SIIM 2007 - Imaging Informatics Research:
caBIG Imaging Workspace Demonstration

There are unique requirements and challenges for the research and clinical trials communities in medical imaging informatics. Some of the most exciting, innovative, and far-reaching projects are currently being funded or considered by a project known as the caBIG Imaging Workspace of the National Cancer Institute (NCI). These will likely have a major impact on all of us who are involved in medical imaging informatics and indeed in the field of diagnostic imaging.

caBIG refers to the National Institutes of Health (NIH)’s National Cancer Institute Cancer Biomedical Informatics Grid, a project designed to use grid computing to interconnect the approximately 50 clinical cancer centers throughout the country together using protocols, standards, and commonly adopted free and open source software. The ultimate purpose of the project is to achieve a level of online access to patient data that would permit physicians to personalize care of a cancer patient based not only on the literature written for a given disease but also on that patient’s unique DNA make-up, tumor DNA and proteomic data, patient pharmacokinetic data and of course, patient anatomic and functional imaging data.

The workspace, which includes informatics experts from across the country in multiple subspecialty areas, currently has multiple simultaneous projects.  The following and more will be highlighted at this demonstration, which will be ongoing throughout the meeting.

1.  XIP – Extensible Imaging Platform: A free and open source platform that facilitates the sharing not of images and other patient data but of image display, processing, and analysis algorithms themselves.
2.  GridCAD and Virtual PACS: Grid computing has received surprisingly little attention in diagnostic imaging despite its tremendous potential to promote interoperability, improve security, and support more efficient sharing of image data and software algorithms. These projects demonstrate the use of the GRID to support multiple concurrent machine and human lung nodule detectors and the potential use of grid computing to tie together multiple disparate imaging systems into a single virtual PACS.
3.  The Annotation and Image Markup and Query Formulation Projects: The first project of its kind that we’re aware of to propose/create a “standard” means of adding information/knowledge to an image in a clinical environment in which there is currently chaos in order to create a future in which image content can be easily and automatically searched.
4.  The RadLex Research Playbook: A project performed in concert with the RSNA’s RadLex effort to create a means of describing image acquisition devices and protocols in a unified fashion that is not vendor proprietary.