遗忘即保留：面向3D医学图像分割的机器遗忘
To forget is to preserve: Machine Unlearning for 3D medical image segmentation
AI总结：
针对数据隐私法规，研究基于四种机制的近似遗忘策略在3D医学图像分割中的应用，通过Dice系数和MAE评估，发现噪声标签策略在遗忘集和保留集间取得最佳平衡。
摘要：
随着新的数据隐私法规（如GDPR [1]）允许个人要求从训练好的机器学习模型中删除其任何个人信息，人们开始推动研究从模型中遗忘数据以遵守这些法律。在这方面，基于四种机制，我们考虑了几种应用于MRBrainS18数据集 [2] 的近似遗忘策略。我们使用3D ResNet-50 [3] 作为分割的骨干架构，该架构已通过Med3D框架 [4] 进行预训练。以预训练模型为基线，我们评估了在两类主体（即保留和遗忘）上的相应保留准确率。我们通过Dice相似系数和平均绝对误差（MAE）值评估这些方法，使用两个独立的训练周期（20和50个epoch）。结果表明，噪声标签策略具有最佳的整体权衡，在50个epoch后，遗忘集准确率下降93%，同时保留集准确率保持84%。所有其他策略在更高的epoch数下表现出极端的遗忘水平，同时其保留集性能也出现灾难性退化。本研究结果为在主体特定水平上的遗忘提供了严格的性能指标基线，并为从业者选择适当策略提供了明确标准。
英文摘要：
With new data privacy laws such as the General Data Protection Regulation (GDPR) [1] that allow individuals to ask that any of their personal information be erased from trained machine learning models, there has been a push to investigate the unlearning of data from models as a way to comply with these laws. In this regard, based on four mechanics, we consider several approximate unlearning strategies applied to the MRBrainS18 dataset [2]. We use a 3D ResNet-50 [3] as a backbone architecture for segmentation that has been pre-trained with the Med3D framework [4]. Considering the pre-trained model as a baseline, we evaluate respective retention accuracy on 2 types of subjects, i.e., retain and forget. We assess these approaches through their Dice similarity coefficient and mean absolute error (MAE) values using two separate training horizons 20 and 50 epochs. The results show that the Noisy Label strategy had the best overall trade-off with a decrease of 93% in the forget set while maintaining 84% accuracy for the retained set after 50 epochs. All other strategies showed extreme levels of forgetting at higher epoch numbers while also demonstrating catastrophic degradation of their retain set performance. The results of this study provide a strict baseline of performance metrics for unlearning on a subject-specific level and provide practitioners with clear criteria for selecting the proper strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
