Abstract：
OBJECTIVE: Concerns about patient privacy issues have limited the application of medical deep learning models in certain real-world scenarios. Differential privacy (DP) can alleviate this problem by injecting random noise into the model. However, naively applying DP to medical models will not achieve a satisfactory balance between privacy and utility due to the high dimensionality of medical models and the limited labeled samples.
METHODS: This work proposed the DP-SSLoRA model, a privacy-preserving classification model for medical images combining differential privacy with self-supervised low-rank adaptation. In this work, a self-supervised pre-training method is used to obtain enhanced representations from unlabeled publicly available medical data. Then, a low-rank decomposition method is employed to mitigate the impact of differentially private noise and combined with pre-trained features to conduct the classification task on private datasets.
RESULTS: In the classification experiments using three real chest-X ray datasets, DP-SSLoRA achieves good performance with strong privacy guarantees. Under the premise of ɛ=2, with the AUC of 0.942 in RSNA, the AUC of 0.9658 in Covid-QU-mini, and the AUC of 0.9886 in Chest X-ray 15k.
CONCLUSIONS: Extensive experiments on real chest X-ray datasets show that DP-SSLoRA can achieve satisfactory performance with stronger privacy guarantees. This study provides guidance for studying privacy-preserving in the medical field. Source code is publicly available online. https://github.com/oneheartforone/DP-SSLoRA.
METHODS: This work proposed the DP-SSLoRA model, a privacy-preserving classification model for medical images combining differential privacy with self-supervised low-rank adaptation. In this work, a self-supervised pre-training method is used to obtain enhanced representations from unlabeled publicly available medical data. Then, a low-rank decomposition method is employed to mitigate the impact of differentially private noise and combined with pre-trained features to conduct the classification task on private datasets.
RESULTS: In the classification experiments using three real chest-X ray datasets, DP-SSLoRA achieves good performance with strong privacy guarantees. Under the premise of ɛ=2, with the AUC of 0.942 in RSNA, the AUC of 0.9658 in Covid-QU-mini, and the AUC of 0.9886 in Chest X-ray 15k.
CONCLUSIONS: Extensive experiments on real chest X-ray datasets show that DP-SSLoRA can achieve satisfactory performance with stronger privacy guarantees. This study provides guidance for studying privacy-preserving in the medical field. Source code is publicly available online. https://github.com/oneheartforone/DP-SSLoRA.
摘要：
目的：对患者隐私问题的担忧限制了医学深度学习模型在某些现实场景中的应用。差分隐私（DP）可以通过将随机噪声注入模型来缓解此问题。然而,由于医学模型的高维度和有限的标记样本，天真地将DP应用于医学模型将无法在隐私和效用之间实现令人满意的平衡。
方法：这项工作提出了DP-SSLoRA模型，结合差分隐私和自监督低秩适应的医学图像隐私保护分类模型。在这项工作中,一种自我监督的预训练方法用于从未标记的公开可用的医疗数据中获得增强的表示。然后，采用低秩分解方法来减轻差分私有噪声的影响，并结合预训练特征对私有数据集进行分类任务。
结果：在使用三个真实胸部X射线数据集的分类实验中，DP-SSLoRA具有强大的隐私保证，可实现良好的性能。在△=2的前提下，RSNA的AUC为0.942，Covid-QU-mini的AUC为0.9658，胸部X光15k的AUC为0.9886。
结论：在真实的胸部X射线数据集上进行的大量实验表明，DP-SSLoRA可以在更强的隐私保证下实现令人满意的性能。本研究为医学领域的隐私保护研究提供了指导。源代码是公开的在线。https://github.com/oneheartforone/DP-SSLoRA。
方法：这项工作提出了DP-SSLoRA模型，结合差分隐私和自监督低秩适应的医学图像隐私保护分类模型。在这项工作中,一种自我监督的预训练方法用于从未标记的公开可用的医疗数据中获得增强的表示。然后，采用低秩分解方法来减轻差分私有噪声的影响，并结合预训练特征对私有数据集进行分类任务。
结果：在使用三个真实胸部X射线数据集的分类实验中，DP-SSLoRA具有强大的隐私保证，可实现良好的性能。在△=2的前提下，RSNA的AUC为0.942，Covid-QU-mini的AUC为0.9658，胸部X光15k的AUC为0.9886。
结论：在真实的胸部X射线数据集上进行的大量实验表明，DP-SSLoRA可以在更强的隐私保证下实现令人满意的性能。本研究为医学领域的隐私保护研究提供了指导。源代码是公开的在线。https://github.com/oneheartforone/DP-SSLoRA。
