We list the core functions of IDC here. Our overall purpose is to support cancer imaging research on the cloud. While some of the capabilities that are needed for this are outside the scope of IDC, and may necessitate interaction with the other components of the Cancer Research Data Commons, we welcome IDC users to bring up any use cases that are related to using cloud computing for cancer imaging research. We will work with you to identify relevant component of CRDC that can help you.
IDC pilot release took place in Fall 2020. We anticipate the production version of IDC to become available in Spring 2021. You can learn about the planned milestones for the IDC development in these slides presented at RSNA 2019.
Our initial goal is to host all of the public collections from The Cancer Imaging Archive (TCIA). The IDC pilot contains a subset of those collections. The complete up to date list of collections included in IDC is available here.
For a dataset to become part of the IDC offering, it has to be de-identified and curated by TCIA, and released as a public TCIA collection. Once this is done, it will (eventually!) be replicated in IDC.
IDC and TCIA are partners in providing FAIR data for cancer imaging researchers. While some of the functions between the two resources are similar, there are also key differences. The table below provides a summary of similarities and differences.
Source of FAIR data for cancer imaging research
Curation of cancer imaging collections
Cloud-based data co-located with compute resources
Recommended mechanism for downloading data to a local resource
Conversion of pathology images and image-derived data into DICOM format
Cloud-based research use cases
Private data collections
Public data collections
IDC is the right choice for you if you want to...
explore metadata, visualize images and annotations, build cohorts from the data included in public TCIA collections
analyze TCIA public collections data on the cloud
use existing tools such as Google Colab, BigQuery, and DataStudio with the TCIA public collections data
perform complex queries against any of the DICOM attributes in the TCIA public collections
utilize other resources available in CRDC, such as CRDC Cloud Resources, for data analysis
quickly visualize specific images from TCIA public collections
IDC is NOT the right choice for you if you want to...
download data to your computer
upload and share publicly the imaging dataset you collected
de-identify your dataset
Define relevant imaging data cohorts from public datasets (based on rich standardized metadata).
Explore the cohort, check quality (visualize images and image-derived data).
Apply off-the-shelf cloud analytics tools to the cohort:
BigQuery, DataStudio, Colab Notebooks
Further cohort refinement, metadata exploration, analysis
Perform exploratory analysis of data on a cloud VM.
Integrate with other data sources:
Non-imaging data from CRDC (i.e., genomics and proteomics)
Share analysis results and workflows.
The main website for the Cancer Research Data Commons (CRDC) is https://datacommons.cancer.gov/.
At the moment, non-imaging data, such as the spreadsheets with clinical information, is not replicated on IDC and it is not possible to search this data using IDC Portal. You will need to access this data from TCIA.
Our longer-term plan is to work with the CRDC Center for Cancer Data Harmonization (CCDH) to harmonize the data in these spreadsheets, and identify the appropriate format and location for the resulting harmonized data.
Review the summary of what you can do with IDC and what you will need to access specific capabilities. If you want to explore the capabilities of the cloud that require a billing account, and would like to develop a better understanding of the costs before committing your credit card, we have limited resources to support pilot projects exploring the use of IDC in cancer research.