In partnership with Leidos Biomedical and the National Cancer Institute (NCI), in 2019 we developed a process for integrating radiology images into a data commons. This project was part of the NCI Data Integration and Imaging Informatics (DI-Cubed) Project, an effort to convert data from various clinical studies into a standardized format and to demonstrate how this standardization can enable data from multiple studies and domains to be combined, creating larger and more useful cohort sizes and making it possible to share data more easily between institutions.
Our Role
Our contribution to the DI-Cubed Project tested the feasibility of linking image data to clinical data in a commons environment and serving this information to researchers in real time, with the INRG Data Commons serving as the paradigm system. In this pilot study, we explored extending the functionality of the INRG Data Commons by integrating MIBG scans, one of the most important imaging modalities for neuroblastoma patients.
We partnered with Children’s Oncology Group to obtain de-identified MIBG images and associated reports, which we stored locally on secure, HIPAA-compliant infrastructure provided by the University of Chicago Center for Research Informatics. Images are stored and indexed in a locally-maintained instance of the National Biomedical Imaging Archive (NBIA) platform. We then linked the images to patients in the INRG database through the use of a shared anonymized identifier.
In addition to incorporating select radiology images into the INRG Data Commons, this pilot project enabled us to make valuable recommendations to the NCI for expanding this type of work in the future.