PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 5, 2026Cancer Research0 citations

Abstract 75: From single H&E to virtual immunohistochemical biomarker staining in the lung tumor microenvironment.

View Full Paper
KTKenneth K.W. ToCJChristopher JacksonLVLouis Vaickus

Key Points

  • The study aimed to develop and validate a virtual immunohistochemistry platform for analyzing lung tumor microenvironments based on H&E slides.
  • Used a deep learning platform (ViewsML) to train a virtual TME panel for predicting biomarkers.
  • Analyzed 316 lung cancer biopsy slides with over 150 million annotated cells.
  • Optimized neural networks for specific biomarker predictions and evaluated model performance using ROC AUC metrics.
  • Conducted blinded pathologist reviews to compare virtual stains with physical IHC.
  • Virtual biomarkers correlated strongly with physical IHC, achieving AUCs between 0.90 and 0.93 for different markers.
  • Preservation of spatial and morphological features in virtual stains.
  • Quantitative analysis allowed precise assessments of cell fraction, cell ratios, and immune clustering.

Abstract

Abstract Profiling the tumor microenvironment (TME) is fundamental to understanding immune, stromal, and tumor interactions influencing cancer diagnosis, progression, and therapeutic response. Physical immunohistochemistry (IHC) remains essential but is limited by reagent dependency, labor-intensive workflows, and tissue exhaustion. This study aimed to develop and validate a virtual IHC platform to reproduce biomarker staining directly from hematoxylin and eosin (H0.0001). Virtual stains preserved spatial and morphological features, including CD31-positive vascular frameworks at tumor-stroma boundaries, CD45-positive immune infiltration, CD68-positive macrophage aggregates, SMA-positive stromal reaction patterns, and CK-positive tumor epithelium. Quantitative per-cell biomarker expression enabled automated precise cell fraction, cell ratio, spatial proximity, and immune and macrophage clustering analysis. These findings demonstrate that ViewsML’s virtual IHC technology can reproduce physical staining from standard H Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 75.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

To et al. (2026) studied this question.

synapsesocial.com/papers/69d1fceba79560c99a0a2b16https://doi.org/10.1158/1538-7445.am2026-75
Ask AI
Helpful
Bookmark
Share
View Full Paper