Leveraging the expertise of physicians to identify medically meaningful features in ‘counterfactual’ images produced via generative machine learning facilitates the auditing of the inference process of medical-image classifiers, as shown for dermatology images.

中文翻译：

---

解释反事实图像

利用医生的专业知识来识别通过生成机器学习生成的“反事实”图像中具有医学意义的特征，有助于审计医学图像分类器的推理过程，如皮肤科图像所示。