Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods.
- de Sitter A Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands. A.deSitter@vumc.nl.
- Visser M Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Brouwer I Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Cover KS Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- van Schijndel RA Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Eijgelaar RS Department of Radiotherapy, The Netherlands Cancer Institute, Amsterdam, the Netherlands.
- Müller DMJ Department of Neurosurgery, Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Ropele S Department of Neurology, Medical University of Graz, Graz, Austria.
- Kappos L Department of Neurology, University Hospital, Kantonsspital, Basel, Switzerland.
- Rovira Á Unitat de Ressonància Magnètica (Servei de Radiologia), Hospital universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain.
- Filippi M Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, UniSR, Milan, Italy.
- Enzinger C Division of Neuroradiology, Vascular and Interventional Radiology, Department of Radiology, Medical University of Graz, Graz, Austria.
- Frederiksen J Department of Neurology, Glostrup University Hospital, Copenhagen, Denmark.
- Ciccarelli O UK/NIHR UCL-UCLH Biomedical Research Centre, Institute of Neurology, UCL, London, UK.
- Guttmann CRG Center for Neurological Imaging, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
- Wattjes MP Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Witte MG Department of Radiotherapy, The Netherlands Cancer Institute, Amsterdam, the Netherlands.
- de Witt Hamer PC Department of Neurosurgery, Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Barkhof F Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- Vrenken H Department of Radiology and Nuclear Medicine, Amsterdam Neuroscience Amsterdam UMC, location VUmc, Amsterdam, the Netherlands.
- 2019-11-07
Published in:
- European radiology. - 2020
Database
Ethics
Magnetic resonance imaging
Neuroimaging
Privacy
Aged
Aged, 80 and over
Algorithms
Alzheimer Disease
Brain
Confidentiality
Face
Female
Glioblastoma
Humans
Image Interpretation, Computer-Assisted
Information Dissemination
Magnetic Resonance Imaging
Male
Middle Aged
Multiple Sclerosis
Neuroimaging
Reproducibility of Results
Tumor Burden
English
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.
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.
- Language
-
- English
- Open access status
- hybrid
- Identifiers
-
- DOI 10.1007/s00330-019-06459-3
- PMID 31691120
- Persistent URL
- https://sonar.rero.ch/global/documents/49824
Statistics
Document views: 17
File downloads:
- fulltext.pdf: 0