提出临床风险感知的模型删训方法，降低误诊风险。
Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification
- 用熵驱动遗忘机制替换随机重标签，避免模型学坏良性特征。
- 在20%~50%数据删除下，假阴性率低于标准方法，临床风险更低。
- 适合医疗影像系统中需兼顾隐私与诊断安全的研究者使用。
深度学习在医学诊断中的应用需平衡患者安全与数据保护合规性。机器删训可选择性移除部署模型中的训练数据，但现有方法多以效率和隐私指标验证，忽视临床错误成本的非对称性。本文研究删训对二分类医学图像任务中临床风险的影响。结果表明，标准删训策略（微调、随机重标签、SalUn）可能降低测试性能并提高假阴性率，加剧临床风险。为此，我们提出SalUn-CRA（临床风险感知版），在遗忘集的恶性样本上采用基于熵的遗忘机制，取代随机重标签，防止模型习得有害的良性关联。在DermaMNIST和PathMNIST数据集上，以20%和50%的数据移除率进行评估，结合不对称成本的全局风险指标，SalUn-CRA的临床风险低于或接近全量重训练，同时保持删训有效性。结果表明，临床风险应成为医疗系统删训验证的核心组成部分。
原文摘要 · Abstract (English)
The application of Deep Learning in medical diagnosis must balance patient safety with compliance with data protection regulations. Machine Unlearning enables the selective removal of training data from deployed models. However, most methods are validated primarily through efficiency and privacy-oriented metrics, with limited attention to clinically asymmetric error costs. In this work, we investigate how unlearning affects clinical risk in binary medical image classification. We show that standard unlearning strategies (Fine-Tuning, Random Labeling, and SalUn) may reduce test utility while increasing false-negative rates, thereby amplifying clinical risk. To mitigate this, we propose SalUn-CRA (Clinical Risk-Aware), a variant of SalUn that replaces random relabeling with entropy-based forgetting for malignant samples in the forget set, preventing the model from learning harmful benign associations. We evaluate on DermaMNIST and PathMNIST medical image datasets under 20% and 50% data removal. Using Global Risk metrics with asymmetric costs, SalUn-CRA achieves lower or comparable clinical risk to full retraining while preserving unlearning effectiveness. These results suggest that clinical risk should be an integral component of unlearning validation in medical systems.
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。