Collection metadata such as their DOIs, titles and abstracts.  Please note that this API was not developed by TCIA. See https://support.datacite.org/ for any technical questions.  The TCIA Helpdesk may be able to assist if your inquiry is related to the content of the data itself.

Official Datacite Documentation

TCIA Metadata in DataCite

TCIA utilizes the following Properties of the DataCite schema.

Property IDProperty Property Description
Identifier DOI of the Dataset
Creator Authors of the Dataset, preferably with ORCIDID
Title  Published Title of the Dataset
Publisher The Cancer Imaging Archive
PublicationYear The Year the Dataset was published in TCIA
10 ResourceType  Dataset; Equivalent to a TCIA Collection
11 *AlternateIdentifier TCIA "Short Name" for the Dataset.  These short names appear in various places such as https://www.cancerimagingarchive.net/collections/ and https://www.cancerimagingarchive.net/tcia-analysis-results/
15 *Version The Current Version of the Dataset
16 *Rights Licensing Information
17 *Description Dataset Abstract

* indicates properties that are "Recommended and Optional" per the Datacite Schema whereas the others are required to create a DOI.


The tcia_utils package contains functions to simplify common tasks one might perform when interacting with The Cancer Imaging Archive (TCIA) via Python.  Issues with this package should be submitted at https://github.com/kirbyju/tcia_utils/issuesInstallation can be achieved with this Pip command:

pip install tcia_utils

To import functions related to Datacite:

from tcia_utils import datacite

An example notebook demonstrating tcia_utils functionality with DataCite's API can be found at https://github.com/kirbyju/TCIA_Notebooks/blob/main/TCIA_DataCite_Queries.ipynb. 

Example Queries

Retrieve a single DataCite record in JSON format.

For this example we are using a Published Collection called "Pseudo-PHI-DICOM-Data":


Return a list of DOIs using the TCIA provider id (tciar)


By default, only 25 records are returned. You can control the number of records returned using pagination options. For example, to return only 5 records




Query on specific information populated in the DataCite schema

Use the "activities" endpoint to see metadata updates in JSON format for a specified DataCite record.

For this example we are using a Published Collection called "Pseudo-PHI-DICOM-Data":


  • No labels