[论文解读] Is Medical Chest X-ray Data Anonymous?

Kai Packhäuser, Sebastian Gündel+4 more|arXiv (Cornell University)|Mar 15, 2021

COVID-19 diagnosis using AI参考文献 41被引用 11

一句话总结

本研究表明，深度学习模型能够以高准确率从已匿名化的医学胸部X光片中重新识别患者，其在ChestX-ray14数据集上的AUC达到0.9940，分类准确率为95.55%。研究结果表明，仅通过移除简单标识符进行匿名化处理，不足以保护患者隐私，即使在初次影像采集多年后依然存在风险。

ABSTRACT

With the rise and ever-increasing potential of deep learning techniques in recent years, publicly available medical datasets became a key factor to enable reproducible development of diagnostic algorithms in the medical domain. Medical data contains sensitive patient-related information and is therefore usually anonymized by removing patient identifiers, e.g., patient names before publication. To the best of our knowledge, we are the first to show that a well-trained deep learning system is able to recover the patient identity from chest X-ray data. We demonstrate this using the publicly available large-scale ChestX-ray14 dataset, a collection of 112,120 frontal-view chest X-ray images from 30,805 unique patients. Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0.9940 and a classification accuracy of 95.55%. We further highlight that the proposed system is able to reveal the same person even ten and more years after the initial scan. When pursuing a retrieval approach, we observe an mAP@R of 0.9748 and a precision@1 of 0.9963. Furthermore, we achieve an AUC of up to 0.9870 and a precision@1 of up to 0.9444 when evaluating our trained networks on CheXpert and the COVID-19 Image Data Collection. Based on this high identification rate, a potential attacker may leak patient-related information and additionally cross-reference images to obtain more information. Thus, there is a great risk of sensitive content falling into unauthorized hands or being disseminated against the will of the concerned patients. Especially during the COVID-19 pandemic, numerous chest X-ray datasets have been published to advance research. Therefore, such data may be vulnerable to potential attacks by deep learning-based re-identification algorithms.

研究动机与目标

• 调查是否可以利用深度学习技术，从已匿名化的医学胸部X光片中重新关联到具体患者。
• 评估跨时间跨度（包括扫描后十余年）的重新识别鲁棒性。
• 评估公开数据集（如ChestX-ray14、CheXpert和COVID-19 Image Data Collection）在身份重建方面的脆弱性。
• 强调在深度学习背景下发布医学影像数据所伴随的隐私风险，尤其是在COVID-19大流行期间。

提出的方法

• 训练了一个基于深度学习的验证系统，用于判断两幅前后位胸部X光片是否属于同一患者。
• 该模型采用孪生神经网络架构，通过比较图像嵌入来预测身份相似性。
• 系统在包含30,805名独立患者共112,120张图像的ChestX-ray14数据集上进行评估。
• 采用mAP@R和precision@1进行基于检索的评估，以衡量重新识别性能。
• 在外部数据集（包括CheXpert和COVID-19 Image Data Collection）上测试了模型的泛化能力。
• 通过AUC、准确率、mAP@R和precision@1等多个评估协议量化了模型性能。

实验结果

研究问题

• RQ1 深度学习模型能否以高准确率从已匿名化的前后位胸部X光片中重新识别患者？
• RQ2 当图像采集时间相隔超过十年时，重新识别的效率如何？
• RQ3 该模型在其他公开可用的医学影像数据集上的泛化能力达到何种程度？
• RQ4 在深度学习背景下，发布已匿名化的医学影像数据存在哪些隐私影响？

主要发现

• 该验证系统在ChestX-ray14数据集上实现了0.9940的AUC和95.55%的分类准确率。
• 该模型在重新识别任务中保持了高性能，mAP@R达到0.9748，precision@1达到0.9963。
• 在CheXpert数据集上，模型AUC最高达0.9870，precision@1最高达0.9444。
• 即使图像采集时间相隔十余年，系统仍能成功重新识别患者。
• 结果表明，当前的匿名化实践不足以防止通过深度学习实现身份重建。
• 通过重新识别存在显著的患者隐私泄露风险，尤其是在公开共享的医学影像数据集中。