3D ReX: Causal Explanations in 3D Neuroimaging Classification
This addresses the challenge of trust for clinicians in AI-driven predictions in medical imaging, though it appears incremental as it applies existing causality theory to a new domain.
The paper tackled the problem of explainability in AI models for medical imaging by introducing 3D ReX, a causality-based post-hoc explainability tool for 3D models, which generates responsibility maps to highlight crucial regions for decisions, tested on a stroke detection model to provide insights into spatial feature distribution.
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.