Changing the face of neuroimaging research: Comparing a new MRI de-facing technique with popular alternatives.


Schwarz CG(1), Kremers WK(2), Wiste HJ(2), Gunter JL(3), Vemuri P(4), Spychalla AJ(4), Kantarci K(4), Schultz AP(5), Sperling RA(5), Knopman DS(6), Petersen RC(6), Jack CR Jr(4); Alzheimer's Disease Neuroimaging Initiative.
Author information:
(1)Department of Radiology, Mayo Clinic, Rochester, MN, United States. Electronic address: [Email]
(2)Department of Health Sciences Research, Mayo Clinic, Rochester, MN, United States.
(3)Department of Radiology, Mayo Clinic, Rochester, MN, United States; Department of Information Technology, Mayo Clinic, Rochester, MN, United States.
(4)Department of Radiology, Mayo Clinic, Rochester, MN, United States.
(5)Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.
(6)Department of Neurology, Mayo Clinic, Rochester, MN, United States.


Recent advances in automated face recognition algorithms have increased the risk that de-identified research MRI scans may be re-identifiable by matching them to identified photographs using face recognition. A variety of software exist to de-face (remove faces from) MRI, but their ability to prevent face recognition has never been measured and their image modifications can alter automated brain measurements. In this study, we compared three popular de-facing techniques and introduce our mri_reface technique designed to minimize effects on brain measurements by replacing the face with a population average, rather than removing it. For each technique, we measured 1) how well it prevented automated face recognition (i.e. effects on exceptionally-motivated individuals) and 2) how it altered brain measurements from SPM12, FreeSurfer, and FSL (i.e. effects on the average user of de-identified data). Before de-facing, 97% of scans from a sample of 157 volunteers were correctly matched to photographs using automated face recognition. After de-facing with popular software, 28-38% of scans still retained enough data for successful automated face matching. Our proposed mri_reface had similar performance with the best existing method (fsl_deface) at preventing face recognition (28-30%) and it had the smallest effects on brain measurements in more pipelines than any other, but these differences were modest.