Artificial intelligence-based digital pathology using H&E-stained whole slide images in immuno-oncology: from immune biomarker detection to immunotherapy response prediction

Immuno-oncology and the advent of immunotherapies, in particular immune checkpoint inhibitors (ICIs), have fundamentally altered the way we treat cancer. Yet only a small subset of patients actually responds to ICIs, and many face significant adverse effects, making the accurate selection of patients for ICIs essential to the work of immuno-oncology. Immune biomarkers, such as programmed death-ligand 1, microsatellite instability/defective mismatch repair, and tumor mutational burden have been developed for patient selection and stratification for ICIs, though their predictive abilities remain limited. This is due to several challenges: lack of adequate tissue sampling, the time-consuming and subjective nature of manual visual-based quantification techniques, and the growing recognition of the complexity of the tumor microenvironment, for which these tests cannot fully capture on their own. Meanwhile, emerging technologies in the field of artificial intelligence (AI), such as the performance of deep learning techniques in digital pathology, have garnered significant attention for their potential to be used in this space. Many have now turned their attention towards the immuno-oncology-related applications for digital pathology, particularly in analyzing whole-slide images of widely available H&E-stained slides to aid in immune biomarker detection and ICI response prediction. In this review, we discuss the current landscape of AI-based digital pathology in immuno-oncology, including its applications for identifying and measuring immune biomarkers and, importantly, its potential for predicting ICI response and survival outcomes. We will end by discussing the challenges and future directions of adopting AI technologies for clinical deployment.