De-Identification of Radiomics Data Retaining Longitudinal Temporal Information

Abstract

We propose a de-identification system which runs in a standalone mode. The system takes care of the de-identification of radiation oncology patient’s clinical and annotated imaging data including RTSTRUCT, RTPLAN, and RTDOSE. The clinical data consists of diagnosis, stages, outcome, and treatment information of the patient. The imaging data could be the diagnostic, therapy planning, and verification images. Archival of the longitudinal radiation oncology verification images like cone beam CT scans along with the initial imaging and clinical data are preserved in the process. During the de-identification, the system keeps the reference of original data identity in encrypted form. These could be useful for the re-identification if necessary.

Appendix

Table 2 Selected DICOM tags for de-identification

Table 3 Patient PHI data de-identification with different tools [22]

Algorithm

Study date = s, Random date = r, Difference between original date and random date = d, Original Date = date, Treatment reference date = TRD;

$$ TotalDay = \sum\limits_{i=1}^{month-1} \frac{day*(day+1)}{2} + \sum\limits_{j=1}^{day} j $$

(1)

d = s-r or d= date-r; TRD day = TotalDay + d; TRD = ConvertToDate(TRD day);