3D ReX: Causal Explanations in 3D Neuroimaging Classification

Melane Navaratnarajah, Sophie A. Martin, David A. Kelly, Nathan Blake, Hana Chockler
2/14/2025
eess.IVcs.AIcs.CV

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Causal Image Synthesis of Brain MR in 3D

83% match2023

REX: Causal discovery based on machine learning and explainability techniques

83% match1 repo282025

MACAW: A Causal Generative Model for Medical Imaging

80% match2024

Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application

80% match2025

From Explainable to Explained AI: Ideas for Falsifying and Quantifying Explanations

80% match1 repo42025

Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration

80% match2025

Cite this paper

@article{navaratnarajah2025rex,
  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},
  year   = {2025},
  eprint = {2502.12181},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.12181v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.12181.svg)](https://codeofpaper.com/paper/2502.12181)

Discussion