Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency.

Details

Serval ID
serval:BIB_F1F51891A9AE
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency.
Journal
Human brain mapping
Author(s)
Molchanova N., Maréchal B., Thiran J.P., Kober T., Huelnhagen T., Richiardi J.
Working group(s)
Alzheimer's Disease Neuroimaging Initiative
ISSN
1097-0193 (Electronic)
ISSN-L
1065-9471
Publication state
Published
Issued date
15/06/2024
Peer-reviewed
Oui
Editor
Alzheimer's Disease Neuroimaging Initiative
Volume
45
Number
9
Pages
e26721
Language
english
Notes
Publication types: Journal Article
Publication Status: ppublish
Abstract
With the rise of open data, identifiability of individuals based on 3D renderings obtained from routine structural magnetic resonance imaging (MRI) scans of the head has become a growing privacy concern. To protect subject privacy, several algorithms have been developed to de-identify imaging data using blurring, defacing or refacing. Completely removing facial structures provides the best re-identification protection but can significantly impact post-processing steps, like brain morphometry. As an alternative, refacing methods that replace individual facial structures with generic templates have a lower effect on the geometry and intensity distribution of original scans, and are able to provide more consistent post-processing results by the price of higher re-identification risk and computational complexity. In the current study, we propose a novel method for anonymized face generation for defaced 3D T1-weighted scans based on a 3D conditional generative adversarial network. To evaluate the performance of the proposed de-identification tool, a comparative study was conducted between several existing defacing and refacing tools, with two different segmentation algorithms (FAST and Morphobox). The aim was to evaluate (i) impact on brain morphometry reproducibility, (ii) re-identification risk, (iii) balance between (i) and (ii), and (iv) the processing time. The proposed method takes 9 s for face generation and is suitable for recovering consistent post-processing results after defacing.
Keywords
Humans, Magnetic Resonance Imaging/methods, Adult, Brain/diagnostic imaging, Brain/anatomy & histology, Male, Female, Neural Networks, Computer, Imaging, Three-Dimensional/methods, Neuroimaging/methods, Neuroimaging/standards, Data Anonymization, Young Adult, Image Processing, Computer-Assisted/methods, Image Processing, Computer-Assisted/standards, Algorithms, brain morphometry, conditional generative adversarial networks, defacing, de‐identification, magnetic resonance imaging, privacy, re‐identification risk
Pubmed
Web of science
Open Access
Yes
Create date
25/06/2024 9:49
Last modification date
26/07/2024 7:01
Usage data