Automated tumor immunophenotyping predicts clinical benefit from anti-PD-L1 immunotherapy

Abstract

Background. Cancer immunotherapy has transformed the clinical approach to patients with malignancies as profound benefits can be seen in a subset of patients. To identify this subset, biomarker analyses increasingly focus on phenotypic and functional evaluation of the tumor microenvironment (TME) to determine if density, spatial distribution, and cellular composition of immune cell infiltrates can provide prognostic and/or predictive information. Attempts have been made to develop standardized methods to evaluate immune infiltrates in the routine assessment of certain tumor types; however, broad adoption of this approach in clinical decision-making is still missing. Methods. We developed approaches to categorize solid tumors into "Desert", "Excluded" and "Inflamed" types according to the spatial distribution of CD8+ immune effector cells to determine the prognostic and/or predictive implications of such labels. To overcome the limitations of this subjective approach we incrementally developed four automated analysis pipelines of increasing granularity and complexity for density and pattern assessment of immune effector cells. Results. We show that categorization based on "manual" observation is predictive for clinical benefit from anti-programmed cell death ligand-1 (PD-L1) therapy in two large cohorts of patients with non-small cell lung cancer (NSCLC) or triple-negative breast cancer (TNBC). For the automated analysis we demonstrate that a combined approach outperforms individual pipelines and successfully relates spatial features to pathologist-based read-outs and patient response to therapy. Conclusions. Our findings suggest tumor immunophenotype (IP) generated by automated analysis pipelines should be evaluated further as potential predictive biomarkers for cancer immunotherapy.