A Deep Learning Framework Integrating Tumor Microenvironmental Features Accurately Predicts Multiple Driver Gene Mutations in Lung Cancer Pathology Images.

Abstract

Deep learning (DL) has the potential to enable the prediction of gene mutations directly from routine histopathology slides in lung cancer. However, existing approaches have largely been limited to mutation-level prediction and have not achieved precise identification of driver mutation subtypes nor exonic variants, constraining the translation of DL into targeted therapy. In this study, we assembled a large multicenter dataset of paired pathology images and next-generation sequencing from 2,573 patients with lung cancer from four hospitals in China. The development of NAVF-Bio, an adaptive multiview feature fusion framework based on multiple instance learning, enabled the integration of tumor microenvironment (TME) features from whole-slide images (WSI) to predict driver mutations and tumor mutational burden (TMB). Benchmarking against 11 state-of-the-art DL methods indicated that NAVF-Bio consistently outperformed existing models in predicting driver mutations (TP53, EGFR, KRAS, ALK) and TMB status, achieving clinically relevant performance in external multicenter validation. Notably, NAVF-Bio accurately predicted the mutated driver gene exons across centers, whereas interpretability analyses using WSI visualization and TME quantification further demonstrated the ability of NAVF-Bio to elucidate pathologically relevant tumor features. Finally, a multigene mutation prediction platform for lung cancer was generated to facilitate the screening of driver gene mutations. Overall, NAVF-Bio mimics the workflow of pathologists when examining slides by observing multiscale features of WSIs and TME characteristics to predict driver gene mutations in lung cancer, which could guide the selection of targeted therapies for patients. The NAVF-Bio framework accurately predicts key driver gene mutations in lung cancer from routine pathology slides, offering opportunities for the application of AI in precision oncology.