Papers › Towards generating more interpretable counterfactuals via concept vectors: a...

Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays

4 Jun 2025arXiv:2506.04058archive 2025-07-28

Bulat Maksudov, Kathleen Curran, Alessandra Mileo

An essential step in deploying medical imaging models is ensuring alignment with clinical knowledge and interpretability. We focus on mapping clinical concepts into the latent space of generative models to identify Concept Activation Vectors (CAVs). Using a simple reconstruction autoencoder, we link user-defined concepts to image-level features without explicit label training. The extracted concepts are stable across datasets, enabling visual explanations that highlight clinically relevant features. By traversing latent space along concept directions, we produce counterfactuals that exaggerate or reduce specific clinical features. Preliminary results on chest X-rays show promise for large pathologies like cardiomegaly, while smaller pathologies remain challenging due to reconstruction limits. Although not outperforming baselines, this approach offers a path toward interpretable, concept-based explanations aligned with clinical knowledge.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Luab/cavisual officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Clinical Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CounterfactualsFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections