Many Cancers routinely identified by imaging haven’t yet benefited from recent advances in computer science. Approaches such as machine learning and deep learning can generate quantitative tumor 3D volumes, complex features and therapy-tracking temporal dynamics. However, cross-disciplinary researchers striving to develop new approaches often lack disease understanding or sufficient contacts within the medical community. Their research can greatly benefit from labeling and annotating basic information in the images such as tumor locations, which are obvious to radiologists.
Crowd-sourcing the creation of publicly-accessible reference data sets could address this challenge. In 2011 the National Cancer Institute funded development of The Cancer Imaging Archive (TCIA), a free and open-access database of medical images. However, most of these collections lack the labeling and annotations needed by image processing researchers for progress in deep learning and radiomics. As a result, TCIA has partnered with the Radiological Society of North America (RSNA) and numerous academic centers to harness the vast knowledge of RSNA meeting attendees to generate these tumor markups. Data sets annotated included CT scans from 352 subjects from the The Cancer Genome Atlas Lung Adenocarcinoma Collection (TCGA-LUAD), The Cancer Genome Atlas Kidney Renal Clear Cell Carcinoma Collection (TCGA-KIRC), The Cancer Genome Atlas Liver Hepatocellular Carcinoma Collection (TCGA-LIHC), and The Cancer Genome Atlas Ovarian Cancer Collection (TCGA-OV) collections on TCIA.
A full explanation of the project can be seen in the Detailed Description tab.
|Data Type||Download all or Query/Filter||License|
|Image Annotations (CSV, 925 kb)|
|DICOM-SR files see note (ZIP, 3.7 Mb)|
|Clinical Data snapshot see note (CSV, 53kb)|
Collections Used in this Third Party Analysis
Below is a list of the Collections used in these analyses:
|Source Data Type||Download all or Query/Filter||License|
|Corresponding original source Images from TCGA-LUAD, TCGA-KIRC, TCGA-LIHC, TCGA-OV (DICOM, 24.2 GB)|
- DICOM-SR note: The conversion XSLT and Makefile depends on pixelmed.jar as a DICOM toolkit, and dicom3tools, dcsrdump and dciodvfy for validation.
- Clinical data note: Because all subjects were pulled from The Cancer Genome Atlas cohorts, clinical data was available through the NCI Genomic Data Commons. A CSV dump of that data is provided here for convenience.
Citations & Data Usage Policy
Users of this data must abide by the TCIA Data Usage Policy and the Creative Commons Attribution 3.0 Unported License under which it has been published. Attribution should include references to the following citations:
Other Publications Using This Data
Version 1 (Current): 2018/05/17
|Data Type||Download all or Query/Filter|
|Images (DICOM, 24.2 GB)|
|Image Annotations (CSV)|
|DICOM-SR files (ZIP) *|
|Clinical Data (CSV) **|
* The conversion XSLT and Makefile depends on pixelmed.jar as a DICOM toolkit, and dicom3tools, dcsrdump and dciodvfy for validation.
** Because all subjects were pulled from The Cancer Genome Atlas cohorts, clinical data was available through the NCI Genomic Data Commons. A CSV dump of that data is provided here for convenience.