发表机构
University College London（伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对医学图像诊断深度学习模型可解释性不足的问题，提出无需生成模型的反事实生成框架，可更透明地改变分类器预测且更接近原图。
AI 中文摘要
深度学习模型在医学图像诊断中已取得令人瞩目的性能，但在临床场景中的部署仍受限于可解释性不足的问题。反事实图像是审查模型行为的一种手段，可展示图像需要如何改变才能让分类器产生不同的预测结果。现有方法通常使用辅助模型（包括生成对抗网络和扩散模型）生成此类解释。这些方法虽常能生成视觉上逼真的图像，但用另一个黑盒模型来解释当前黑盒模型，难以将分类器的决策过程与生成器的归纳偏差分离开来。我们提出一种无需生成模型的新型反事实生成框架，反事实样本直接从分类器提取的因果证据构建而成。该方法是确定性的，无需额外模型训练，且支持在用户指定的感兴趣区域内进行可控编辑。在真实世界医学图像数据集上的实验表明，所提方法可成功改变分类器的预测结果，同时相比生成式基线方法更接近原始图像，为分类器的决策边界提供了更直接、透明的视角。
英文摘要
Deep learning models have achieved impressive performance in medical image diagnosis, yet their deployment in clinical settings remains constrained by limited explainability. Counterfactual images provide one means of auditing model behavior by showing how an image would need to change for a classifier to produce a different prediction. Existing approaches typically generate such explanations using auxiliary models, including generative adversarial networks and diffusion models. While often capable of producing visually realistic images, these methods explain one black-box model using another, making it difficult to separate the classifier's decision-making process from the inductive biases of the generator. We propose a novel counterfactual-generation framework that requires no generative model. Instead, counterfactuals are constructed directly from causal evidence extracted from the classifier. The resulting approach is deterministic, requires no additional model training, and enables controllable edits within user-specified regions of interest. Experiments on real-world medical imaging datasets demonstrate that the proposed method successfully changes classifier predictions while remaining closer to the original image than generative baselines, providing a more direct and transparent view of the classifier's decision boundary.
