BIC Defacing Algorithm
Abstract
Public distribution of imaging information from several MRI data processing projects at the BIC has lead to the development of this DEFACING algorithm that is used as part of anonymisation process. Key features of the algorithm include: the defacing should modify voxels associated with face of the subject, making a rendering of the face unrecognisable, it should work on data in the native scanner space and it should not significantly affect subsequent data processing outcome (model based registration, brain extraction, brain tissue classification and brain segmentation). The algorithm is implemented using the MINC library and source code is publicly available. The effect of the defacing algorithm on the data processing was verified using the ICBM database of 152 scans of young adults.
02 /Specification & Classification
Click any tag to browse matching papers- Citations
- 4
- Assay
- Approach
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Application of a convolutional neural network to the quality control of MRI defacing
Daniel J. Delbarre, Luís Santos, … Ann‐Marie Mallon·Computers in Biology and MedicinePeer-reviewed·Oct 18, 2022
- Defacing biases visual quality assessments of structural MRI
Céline Provins, Élodie Savary, … Oscar Estéban·bioRxiv·Oct 11, 2024
- High-sensitivity detection of facial features on MRI brain scans with a convolutional network
Shashank Bansal, Avinash Kori, … Oscar Estéban·bioRxiv·Apr 25, 2021
- Refacing: reconstructing anonymized facial features using GANs
David Abramian, Anders Eklund·IEEE International Symposium on Biomedical Imaging (ISBI)Peer-reviewed·Apr 1, 2019
- Effect of MRI Defacing on EEG Forward and Inverse Modeling
Angela Mitrovska, Stefan Haufe·Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)Peer-reviewed·Jul 14, 2025
- Modified MRI anonymization (de-facing) for improved MEG coregistration
Ricardo Bruña, Delshad Vaghari, … Richard N. Henson·BioengineeringPeer-reviewed·Oct 21, 2022