Metraipolis › archive › dc_7c642eb5ed9c

Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention — arXiv:2610.09031

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09031
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:40.162Z
SHA-256 of the archived text
77fc38441d6afa26097e8e755fa3ec8924d174307e642ec52e35cc52923a2c7d
Stable URL of this page
https://metraipolis.com/documento/dc_7c642eb5ed9c

How to cite

Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention — arXiv:2610.09031 — arXiv (en), https://arxiv.org/abs/2610.09031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c642eb5ed9c (Metraipolis archive dc_7c642eb5ed9c, sha256 77fc38441d6afa26097e8e755fa3ec8924d174307e642ec52e35cc52923a2c7d)
BibTeX
@misc{dc7c642eb5ed9c,
  title = {Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention — arXiv:2610.09031},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09031},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c642eb5ed9c; sha256 77fc38441d6afa26097e8e755fa3ec8924d174307e642ec52e35cc52923a2c7d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play framework for concept-based interpretation and model refinement. By aligning a single-modality encoder to BioMedCLIP, we construct a Concept Bottleneck Model (CBM) that enables concept-level interventions. These interventions allow us to isolate causal versus spuriously correlated concepts, validate insights with domain experts, and generate counterfactual samples for targeted fine-tuning. We evaluate our framework on a Mayo Clinic ultrasound dataset and the CheXpert 5x200 chest X-ray dataset. Results demonstrate that concept intervention enables reliable model diagnosis while maintaining, and occasionally improving predictive performance via guided fine-tuning. Our findings highlight the practical value of this framework for controlled, interpretable refinement of clinical deep learning models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.09031 — 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 2026-10-08T12:14:15.369Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).