Pan-cancer estimation of prognostic immune biomarkers from histopathology using artificial intelligence
- 1Dana-Farber Cancer Institute
Abstract
Multiplex immunofluorescence (mIF) assays such as ImmunoProfile provide standardized quantification of prognostic immune markers but are costly and not routinely used in clinical settings. We developed a weakly-supervised AI model, HistoProfile, to estimate intratumoral cell densities of key immune biomarkers (CD8, FOXP3, PD-1, and PD-L1) and the PD-L1 tumor proportion score from routine H&E-stained whole-slide images. Trained on a large pan-cancer cohort with paired H&E and mIF data, HistoProfile discriminated biomarker-high from biomarker-low tumors in held-out samples and tumor-specific subgroups (AUROCs of 0.78-0.89 across biomarkers). Critically, the estimated biomarkers preserved prognostic stratification in downstream survival analyses, and showed cancer-specific survival associations across TCGA cohorts where mIF is unavailable. These findings support scalable H&E-based estimation of key immune biomarker measurements for large-scale immune profiling and risk stratification.
Related
- Converging Paths: Artificial Intelligence for Integrating Biological and Digital Biomarkers in Personalized Longevity Medicine
- Integrating biomarkers and artificial intelligence for precision diagnostics in cattle health and herd management: a review
- Early Structure–Function Correlates in Neovascular Age-Related Macular Degeneration Using Artificial Intelligence–Derived OCT Biomarkers
- Morphologic intratumoral heterogeneity from routine whole-slide histopathology is prognostic for survival in primary central nervous system lymphoma: development in the LOC Network and international external validation
- Granulomatous lobular mastitis: diagnostic and prognostic biomarkers
BibTeX
@misc{li2026pancancer,
title = {{Pan-cancer estimation of prognostic immune biomarkers from histopathology using artificial intelligence}},
author = {Y. Li and A. R. Diab and A. Lamane and J. R. Lindsay and S. J. Rodig and R. A. Irizarry and W. Lotter},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.06.757083},
url = {https://www.biorxiv.org/content/10.64898/2026.10.06.757083v1},
note = {Public domain},
}
RIS
TY - UNPB
TI - Pan-cancer estimation of prognostic immune biomarkers from histopathology using artificial intelligence
AU - Y. Li
AU - A. R. Diab
AU - A. Lamane
AU - J. R. Lindsay
AU - S. J. Rodig
AU - R. A. Irizarry
AU - W. Lotter
PY - 2026
DA - 2026/10/06
PB - bioRxiv
DO - 10.64898/2026.10.06.757083
UR - https://www.biorxiv.org/content/10.64898/2026.10.06.757083v1
AB - Multiplex immunofluorescence (mIF) assays such as ImmunoProfile provide standardized quantification of prognostic immune markers but are costly and not routinely used in clinical settings. We developed a weakly-supervised AI model, HistoProfile, to estimate intratumoral cell densities of key immune biomarkers (CD8, FOXP3, PD-1, and PD-L1) and the PD-L1 tumor proportion score from routine H&E-stained whole-slide images. Trained on a large pan-cancer cohort with paired H&E and mIF data, HistoProfile discriminated biomarker-high from biomarker-low tumors in held-out samples and tumor-specific subgroups (AUROCs of 0.78-0.89 across biomarkers). Critically, the estimated biomarkers preserved prognostic stratification in downstream survival analyses, and showed cancer-specific survival associations across TCGA cohorts where mIF is unavailable. These findings support scalable H&E-based estimation of key immune biomarker measurements for large-scale immune profiling and risk stratification.
ER -