Metraipolis › archive › dc_60a8aafed205

Generating Medical Image Counterfactuals using Causal Explanations — arXiv:2609.02697

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02697
License (as archived)
CC0-1.0
Archived
2026-10-17T05:50:14.641Z
SHA-256 of the archived text
187f7ca54bd70318dda646a409dd51006d152759d6b0b0ca4fe51451827e2f19
Stable URL of this page
https://metraipolis.com/documento/dc_60a8aafed205

How to cite

Generating Medical Image Counterfactuals using Causal Explanations — arXiv:2609.02697 — arXiv (en), https://arxiv.org/abs/2609.02697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60a8aafed205 (Metraipolis archive dc_60a8aafed205, sha256 187f7ca54bd70318dda646a409dd51006d152759d6b0b0ca4fe51451827e2f19)
BibTeX
@misc{dc60a8aafed205,
  title = {Generating Medical Image Counterfactuals using Causal Explanations — arXiv:2609.02697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60a8aafed205; sha256 187f7ca54bd70318dda646a409dd51006d152759d6b0b0ca4fe51451827e2f19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning models have achieved impressive performance in medical image diagnosis, yet their deployment in clinical settings remains constrained by limited explainability. Counterfactual images provide one means of auditing model behavior by showing how an image would need to change for a classifier to produce a different prediction. Existing approaches typically generate such explanations using auxiliary models, including generative adversarial networks and diffusion models. While often capable of producing visually realistic images, these methods explain one black-box model using another, making it difficult to separate the classifier's decision-making process from the inductive biases of the generator. We propose a novel counterfactual-generation framework that requires no generative model. Instead, counterfactuals are constructed directly from causal evidence extracted from the classifier. The resulting approach is deterministic, requires no additional model training, and enables controllable edits within user-specified regions of interest. Experiments on real-world medical imaging datasets demonstrate that the proposed method successfully changes classifier predictions while remaining closer to the original image than generative baselines, providing a more direct and transparent view of the classifier's decision boundary.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.02697 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T05:25:58.153Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).