A digital mask to safeguard patient privacy

作者：Yang, Yahan; Lyu, Junfeng; Wang, Ruixin; Wen, Quan; Zhao, Lanqin; Chen, Wenben; Bi, Shaowei; Meng, Jie; Mao, Keli; Xiao, Yu; Liang, Yingying; Zeng, Danqi; Du, Zijing; Wu, Yuxuan; Cui, Tingxin; Liu, Lixue; Iao, Wai Cheng; Li, Xiaoyan; Cheung, Carol Y.; Zhou, Jianhua; Hu, Youjin; Wei, Lai; Lai, Iat Fan; Yu, Xinping; Chen, Jingchang; Wang, Zhonghao; Mao, Zhen; Ye, Huijing; Xiao, Wei; Yang, Huasheng; Huang, Danping; Lin, Xiaoming; Zheng, Wei-shi; Wang, Ruixuan; Yu-Wai-Man, Patrick; Xu, Feng

来源：Nature Medicine, 2022, 28(9): 1883-+.

DOI：10.1038/s41591-022-01966-1

A deep-learning algorithm that removes patient-identifying information from facial images, while retaining sufficient information for accurate disease diagnosis, has the potential to protect patient privacy and facilitate public acceptance of facial imaging for use in digital medicine. @@@ The storage of facial images in medical records poses privacy risks due to the sensitive nature of the personal biometric information that can be extracted from such images. To minimize these risks, we developed a new technology, called the digital mask (DM), which is based on three-dimensional reconstruction and deep-learning algorithms to irreversibly erase identifiable features, while retaining disease-relevant features needed for diagnosis. In a prospective clinical study to evaluate the technology for diagnosis of ocular conditions, we found very high diagnostic consistency between the use of original and reconstructed facial videos (kappa >= 0.845 for strabismus, ptosis and nystagmus, and kappa = 0.801 for thyroid-associated orbitopathy) and comparable diagnostic accuracy (P >= 0.131 for all ocular conditions tested) was observed. Identity removal validation using multiple-choice questions showed that compared to image cropping, the DM could much more effectively remove identity attributes from facial images. We further confirmed the ability of the DM to evade recognition systems using artificial intelligence-powered re-identification algorithms. Moreover, use of the DM increased the willingness of patients with ocular conditions to provide their facial images as health information during medical treatment. These results indicate the potential of the DM algorithm to protect the privacy of patients' facial images in an era of rapid adoption of digital health technologies.

• 单位
  南方医科大学; 广东省人民医院; 清华大学; 中山大学