让深度统计检验可解释，看清医学影像中哪些样本和区域导致组间差异。
Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging
- 通过样本级与特征级解释，揭示深度双样本检验的决策依据。
- 在无标签场景下识别关键样本与病理性解剖区域，效果显著。
- 适合需要可解释性分析的医学影像研究者使用。
深度神经网络双样本检验近期在检测组间分布差异方面表现强劲，但其黑箱特性限制了在生物医学分析中的可解释性与实际应用。现有事后可解释方法多依赖类别标签，不适用于无标签的统计检验场景。本文提出一种可解释的深度统计检验框架，为深度双样本检验增加样本级与特征级解释，揭示导致组间统计差异的个体样本与输入特征。该方法能定位图像中贡献最大的区域及关键样本，提供空间与实例级别的洞察。应用于生物医学影像数据时，框架成功识别出具有影响力的样本，并突出与疾病相关的解剖学有意义区域。本工作连接了统计推断与可解释AI，实现医学影像中无需标签的可解释群体分析。
原文摘要 · Abstract (English)
Deep neural two-sample tests have recently shown strong power for detecting distributional differences between groups, yet their black-box nature limits interpretability and practical adoption in biomedical analysis. Moreover, most existing post-hoc explainability methods rely on class labels, making them unsuitable for label-free statistical testing settings. We propose an explainable deep statistical testing framework that augments deep two-sample tests with sample-level and feature-level explanations, revealing which individual samples and which input features drive statistically significant group differences. Our method highlights which image regions and which individual samples contribute most to the detected group difference, providing spatial and instance-wise insight into the test's decision. Applied to biomedical imaging data, the proposed framework identifies influential samples and highlights anatomically meaningful regions associated with disease-related variation. This work bridges statistical inference and explainable AI, enabling interpretable, label-free population analysis in medical imaging.
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。