ROFI能隐去患者面部又保留眼病特征，保障隐私同时支持诊断与可逆恢复。
ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
- 基于弱监督学习与神经身份转换，隐去人脸但保留疾病特征。
- 对11种眼病保持98%以上准确率和超过0.90的κ一致性，匿名化超95%图像。
- 支持诊断结果不变、可逆恢复，适合医疗影像共享与长期随访场景。
患者面部图像为眼病评估提供了便利，但也引发隐私担忧。本文提出ROFI，一种基于深度学习的眼科隐私保护框架。通过弱监督学习与神经身份转换，ROFI在保留疾病特征的同时实现面部匿名化（准确率超98%，κ>0.90）。在三个队列中对11种眼病实现100%诊断敏感度与高一致性的κ>0.90，成功匿名化超过95%的图像。ROFI兼容人工智能系统，保持原始诊断结果（κ>0.80），并支持安全图像反向还原（相似度超98%），便于审计与长期诊疗。结果表明，ROFI在数字医疗时代有效保护患者隐私。
原文摘要 · Abstract (English)
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, $κ> 0.90$). It achieves 100\% diagnostic sensitivity and high agreement ($κ> 0.90$) across eleven eye diseases in three cohorts, anonymizing over 95\% of images. ROFI works with AI systems, maintaining original diagnoses ($κ> 0.80$), 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。