To observe and diagnose cancer in modern times, medical professionals rely heavily on imaging instruments, such as CT and MR. The images generated by these instruments have been standardized into a digital file format to contain all the relevant information. The Digital Imaging and Communications in Medicine (DICOM) Standard was the result, which dictates proper handling, storing, printing and transmitting of medical imaging information. It contains a file format definition and a network communications protocol. The DICOM file (.dcm) carries with it both pixel data to generate an image, as well as important information regarding the patient and the imaging procedure. This information allows an individual's electronic health record to easily be maintained and updated. However, some of this information, referred to as protected health information (PHI), is legally protected from all but the patient or attending healthcare professional. This means that researchers must find a way to detach the image from the individual while still retaining important information for research.

The DICOM De-Identifier aims to accomplish just that; to remove all recognized PHIs from a DICOM file while still allowing the researcher to access the relevant data. The process is currently being done by hand; therefore, this program will offer an affordable solution for faster and more streamlined de-identification, ultimately allowing larger data sets to be used. It will also be designed such that any health researcher will be able to use it, adjusting the level of de-identification as they require, and due to the generality of DICOM, it can be used for any imaging modality.