Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

on behalf of the MAGNIMS Study Group and Alzheimer’s Disease Neuroimaging Initiative

doi:10.1007/s00330-019-06459-3

Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

on behalf of the MAGNIMS Study Group and Alzheimer’s Disease Neuroimaging Initiative

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

Background: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants’ privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups. Methods: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer’s Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests. Results: Automated analysis methods failed in 0–19% of cases in FFR-processed images versus 0–2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001). Conclusions: All three outcome measures were affected differently by FFR, including failure of analysis methods and both “random” variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants’ privacy. Key Points: • Protecting participants’ privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.

Original language	English
Pages (from-to)	1062-1074
Number of pages	13
Journal	European Radiology
Volume	30
Issue number	2
Early online date	5 Nov 2019
DOIs	https://doi.org/10.1007/s00330-019-06459-3
Publication status	Published - Feb 2020

Funding

The authors of this manuscript declare relationships with the following companies: A. de Sitter is employed on a project sponsored by a research grant from Teva Pharmaceuticals (grant to H. Vrenken and F. Barkhof). M. Visser has nothing to disclose. I. Brouwer is partly employed on a project sponsored by a research grant from Teva Pharmaceuticals (grant to H. Vrenken and F. Barkhof) and is partly employed on a project sponsored by a research grant from Novartis (grant to H. Vrenken and F. Barkhof). K.S. Cover has nothing to disclose. R.A. van Schijndel has nothing to disclose. R.S. Eijgelaar has nothing to disclose. D.M.J. Müller has nothing to disclose. S. Ropele has nothing to disclose. L. Kappos has served in the last 24 months as international or local principal investigator for the following drug studies: BOLD EXT., EXPAND (Siponimod, Novartis), DECIDE, DECIDE EXT. (Daclizumab HYP, Biogen), ENDORSE (DMF, Biogen), FINGORETT, FTY-UMBRELLA, INFORMS, INFORMS EXT LONGTERMS. (Fingolimod, Novartis), MOMENTUM (Amiselimod, Mitsubishi) OCRELIZUMAB PHASE II EXT., OPERA, ORATORIO and extensions (Ocrelizumab, Roche), REFLEXION (IFN β-1a, Merck), STRATA EXT, TOP (Natalizumab, Biogen), TERIFLUNOMIDE EXT, TERRIKIDS (Teriflunomide, Sanofi-Aventis), and ASCLEPIOS I/II (Ofatumumab, Novartis). L. Kappos is a member in the Editorial Boards of the following journals: “ Journal of Neurology ”, “ Multiple Sclerosis Journal ”, “ Neurology and Clinical Neuroscience “, “ Multiple Sclerosis and Related Disorders ”, “ Clinical and Translational Neuroscience ”. Á. Rovira serves on scientific advisory boards for Novartis, Sanofi-Genzyme, Icometrix, SyntheticMR, Bayer, Biogen, and OLEA Medical, and has received speaker honoraria from Bayer, Sanofi-Genzyme, Bracco, Merck Serono, Teva Pharmaceutical Industries Ltd., Novartis, Roche, and Biogen. M. Filippi received speaker honoraria from Biogen Idec, Novartis, Genzyme, Sanofi-Aventis, Teva, Merck Serono, and Roche and receives research support from the Italian Ministry of Health and Fondazione Italiana Sclerosi Multipla. C. Enzinger declares no conflict of interest. J. Frederiksen has received no funding to support the presented work. She has served on scientific advisory boards for and received funding for travel related to these activities as well as honoraria from Biogen Idec, Merck Serono, Sanofi-Aventis, Teva, Novartis, and Almirall. She has received speaker honoraria from Biogen Idec, Teva, and Novartis. She has served as advisor on preclinical development for Takeda. O. Ciccarelli has received research grants from the MS Society of Great Britain & Northern Ireland, National Institute for Health Research (NIHR) University College London Hospitals Biomedical Research Centre, EUH2020, Spinal Cord Research Foundation, and Rosetrees Trust. Professor Ciccarelli serves as a consultant for Novartis, Teva, and Roche and has received an honorarium from the AAN as Associate Editor of Neurology and serves on the Editorial Board of Multiple Sclerosis Journal . C.R.G. Guttmann has received research grants form Sanofi and the National Multiple Sclerosis Society. M.P. Wattjes has received speaker and/or consultancy fees from Biogen, Biologix, Bayer Healthcare, Celgene, Genilac, IXICO, Novartis, Merck Serono, Sanofi-Genzyme, Springer Healthcare, and Roche. M.G. Witte has nothing to disclose. P.C. de Witt Hamer has nothing to disclose. F. Barkhof has received compensation for consulting services and/or speaking activities from Bayer Schering Pharma, Biogen Idec, Merck Serono, Novartis, Genzyme, Synthon BV, Roche, Teva, Jansen research and IXICO and is supported by the NIHR Biomedical Research Centre at UCLH. H. Vrenken has received research grants from Novartis, Teva, Merck Serono, and Pfizer; consulting fees from Merck Serono; and speaker honoraria from Novartis; all funds were paid directly to his institution. The PICTURE project is supported by the program Innovative Medical Devices Initiative (IMDI) with project number 10-10400-96-14003, which is financed by the Netherlands Organization for Scientific Research (NWO). This research is also supported by a research grant from the Dutch Cancer Society (VU2014-7113). The MS Center Amsterdam is supported by the Dutch MS Research Foundation through program grants (09-358d and 14-358e). Frederik Barkhof and Olga Ciccarelli were supported by the NIHR Biomedical Research Centre at UCLH. Part of the data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database ( adni.loni.usc.edu ). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd. and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( www.fnih.org ). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. MAGNIMS Study Group; MAGNIMS (Magnetic Resonance Imaging in MS) Study Group is a European study group of academics that share the interest in MS and imaging. We want to thank Bob van Hoek that we could use the MR image of his head for the 3D render figure (Fig. 1 ). Part of the data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd. and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. MAGNIMS Study Group; MAGNIMS (Magnetic Resonance Imaging in MS) Study Group is a European study group of academics that share the interest in MS and imaging. We want to thank Bob van Hoek that we could use the MR image of his head for the 3D render figure (Fig. 1).

Funders	Funder number
ADNI clinical sites in Canada
Alzheimer’s Association
Alzheimer’s Drug Discovery Foundation
Araclon Biotech
CereSpir, Inc.
Cogstate
Cord Research Foundation
DOD ADNI
Dutch Cancer Society	VU2014-7113
Dutch MS Research Foundation	09-358d, 14-358e
Elan Pharmaceuticals, Inc.
Euroimmun
IXICO Ltd.
Janssen Alzheimer Immunotherapy Research & Development, LLC.
Lumosity
Merck Serono
Meso Scale Diagnostics, LLC.
Netherlands Organization for Scientific Research
NeuroRx Research
Neurotrack Technologies
Piramal Imaging
TEVA
Teva Pharmaceuticals
Transition Therapeutics
National Institutes of Health
U.S. Department of Defense	W81XWH-12-2-0012
Foundation for the National Institutes of Health
National Institute on Aging	U01AG024904
National Institute of Biomedical Imaging and Bioengineering
National Multiple Sclerosis Society
Bristol-Myers Squibb
Eli Lilly and Company
Pfizer
Genentech
Genzyme
Merck
Novartis
Roche
Sanofi
Biogen
University of Southern California
Biogen IDEC
AbbVie
GE Healthcare
F. Hoffmann-La Roche
Alzheimer's Disease Neuroimaging Initiative
Fondazione Italiana Sclerosi Multipla
BioClinica
Novartis Pharmaceuticals Corporation
Takeda Pharmaceutical Company
Northern California Institute for Research and Education
DoD Alzheimer's Disease Neuroimaging Initiative
Johnson and Johnson Pharmaceutical Research and Development
Conchological Society of Great Britain and Ireland
Canadian Institutes of Health Research
National Institute for Health Research
Rosetrees Trust
Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Eisai
Fujirebio Europe
Bayer Schering
Servier
UCLH Biomedical Research Centre	EUH2020
H. Lundbeck A/S

Keywords

Database
Ethics
Magnetic resonance imaging
Neuroimaging
Privacy

Access to Document

10.1007/s00330-019-06459-3

Persistent URL (handle)

Persistent link

Cite this

@article{da436c307da447d7bcf53cfb701b6294,

title = "Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods",

abstract = "Background: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants{\textquoteright} privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups. Methods: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer{\textquoteright}s Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests. Results: Automated analysis methods failed in 0–19\% of cases in FFR-processed images versus 0–2\% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001). Conclusions: All three outcome measures were affected differently by FFR, including failure of analysis methods and both “random” variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants{\textquoteright} privacy. Key Points: • Protecting participants{\textquoteright} privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.",

keywords = "Database, Ethics, Magnetic resonance imaging, Neuroimaging, Privacy",

author = "\{de Sitter\}, A. and M. Visser and I. Brouwer and Cover, \{K. S.\} and \{van Schijndel\}, \{R. A.\} and Eijgelaar, \{R. S.\} and M{\"u}ller, \{D. M.J.\} and S. Ropele and L. Kappos and Rovira and M. Filippi and C. Enzinger and J. Frederiksen and O. Ciccarelli and Guttmann, \{C. R.G.\} and Wattjes, \{M. P.\} and Witte, \{M. G.\} and \{de Witt Hamer\}, \{P. C.\} and F. Barkhof and H. Vrenken and \{on behalf of the MAGNIMS Study Group and Alzheimer{\textquoteright}s Disease Neuroimaging Initiative\}",

year = "2020",

month = feb,

doi = "10.1007/s00330-019-06459-3",

language = "English",

volume = "30",

pages = "1062--1074",

journal = "European Radiology",

issn = "0938-7994",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "2",

}

TY - JOUR

T1 - Facing privacy in neuroimaging

T2 - removing facial features degrades performance of image analysis methods

AU - de Sitter, A.

AU - Visser, M.

AU - Brouwer, I.

AU - Cover, K. S.

AU - van Schijndel, R. A.

AU - Eijgelaar, R. S.

AU - Müller, D. M.J.

AU - Ropele, S.

AU - Kappos, L.

AU - Rovira,

AU - Filippi, M.

AU - Enzinger, C.

AU - Frederiksen, J.

AU - Ciccarelli, O.

AU - Guttmann, C. R.G.

AU - Wattjes, M. P.

AU - Witte, M. G.

AU - de Witt Hamer, P. C.

AU - Barkhof, F.

AU - Vrenken, H.

AU - on behalf of the MAGNIMS Study Group and Alzheimer’s Disease Neuroimaging Initiative

PY - 2020/2

Y1 - 2020/2

N2 - Background: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants’ privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups. Methods: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer’s Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests. Results: Automated analysis methods failed in 0–19% of cases in FFR-processed images versus 0–2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001). Conclusions: All three outcome measures were affected differently by FFR, including failure of analysis methods and both “random” variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants’ privacy. Key Points: • Protecting participants’ privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.

AB - Background: Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants’ privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups. Methods: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer’s Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests. Results: Automated analysis methods failed in 0–19% of cases in FFR-processed images versus 0–2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001). Conclusions: All three outcome measures were affected differently by FFR, including failure of analysis methods and both “random” variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants’ privacy. Key Points: • Protecting participants’ privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.

KW - Database

KW - Ethics

KW - Magnetic resonance imaging

KW - Neuroimaging

KW - Privacy

UR - https://www.scopus.com/pages/publications/85074811129

UR - https://www.scopus.com/pages/publications/85074811129#tab=citedBy

U2 - 10.1007/s00330-019-06459-3

DO - 10.1007/s00330-019-06459-3

M3 - Article

C2 - 31691120

AN - SCOPUS:85074811129

SN - 0938-7994

VL - 30

SP - 1062

EP - 1074

JO - European Radiology

JF - European Radiology

IS - 2

ER -

Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

Abstract

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this