DELTA: Training-free and label-free correction of pathology foundation model embeddings through paired counterfactual stain-appearance interventions

Staining and scanning variation impairs pathology foundation model (FM) generalization. We propose DELTA, a training-free, label-free method for post-hoc correction of FM embeddings. DELTA estimates recurrent directions from paired embedding differences between original patches and counterfactual stain-appearance variants preserving spatial structure, then attenuates aligned components through a fixed projection. Estimation from 4% of eligible patches per source dataset required no separately acquired matched images. Operators directly correct stored embeddings. On PathoROB, DELTA improved patch-level representation robustness over raw embeddings in all 20 FMs. Mean classification gains over established correction methods persisted after patch aggregation. DELTA provided additional gains after stain normalization. Whole-slide analyses showed improved in-distribution survival discrimination in TCGA-BRCA and normative cancer screening in a clinical cohort. Operators from TCGA-BRCA reduced embedding variation in the PLISM dataset across 13 staining conditions and 7 scanners without refitting. With projection rank and center matched, DELTA outperformed projections from mismatched pairs in retrieval and tissue-category concordance. Corrected embeddings retained information for spatial gene-expression prediction in the STP-BENCH datasets, with gains for tumor microenvironment markers in selected cohorts.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-19
DOI
https://doi.org/10.64898/2026.11.18.767727
Primary Topic
AI in cancer detection
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

DELTA: Training-free and label-free correction of pathology foundation model embeddings through paired counterfactual stain-appearance interventions

Yoon Ho Choi, Jaewoong Kang, Chulho Kim, Seung‐Ho Shin
bioRxiv (Cold Spring Harbor Laboratory)
AI in cancer detection
preprint

DELTA: Training-free and label-free correction of pathology foundation model embeddings through paired counterfactual stain-appearance interventions

Yoon Ho Choi, Jaewoong Kang, Chulho Kim, Seung‐Ho Shin
preprint en

Abstract

Staining and scanning variation impairs pathology foundation model (FM) generalization. We propose DELTA, a training-free, label-free method for post-hoc correction of FM embeddings. DELTA estimates recurrent directions from paired embedding differences between original patches and counterfactual stain-appearance variants preserving spatial structure, then attenuates aligned components through a fixed projection. Estimation from 4% of eligible patches per source dataset required no separately acquired matched images. Operators directly correct stored embeddings. On PathoROB, DELTA improved patch-level representation robustness over raw embeddings in all 20 FMs. Mean classification gains over established correction methods persisted after patch aggregation. DELTA provided additional gains after stain normalization. Whole-slide analyses showed improved in-distribution survival discrimination in TCGA-BRCA and normative cancer screening in a clinical cohort. Operators from TCGA-BRCA reduced embedding variation in the PLISM dataset across 13 staining conditions and 7 scanners without refitting. With projection rank and center matched, DELTA outperformed projections from mismatched pairs in retrieval and tissue-category concordance. Corrected embeddings retained information for spatial gene-expression prediction in the STP-BENCH datasets, with gains for tumor microenvironment markers in selected cohorts.

bioRxiv (Cold Spring Harbor Laboratory)
Hallym University (KR), Sacred Heart Hospital (NG), Sacred Heart Hospital (US), Hallym University Chuncheon Sacred Heart Hospital (KR)
AI in cancer detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon