Metraipolis › archive › dc_ce41a73af1af
Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease — arXiv:2608.17370
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17370
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:48:36.787Z
- SHA-256 of the archived text
15fc0d95a04e15ab21524702effb771360ee87d7e462f882a06dc203ffa905ec- Stable URL of this page
https://metraipolis.com/documento/dc_ce41a73af1af
How to cite
Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease — arXiv:2608.17370 — arXiv (en), https://arxiv.org/abs/2608.17370 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce41a73af1af (Metraipolis archive dc_ce41a73af1af, sha256 15fc0d95a04e15ab21524702effb771360ee87d7e462f882a06dc203ffa905ec)
BibTeX
@misc{dcce41a73af1af,
title = {Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease — arXiv:2608.17370},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17370},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce41a73af1af; sha256 15fc0d95a04e15ab21524702effb771360ee87d7e462f882a06dc203ffa905ec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17370. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative models promise a route to explainable clinical AI: rather than probe a classifier, model the distributions of healthy and diseased patients and read explanations off the geometry between them. We build such a system - an optimal-transport rectified flow trained between two clinical distributions - and use it to ask a pointed question the field too rarely tests: do the resulting explanation heatmaps actually localize disease? On tabular tumour biomarkers (Breast Cancer Wisconsin) a single flow yields per-patient counterfactuals, an unsupervised malignancy score (AUROC 0.91; 0.93 +/- 0.01 across five seeds), and a label-free attribution that agrees with a supervised classifier (r ~ 0.5) - a compact, honest interpretability engine, though it never out-predicts logistic regression. Moving to chest X-rays, we show the transport heatmap is a population-level signal, not a localiser; a reconstruction-based, identity-preserving variant does localize synthetic lesions (pointing game 0.52), yet on real RSNA radiologist boxes it collapses to chance while only supervised Grad-CAM stays above it. The central result is a synthetic-to-real gap: label-free heatmaps that look compelling on planted lesions are not evidence of real localisation. We contribute a reusable optimal-transport recipe for generative explanations and a controlled benchmark for stress-testing whether they localize. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.17370 — 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 2026-10-18T14:47:59.396Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).