Unmasking a Privacy Concern: Potential Identification of Patients in an Immobilization Mask from 3D Reconstructions of Simulation CTs.

Abstract Background Previous studies have demonstrated that patients can be identified from 3D reconstructions of CT or MRI data of the brain or head and neck. This presents a privacy and security concern for scan data released to public datasets. It is unknown if thermoplastic immobilization masks used for treatment planning in radiation therapy are sufficient to prevent facial recognition. Our study sought to evaluate if patients with an immobilization mask could be identified on 3D reconstructions of scan data. Methods Our study reconstructed 3D images from simulation CT (SIM-CT) scans of 35 patients and compared these to original patient photographs to test if the thermoplastic mask obfuscated facial features. Blind review from 4 facial recognition algorithms and a human (radiation oncologist) was evaluated for the ability to match 3D reconstructions of patients scans to patient images. The matching procedure was repeated against an expanded testing dataset of the 35 patient photographs plus 13,233 facial photographs from the “Labeled Faces in the Wild” dataset. (13,268 photographs in total) Results Facial Recognition algorithms were able to match a maximum of 83% (range, 60%-83%) of patients to the corresponding images. Radiation Oncologist blinded review correctly matched 80% of patients to the corresponding images. Ethnicity and facial hair were the most common reasons for patient mismatch. In the expanded testing dataset, algorithms were also able to match a maximum of 83% (range, 57-83%) of patients. Conclusion The majority of patients were able to be identified through computer algorithm or human review even under a SIM-CT mask. These results suggest there is a potential privacy and security concern when SIM-CT data are released to publicly available datasets.