Abstract
Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning and neural identity translation, ROFI anonymizes facial features while retaining disease features (over 98\% accuracy, $\kappa > 0.90$). It achieves 100\% diagnostic sensitivity and high agreement ($\kappa > 0.90$) across eleven eye diseases in three cohorts, anonymizing over 95\% of images. ROFI works with AI systems, maintaining original diagnoses ($\kappa > 0.80$), and supports secure image reversal (over 98\% similarity), enabling audits and long-term care. These results show ROFI's effectiveness of protecting patient privacy in the digital medicine era.
Abstract (translated)
患者面部图像为评估眼科疾病提供了一种便捷的方法,同时也引发了隐私方面的担忧。在这里,我们介绍了ROFI,这是一个基于深度学习的眼科隐私保护框架。通过弱监督学习和神经身份翻译技术,ROFI能够在去除非必要面部特征的同时保留疾病的特征(超过98%的准确性,$\kappa > 0.90$)。在三个不同队列中的十一种眼科疾病上,ROFI实现了100%的诊断敏感度,并且具有高度的一致性($\kappa > 0.90$),同时去除了超过95%图像中的非必要面部信息。此外,该框架能够与AI系统兼容,保持原始诊断结果($\kappa > 0.80$),并支持安全的图像恢复功能(相似度超过98%),从而允许进行审核和长期跟踪护理。这些结果显示了ROFI在数字医疗时代有效保护患者隐私方面的效果。
URL
https://arxiv.org/abs/2510.11073