Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Images

TL;DR

OmniScreen is an AI system that rapidly predicts a wide range of molecular biomarkers from routine cancer tissue images, offering a cost-effective alternative to traditional molecular assays with high accuracy across diverse tumor types.

Contribution

This work introduces OmniScreen, a unified AI model that predicts multiple biomarkers simultaneously from H&E images, including rare targets, improving efficiency over traditional single-biomarker models.

Findings

OmniScreen accurately predicts biomarkers across various cancers.

The model performs well even with small tumor areas.

Biomarker prediction correlates with tumor size and histologic features.

Abstract

Molecular assays are standard of care for detecting genomic alterations in cancer prognosis and therapy selection but are costly, tissue-destructive and time-consuming. Artificial intelligence (AI) applied to routine hematoxylin and eosin (H&E)-stained whole slide images (WSIs) offers a fast and economical alternative for screening molecular biomarkers. We introduce OmniScreen, a high-throughput AI-based system leveraging Virchow2 embeddings extracted from 60,529 cancer patients with paired 489-gene MSK-IMPACT targeted biomarker panel and WSIs. Unlike conventional approaches that train separate models for each biomarker, OmniScreen employs a unified model to predict a broad range of clinically relevant biomarkers across cancers, including low-prevalence targets impractical to model individually. OmniScreen reliably identifies therapeutic targets and shared phenotypic features across common and rare tumors. We investigate the biomarker prediction probabilities and accuracies of OmniScreen in relation to tumor area, cohort size, histologic subtype alignment, and pathway-level morphological patterns. These findings underscore the potential of OmniScreen for routine clinical screening.