Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging
This work addresses the need for interpretable, label-free statistical analysis in biomedical imaging, offering a novel method for explaining deep statistical tests, though it is incremental in combining existing concepts.
The authors tackled the problem of deep neural two-sample tests lacking interpretability in biomedical imaging by proposing an explainable framework that provides sample-level and feature-level explanations, identifying influential samples and anatomically meaningful regions to reveal group differences.
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.