Computational Mapping of Reactive Stroma in Prostate Cancer Yields Interpretable, Prognostic Biomarkers

TL;DR

This paper introduces PROTAS, a deep learning tool that quantifies reactive stroma in prostate cancer histology slides, providing interpretable biomarkers that improve prognosis and outperform pathologists in detection.

Contribution

PROTAS is a novel deep learning framework that accurately quantifies reactive stroma in prostate cancer, linking morphology to biology and enhancing prognostic predictions.

Findings

PROTAS detects reactive stroma robustly across datasets.

PROTAS outperforms pathologists in stromal detection.

Spatial stromal features predict recurrence independently.

Abstract

Current histopathological grading of prostate cancer relies primarily on glandular architecture, largely overlooking the tumor microenvironment. Here, we present PROTAS, a deep learning framework that quantifies reactive stroma (RS) in routine hematoxylin and eosin (H&E) slides and links stromal morphology to underlying biology. PROTAS-defined RS is characterized by nuclear enlargement, collagen disorganization, and transcriptomic enrichment of contractile pathways. PROTAS detects RS robustly in the external Prostate, Lung, Colorectal, and Ovarian (PLCO) dataset and, using domain-adversarial training, generalizes to diagnostic biopsies. In head-to-head comparisons, PROTAS outperforms pathologists for RS detection, and spatial RS features predict biochemical recurrence independently of established prognostic variables (c-index 0.80). By capturing subtle stromal phenotypes associated with tumor progression, PROTAS provides an interpretable, scalable biomarker to refine risk stratification.