@article{5fda9af188134b249a604593a76e3890,
title = "Changing the face of neuroimaging research: Comparing a new MRI de-facing technique with popular alternatives",
abstract = "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.",
keywords = "Anonymization, De-Facing, De-Identification, Face Recognition, Reliability",
author = "{The Alzheimer's Disease Neuroimaging Initiative} and Schwarz, {Christopher G.} and Kremers, {Walter K.} and Wiste, {Heather J.} and Gunter, {Jeffrey L.} and Prashanthi Vemuri and Spychalla, {Anthony J.} and Kejal Kantarci and Schultz, {Aaron P.} and Sperling, {Reisa A.} and Knopman, {David S.} and Petersen, {Ronald C.} and Jack, {Clifford R.}",
note = "Funding Information: The authors give their thanks to all the volunteers, participants, and coordinators who contributed to this research, with special thanks to Steven M. Smith, Josie M. Williams, Paul D. Lewis, Steven J. Demuth, Soudabeh Kargar, and Zuzana Nedelska. Thank you to Stephen Weigand for statistical advice. We gratefully thank our funding sources: NIH grants R56 AG068206, U01 AG006786, P50 AG016574, R01 AG034676, R37 AG011378, R01 AG041851, R01 NS097495, R01 AG056366, U01 NS100620; The GHR Foundation; The Elsie and Marvin Dekelboum Family Foundation; The Alexander Family Alzheimer's Disease Research Professorship of the Mayo Clinic; The Liston Award; The Schuler Foundation; and The Mayo Foundation for Medical Education and Research. We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Quadro P6000 GPU used in generating 3D facial reconstructions for this research. Funding Information: Dr. Schwarz receives funding from the National Institutes of Health, related and unrelated to this study, and has a related US patent pending. Funding Information: The authors give their thanks to all the volunteers, participants, and coordinators who contributed to this research, with special thanks to Steven M. Smith, Josie M. Williams, Paul D. Lewis, Steven J. Demuth, Soudabeh Kargar, and Zuzana Nedelska. Thank you to Stephen Weigand for statistical advice. We gratefully thank our funding sources: NIH grants R56 AG068206, U01 AG006786, P50 AG016574, R01 AG034676, R37 AG011378, R01 AG041851, R01 NS097495, R01 AG056366, U01 NS100620; The GHR Foundation; The Elsie and Marvin Dekelboum Family Foundation; The Alexander Family Alzheimer's Disease Research Professorship of the Mayo Clinic; The Liston Award; The Schuler Foundation; and The Mayo Foundation for Medical Education and Research. We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Quadro P6000 GPU used in generating 3D facial reconstructions for this research. ICC and bias calculations for every regional measurement from each pipeline are provided in supplementary material. ADNI images are available directly through ADNI (http://adni.loni.usc.edu/). The face recognition data-set contains participant photos, which are considered primary identifiers; to protect participant privacy and comply with the IRB and consent forms, these data cannot be shared. MRI and other data from the Mayo Clinic Study of Aging and the Alzheimer's Disease Research Center are available to qualified academic and industry researchers by request to the Mayo Clinic Study of Aging/Alzheimer's Disease Research Center Executive Committee. Our mri_reface software is still in development, but it will be provided to qualified researchers by request and will later be released as free for non-commercial research use. The mri_deface, pydeface, and fsl_deface de-face software are each available from their respective authors. Microsoft Azure face recognition is a proprietary cloud-based service by Microsoft. Disclosure Statements, Dr. Schwarz receives funding from the National Institutes of Health, related and unrelated to this study, and has a related US patent pending. Dr. Kremers received grant funding from NIH for this study, and from NIH, DOD, AstraZeneca, Biogen and Roche unrelated to this study. Ms. Wiste reports no disclosures. Dr. Gunter receives funding from the NIH, and has a related US patent pending. Dr. Vemuri receives funding from the NIH. Mr. Spychalla reports no disclosures. Dr. Kantarci serves on the data safety monitoring board for Takeda Global Research and Development Center, Inc.; data monitoring boards of Pfizer and Janssen Alzheimer Immunotherapy; and receives research support from Avid Radiopharmaceuticals and Eli Lilly, the Alzheimer's Drug Discovery Foundation, and NIH. Dr. Schultz reports no disclosures. Dr. Sperling has received research funding from NIH, Alzheimer's Association, GHR Foundation, Eli Lilly, Janssen, and Eisai. She has served as a consultant for AC Immune, Acumen, Cytox, Janssen, Neurocentria, Prothena, Renew. Dr. Knopman served on a Data Safety Monitoring Board for the DIAN study. He serves on a Data Safety monitoring Board for a tau therapeutic for Biogen, but receives no personal compensation. He is an investigator in clinical trials sponsored by Biogen, Lilly Pharmaceuticals and the University of Southern California. He serves as a consultant for Samus Therapeutics, Third Rock and Alzeca Biosciences but receives no personal compensation. He receives research support from the NIH. Dr. Petersen serves on scientific advisory boards for Elan Pharmaceuticals, Wyeth Pharmaceuticals, and GE Healthcare; receives royalties from publishing Mild Cognitive Impairment (Oxford University Press, 2003); and receives research support from NIH. Dr. Jack serves on an independent data monitoring board for Roche and has consulted for Eisai, but he receives no personal compensation from any commercial entity. He receives research support from NIH and the Alexander Family Alzheimer's Disease Research Professorship of the Mayo Clinic and has a related US patent pending. Funding Information: Dr. Kantarci serves on the data safety monitoring board for Takeda Global Research and Development Center, Inc.; data monitoring boards of Pfizer and Janssen Alzheimer Immunotherapy; and receives research support from Avid Radiopharmaceuticals and Eli Lilly, the Alzheimer's Drug Discovery Foundation, and NIH. Publisher Copyright: {\textcopyright} 2021 The Author(s)",
year = "2021",
month = may,
day = "1",
doi = "10.1016/j.neuroimage.2021.117845",
language = "English (US)",
volume = "231",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
}