3D ReX: Causal Explanations in 3D Neuroimaging Classification
Image and Video Processing
2025-04-30 v3 Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Abstract
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.
Cite
@article{arxiv.2502.12181,
title = {3D ReX: Causal Explanations in 3D Neuroimaging Classification},
author = {Melane Navaratnarajah and Sophie A. Martin and David A. Kelly and Nathan Blake and Hana Chockler},
journal= {arXiv preprint arXiv:2502.12181},
year = {2025}
}
Comments
Presented in the 2nd Workshop on Imageomics (Imageomics-AAAI-25), Discovering Biological Knowledge from Images using AI, held as part of AAAI-2025