Metraipolis › archive › dc_5c196abc5fb6
Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation — arXiv:2610.41763
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41763
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T05:03:47.366Z
- SHA-256 of the archived text
f50a6d00a41d5afd2ddcf9c738d11fa469c3331712035d7d682f503e113476e5- Stable URL of this page
https://metraipolis.com/documento/dc_5c196abc5fb6
How to cite
Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation — arXiv:2610.41763 — arXiv (en), https://arxiv.org/abs/2610.41763 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5c196abc5fb6 (Metraipolis archive dc_5c196abc5fb6, sha256 f50a6d00a41d5afd2ddcf9c738d11fa469c3331712035d7d682f503e113476e5)
BibTeX
@misc{dc5c196abc5fb6,
title = {Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation — arXiv:2610.41763},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41763},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5c196abc5fb6; sha256 f50a6d00a41d5afd2ddcf9c738d11fa469c3331712035d7d682f503e113476e5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41763. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable histopathology segmentation requires models that rely on pathology-relevant structures rather than spurious background correlations. In this work, we argue that improving architectures alone is insufficient if models continue to rely on spurious correlations rather than pathology-relevant features. We introduce a causality-inspired evaluation framework based on controlled interventions that explicitly probes model sensitivity to foreground tissue structure and background/domain variation. Building on this, we propose the Causal Reliance Score (CRS), a metric that quantifies the relative sensitivity of model predictions to foreground perturbation versus background/domain variation under controlled interventions. To support this analysis, we design augmentation strategies that act as implicit counterfactual interventions during training, encouraging invariance to nuisance factors while preserving morphology. We demonstrate how these interventions reveal behavioural differences between models that are not captured by standard metrics such as Dice or IoU. While we instantiate our framework using a self-supervised transformer (CAUSE-ViT), the primary contribution of this work is not a new architecture, but a principled intervention-based methodology and evaluation metric for auditing model behaviour in medical image segmentation. Our results suggest that evaluating model behaviour through counterfactual interventions is essential for developing reliable and clinically robust medical image segmentation systems. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.41763 — 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 2026-11-02T04:49:13.271Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).