Facial Anonymization and Privacy Concerns in Total-Body PET/CT
Aaron Selfridge, Benjamin A. Spencer, Yasser G. Abdelhafez, Keisuke Nakagawa, John D. Tupin, Ramsey D. Badawi
Abstract
Total-body PET/CT images can be rendered to produce images of a subject’s face and body. In response to privacy and identifiability concerns when sharing data, we have developed and validated a workflow that obscures (defaces) a subject’s face in 3-dimensional volumetric data. <b>Methods:</b> To validate our method, we measured facial identifiability before and after defacing images from 30 healthy subjects who were imaged with both [<sup>18</sup>F]FDG PET and CT at either 3 or 6 time points. Briefly, facial embeddings were calculated using Google’s FaceNet, and an analysis of clustering was used to estimate identifiability. <b>Results:</b> Faces rendered from CT images were correctly matched to CT scans at other time points at a rate of 93%, which decreased to 6% after defacing. Faces rendered from PET images were correctly matched to PET images at other time points at a maximum rate of 64% and to CT images at a maximum rate of 50%, both of which decreased to 7% after defacing. We further demonstrated that defaced CT images can be used for attenuation correction during PET reconstruction, introducing a maximum bias of −3.3% in regions of the cerebral cortex nearest the face. <b>Conclusion:</b> We believe that the proposed method provides a baseline of anonymity and discretion when sharing image data online or between institutions and will help to facilitate collaboration and future regulatory compliance.