Refacing: reconstructing anonymized facial features using GANs

Abstract

Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.

References in corpus (4)

• A Survey on Deep Learning in Medical Image Analysis
• Generative Adversarial Network in Medical Imaging: A Review
• Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT
• Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training

Cited by in corpus (5)

• Generative Adversarial Network in Medical Imaging: A Review
• Generating fMRI volumes from T1-weighted volumes using 3D CycleGAN
• Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis
• Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency
• Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks