For The University of Alabama at Birmingham
Clinical imaging data, often stored as DICOM files, is the fuel needed to train new machine learning models. But before clinical images can be used, any identifying information must be removed. This process is called DICOM de-identification.
To provide their researchers easier access to clinical images, UAB’s Department of Radiology wanted to streamline its DICOM de-identification process. Their initial process involved manual steps that could be automated—speeding up the process while also avoiding human error.
UAB hired Innolitics to provide a DICOM de-identification solution.
We worked with the Department of Radiology’s vice chair of clinical research to understand UAB’s requirements. They needed a solution that would:
We examined the free DICOM de-identification tools available, and in particular RSNA’s Clinical Trial Processor. No existing tool met all of UAB’s needs, so built a tool using Python and the pydicom library.
The tool is data-driven:
The system provides other useful outputs on a per-project basis:
After developing and testing the tool, we worked directly with UAB’s IT department to install it. We continue to provide support and occasionally implement new feature requests.
The tool has been used successfully on several research projects and has not affected the clinical PACS.