Inflamed immune phenotype predicts favorable clinical outcomes of immune checkpoint inhibitor therapy across multiple cancer types

Abstract

BackgroundThe inflamed immune phenotype (IIP), defined by enrichment of tumor-infiltrating lymphocytes (TILs) within intratumoral areas, is a promising tumor-agnostic biomarker of response to immune checkpoint inhibitor (ICI) therapy. However, it is challenging to define the IIP in an objective and reproducible manner during manual histopathologic examination. Here, we investigate artificial intelligence (AI)-based immune phenotypes capable of predicting ICI clinical outcomes in multiple solid tumor types.MethodsLunit SCOPE IO is a deep learning model which determines the immune phenotype of the tumor microenvironment based on TIL analysis. We evaluated the correlation between the IIP and ICI treatment outcomes in terms of objective response rates (ORR), progression-free survival (PFS), and overall survival (OS) in a cohort of 1,806 ICI-treated patients representing over 27 solid tumor types retrospectively collected from multiple institutions.ResultsWe observed an overall IIP prevalence of 35.2% and significantly more favorable ORRs (26.3% vs 15.8%), PFS (median 5.3 vs 3.1 months, HR 0.68, 95% CI 0.61 to 0.76), and OS (median 25.3 vs 13.6 months, HR 0.66, 95% CI 0.57 to 0.75) after ICI therapy in IIP compared with non-IIP patients, respectively (p<0.001 for all comparisons). On subgroup analysis, the IIP was generally prognostic of favorable PFS across major patient subgroups, with the exception of the microsatellite unstable/mismatch repair deficient subgroup.ConclusionThe AI-based IIP may represent a practical, affordable, clinically actionable, and tumor-agnostic biomarker prognostic of ICI therapy response across diverse tumor types.

RIGATonI: An R software for Rapid Identification of Genomic Alterations in Tumors affecting lymphocyte Infiltration

“…Our initial model trained with samples selected using Saltz et al annotations was discordant with pathologist annotations. New approaches like Lunit SCOPE IO also use deep learning techniques to estimate immune cells on digital pathology slides 30 . Lunit SCOPE IO was trained on >17,000 H&E images across 24 cancer types 30 .…”

“…New approaches like Lunit SCOPE IO also use deep learning techniques to estimate immune cells on digital pathology slides 30 . Lunit SCOPE IO was trained on >17,000 H&E images across 24 cancer types 30 . This scale of training data would never be possible using manual pathologist review.…”

“…This scale of training data would never be possible using manual pathologist review. Additionally, Lunit SCOPE IO considers the boundaries of the tumor on the histology slide 30 . Importantly, the goal of this software is to predict immunotherapy response not to quantify or qualify inflammation more broadly 30 .…”

“…Additionally, Lunit SCOPE IO considers the boundaries of the tumor on the histology slide 30 . Importantly, the goal of this software is to predict immunotherapy response not to quantify or qualify inflammation more broadly 30 . Lunit SCOPE IO is primarily a clinical tool and does not make available its software for research use on big data repositories.…”