# Privacy Protection in MRI Scans Using 3D Masked Autoencoders

Source: [Privacy Protection in MRI Scans Using 3D Masked Autoencoders](<https://www.sota2.com/research/paper/68fa72941e209131cea57461>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:36:55.225Z

Authors: Lennart Alexander Van der Goten, Kevin Smith

Published: 2023-10-24T12:25:37.000Z

## Abstract

MRI scans provide valuable medical information, however they also contain sensitive and personally identifiable information that needs to be protected. Whereas MRI metadata is easily sanitized, MRI image data is a privacy risk because it contains information to render highly-realistic 3D visualizations of a patient's head, enabling malicious actors to possibly identify the subject by cross-referencing a database. Data anonymization and de-identification is concerned with ensuring the privacy and confidentiality of individuals' personal information. Traditional MRI de-identification methods remove privacy-sensitive parts (e.g. eyes, nose etc.) from a given scan. This comes at the expense of introducing a domain shift that can throw off downstream analyses. In this work, we propose CP-MAE, a model that de-identifies the face by remodeling it (e.g. changing the face) rather than by removing parts using masked autoencoders. CP-MAE outperforms all previous approaches in terms of downstream task performance as well as de-identification. With our method we are able to synthesize high-fidelity scans of resolution up to $256^3$ -- compared to $128^3$ with previous approaches -- which constitutes an eight-fold increase in the number of voxels.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [User-based De-identification Matching on OASIS-3](<https://www.sota2.com/research/sota/user-based-de-identification-matching-on-oasis-3.md>): User-based De-identification Matching; OASIS-3; Accuracy: 23.41.

- [Model-based De-identification Matching on OASIS-3](<https://www.sota2.com/research/sota/model-based-de-identification-matching-on-oasis-3.md>): Model-based De-identification Matching; OASIS-3; Accuracy: 58.19.

- [User-based De-identification Matching on ADNI](<https://www.sota2.com/research/sota/user-based-de-identification-matching-on-adni.md>): User-based De-identification Matching; ADNI; Accuracy: 41.74.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.15778>)

[PDF](<https://arxiv.org/pdf/2310.15778.pdf>)

[Implementation](<https://github.com/mmilch01/mask_face2>)