...
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 TCGA-LUAD, TCGA-KIRC, TCGA-LIHC, and TCGA-OV.
A full explanation of the project can be seen in the booth posters:
...
- Source DICOM scans annotated by participants
- RSNA2017CCC-doiJNLP-e8nBWDCC.jnlp (Download Manager software requires Java to launch)
- DICOM metadata and X/Y/Z measurement coordinates
- DICOM-SR representation of crowd measurements
- CrowdsCureCancer-dicomsrfiles_20180830.zip
- CrowdsCureCancerCSV_converttoDICOMSR_20180830.zip
- Note: The conversion XSLT and Makefile depends on pixelmed.jar as a DICOM toolkit,
and dicom3tools, dcsrdump and dciodvfy for validation.
- Note: The conversion XSLT and Makefile depends on pixelmed.jar as a DICOM toolkit,
- TCGA Clinical Data
- ccc2017clinical.csv
- 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.
- ccc2017clinical.csv