arXiv 2502.121812025-04-29eess.IVcs.AIcs.CVcs.LG

3D ReX：3D神经影像分类中的因果解释

3D ReX: Causal Explanations in 3D Neuroimaging Classification

King’s College London（伦敦国王学院）；University College London（伦敦大学学院）

Melane Navaratnarajah, Sophie A. Martin, David A. Kelly, Nathan Blake, Hana Chockler

备注：: Presented in the 2nd Workshop on Imageomics (Imageomics-AAAI-25), Discovering Biological Knowledge from Images using AI, held as part of AAAI-2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出首个基于因果的3D模型事后可解释性工具3D ReX，利用实际因果理论生成责任图，在卒中检测模型上验证其能有效揭示与卒中相关的特征空间分布。

摘要：

可解释性仍是医学影像中AI模型的重大难题，使临床医生难以信任AI驱动的预测。我们引入3D ReX，首个用于3D模型的基于因果的事后可解释性工具。3D ReX利用实际因果理论生成责任图，突出对模型决策最关键的区域。我们在卒中检测模型上测试3D ReX，揭示了与卒中相关的特征空间分布。

英文摘要：

Explainability remains a significant problem for AI models in medical imaging, making it challenging for clinicians to trust AI-driven predictions. We introduce 3D ReX, the first causality-based post-hoc explainability tool for 3D models. 3D ReX uses the theory of actual causality to generate responsibility maps which highlight the regions most crucial to the model's decision. We test 3D ReX on a stroke detection model, providing insight into the spatial distribution of features relevant to stroke.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。