用因果理论解释3D脑影像模型决策，帮医生理解AI判断依据。
3D ReX: Causal Explanations in 3D Neuroimaging Classification
- 基于实际因果理论生成责任图，定位影响判断的关键脑区。
- 在中风检测模型上验证，揭示与中风相关特征的空间分布。
- 首个面向3D医学影像的因果可解释工具，适合临床AI可信性研究。
可解释性仍是医疗影像AI的重大挑战，导致临床医生难以信任AI预测结果。我们提出3D ReX，首个基于因果关系的3D模型后处理解释工具。3D ReX利用实际因果理论生成责任图，突出模型决策中最关键的区域。我们在中风检测模型上测试了3D ReX，揭示了与中风相关特征的空间分布，为理解模型决策提供了新视角。
原文摘要 · Abstract (English)
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.
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。