DEMO: A Scalable Artificial Intelligence Framework for Rapid EGFR Mutation Screening in Lung Cancer

Abstract

This paper presents two approaches to predict Epidermal Growth Factor Receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients from Hematoxylin and Eosin (H&E) stained histopathology whole slide images (WSIs). The first uses a two-step process: training a vision transformer on histology classification, then using it as a frozen feature extractor for a multiple instance learning (MIL) aggregator. The second implements end-to-end training of a pre-trained foundation model encoder and an MIL aggregator using distributed training. An in-real-time pipeline is presented for rapid clinical EGFR screening. Experiments on a large patient cohort demonstrate effectiveness, with the best model achieving 0.83 AUC and ~2-minute inference time per slide, offering a potential rapid, cost-effective alternative to conventional molecular testing in a live clinical setting.