Model Releases
What Carries the Signal in Pathology Foundation-Model Atlases? A Patient-Level Controlled Benchmark in Breast Cancer
arXiv:2608.00105v1 Announce Type: new Abstract: Pathology foundation models are reported to encode molecular programmes in tissue morphology, but the evidence is usually a cohort-wide ranked gene list
arXiv:2608.00105v1 Announce Type: new Abstract: Pathology foundation models are reported to encode molecular programmes in tissue morphology, but the evidence is usually a cohort-wide ranked gene list rather than a prediction for a held-out patient. We rebuild such an analysis with the patient as the unit of evidence and ask which pipeline component carries signal. Across 11 frozen backbones, four pre-specified gene programmes and 285 TCGA-BRCA patients with paired slides and RNA-seq (44 cells; GroupKFold by patient, all preprocessing fitted inside the fold), ridge regression on mean-pooled embeddings predicts held-out programme scores at Spearman rho = 0.25-0.56, UNI2 strongest on all four (immune 0.556). A matched permutation null gives raw p ~ 1e-4 at 10,000 permutations for every cell; Holm-adjusted p = 0.0044. The signal is real but not uniformly morphological. Against competing models on the same patients and folds, embeddings beat tissue composition for ER/luminal, proliferation and immune (+0.280, +0.284, +0.479; p =5/6 drivers.
Related
- Harnessing Adversarial Distillation to Customise Debiased, Disease-Specific Pathology Foundation Models for Breast Cancer
- MOOZY: A Patient-First Foundation Model for Computational Pathology
- Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction
Source: arXiv cs.CV | 2026-08-04