Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918141809917952 |
|---|---|
| author | Gao, Chenyu Xu, Kaiwen Kim, Michael E. Zuo, Lianrui Li, Zhiyuan Archer, Derek B. Hohman, Timothy J. Moore, Ann Zenobia Ferrucci, Luigi Beason-Held, Lori L. Resnick, Susan M. Davatzikos, Christos Prince, Jerry L. Landman, Bennett A. |
| author_facet | Gao, Chenyu Xu, Kaiwen Kim, Michael E. Zuo, Lianrui Li, Zhiyuan Archer, Derek B. Hohman, Timothy J. Moore, Ann Zenobia Ferrucci, Luigi Beason-Held, Lori L. Resnick, Susan M. Davatzikos, Christos Prince, Jerry L. Landman, Bennett A. |
| contents | Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p < 0.05). This performance also generalizes well to previously unseen datasets. For skeletal muscle radiodensity predictions, using defaced images results in significantly weaker Spearman's rank correlation coefficients compared to using original images (p < 10-4). For shin muscle, the correlation is statistically significant (p < 0.05) when using original images but not statistically significant (p > 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential Gao, Chenyu Xu, Kaiwen Kim, Michael E. Zuo, Lianrui Li, Zhiyuan Archer, Derek B. Hohman, Timothy J. Moore, Ann Zenobia Ferrucci, Luigi Beason-Held, Lori L. Resnick, Susan M. Davatzikos, Christos Prince, Jerry L. Landman, Bennett A. Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p < 0.05). This performance also generalizes well to previously unseen datasets. For skeletal muscle radiodensity predictions, using defaced images results in significantly weaker Spearman's rank correlation coefficients compared to using original images (p < 10-4). For shin muscle, the correlation is statistically significant (p < 0.05) when using original images but not statistically significant (p > 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information. |
| title | Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.18834 |