arXiv · 2611.19630
Where slide-level foundation-model classifiers fail on atypical breast lesions
Abstract
Whether a ductal breast lesion is called atypical hyperplasia or low-grade carcinoma in situ increasingly determines surgery. However, slide-level classifiers built on pathology foundation models (PFMs) perform worst on these lesions. Using four PFMs, cross-validation on BRACS and preregistered hypotheses, we studied where the classification of atypia fails. Because slides are labelled with their most severe lesion, only 39% of the slides with annotated atypical ductal hyperplasia (ADH) were labelled ADH. Attention ranked the lesion high but rarely first, and showing the model only the lesion helped little, whereas classifiers trained per decision with lesion-level labels improved all four atypical boundaries. ADH regions inserted into benign slides raised the probability of malignancy more than that of atypia. In a hospital with pathologist-labelled single-subtype slides and in HISTAI, benign slides were scored closer to lesions and triage specificity fell from 0.48-0.53 to 0.00-0.07 and 0.22.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Nerea Hernandez, Luis J. Herrera, Cesar Ramirez, Olga Valenzuela, Ignacio Rojas, Francisco M. Ortuño. 2026-11-14. Where slide-level foundation-model classifiers fail on atypical breast lesions. https://searcharxiv.com/abs/2611.19630
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.