3D ReX: Causal Explanations in 3D Neuroimaging Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918003364331520 |
|---|---|
| author | Navaratnarajah, Melane Martin, Sophie A. Kelly, David A. Blake, Nathan Chockler, Hana |
| author_facet | Navaratnarajah, Melane Martin, Sophie A. Kelly, David A. Blake, Nathan Chockler, Hana |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D ReX: Causal Explanations in 3D Neuroimaging Classification Navaratnarajah, Melane Martin, Sophie A. Kelly, David A. Blake, Nathan Chockler, Hana Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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. |
| title | 3D ReX: Causal Explanations in 3D Neuroimaging Classification |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.12181 |