Graph perceiver network for lung tumor and bronchial premalignant lesion stratification from histopathology

Abstract

Bronchial premalignant lesions (PMLs) precede the development of invasive lung squamous carcinoma (LUSC), posing a significant challenge in distinguishing those likely to advance to LUSC from those that might regress without intervention. In this context, we present a novel computational approach, the Graph Perceiver Network (GRAPE-Net), leveraging hematoxylin and eosin (H&E) stained whole slide images (WSIs) to stratify endobronchial biopsies of PMLs across a spectrum from normal to tumor lung tissues. GRAPE-Net outperforms existing frameworks in classification accuracy predicting LUSC, lung adenocarcinoma (LUAD), and non-tumor (normal) lung tissue on The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC) datasets containing lung resection tissues while efficiently generating pathologist-aligned, class-specific heatmaps. The network was further tested using endobronchial biopsies from two data cohorts, containing normal to carcinoma in situ histology, and it demonstrated a unique capability to differentiate carcinoma in situ lung squamous PMLs based on their progression status to invasive carcinoma. The network may have utility in stratifying PMLs for chemoprevention trials or more aggressive follow-up.