MirrorNet：医学图像匿名化真的能保护患者身份吗？
MirrorNet: Can Medical Image Anonymization Really Protect Patient Identity?
浏览论文内容
中文总结 AI 辅助
本研究提出MirrorNet模型，通过耦合循环一致变分自编码器发现去标识化医学扫描仍可识别患者，建议将其作为生物识别数据管理，相关代码与模型已公开。
中文摘要 AI 辅助
医学图像通常会被去标识化——移除姓名、日期和其他元数据——然后共享用于研究、教学和公共基准，人们认为这会使图像匿名。这种去标识化保护了元数据，但未保护像素，除了直接包含面部结构的扫描外，图像内容本身是否能识别患者几乎未被审查。我们通过使用一对耦合的循环一致变分自编码器，在横截面医学图像与非医学的患者识别图像之间学习循环一致对应关系，来研究这个问题。对于保留的扫描，模型能恢复可识别的患者肖像（身份区域平均绝对误差MAE为0.163）；反之，它能从该类图像合成扫描。这些结果表明，去标识化的医学扫描仍具有识别性——实际上，它是患者的照片——成像数据应被作为生物识别数据而非可匿名化记录进行管理。为支持可复现，代码和训练好的模型已在此httpsURL共享。
英文摘要
Medical images are routinely de-identified---names, dates, and other metadata removed---and then shared for research, teaching, and public benchmarks under the assumption that this renders them anonymous. Such de-identification protects the metadata but not the pixels, and---apart from scans that directly contain facial structures---whether the image content itself identifies the patient has received little scrutiny. We investigate this question by learning a cycle-consistent correspondence between a cross-sectional medical image and a non-medical, patient-identifying image, using a pair of coupled, cycle-consistent variational autoencoders. From a held-out scan, the model recovers a recognisable likeness of the patient (identity-region MAE = 0.163); conversely, it synthesises a scan from such an image. These results indicate that a de-identified medical scan remains identifying---it is, in effect, a photograph of the patient---and that imaging data should be governed as biometric data rather than as anonymisable records. To support reproducibility, the code and trained models are shared at https://github.com/attilasimko/public-repository.
发表机构
- Umeå University（于默奥大学）
机构由 AI 辅助整理，请以论文原文为准。
