近日，研究中心博士生王斌的一篇论文 “Adaptive Feature Unlearning for Trustworthy Medical Imaging Privacy”被国际医学影像领域权威期刊 Medical Image Analysis （MedIA，JCR 一区，影响因子 11.8）录用。该论文聚焦医学影像人工智能模型中的患者隐私保护问题，提出了面向可信医学影像分析的自适应特征遗忘框架 AdaptForget，为医疗数据撤回、模型隐私保护和可信审计提供了新的技术思路。

论文摘要：深度学习已成为医学影像分析中的重要组成部分，但其记忆训练数据的倾向给患者隐私带来了严重风险。机器遗忘通过撤销敏感信息提供了一种潜在的解决方案，然而现有方法仍面临三个关键局限：（1）它们通常只能实现输出层面的变化，而残余的特征表示仍然存在；（2）它们依赖批量重训练，使得实时移除单个患者图像变得不可行；（3）它们缺乏严格的指标来验证特征空间中的遗忘效果。为解决上述问题，本文提出了 AdaptForget，一种面向隐私保护医学影像分析的领域自适应特征级遗忘框架。AdaptForget 引入分布外（out-of-distribution, OOD）引导机制，在特征流形中将被遗忘数据与保留数据解耦，并由特征级遗忘理论界提供支撑。为防止特征坍塌，本文设计了一种 OOD 驱动的特征—输出解耦损失，以实现对被遗忘数据的结构化移除。为支持及时撤销，本文形式化定义了单条目遗忘任务，使单个患者记录能够被即时擦除。为实现客观审计，本文提出了隔离验证距离（isolation verification distance, IVD），这是一种新的度量指标，可量化特征分离程度，并为遗忘效果提供可解释的证据。在四个医学影像基准数据集（组织病理学、视网膜眼底、皮肤病学和 OCT）以及补充的医疗健康记录数据集上的大量实验表明，AdaptForget 在保持模型效用的同时，实现了当前先进水平的隐私保护效果。

Abstract: Deep learning has become integral to medical imaging, but its tendency to memorize training data poses serious risks for patient privacy. Machine unlearning offers a potential remedy by revoking sensitive information, yet existing approaches face three key limitations: (1) they often achieve only output-level changes while residual feature representations remain; (2) they rely on batch retraining, making real-time removal of individual patient images infeasible; and (3) they lack rigorous metrics to verify forgetting in feature space. We propose AdaptForget, a domain-adaptive feature-level unlearning framework for privacy-preserving medical image analysis. AdaptForget introduces out-of-distribution (OOD) guidance to disentangle forgotten data from retained data in the feature manifold, supported by a theoretical feature-level unlearning bound. To prevent feature collapse, we design an OOD-driven feature-output disentanglement loss that enforces structured removal of forgotten data. To enable timely revocation, we formalize the task of single-entry forgetting, allowing immediate erasure of individual patient records. For objective auditing, we propose the isolation verification distance, a novel metric that quantifies feature separation and provides interpretable evidence of forgetting. Extensive experiments on four medical imaging benchmarks (histopathology, retinal fundus, dermatology, and OCT) as well as complementary healthcare record datasets demonstrate that AdaptForget achieves state-of-the-art privacy protection while preserving model utility.