Abstract 5684: A methodology for designing and validating computational pathology scores for immune cell clustering in tumor biopsies

Abstract

Abstract Abstract: Introduction: Immune cell clustering is commonly observed in histopathology images. As the frequency and nature of immune cell clustering may represent biological phenomenon critical to response to immunotherapy, it is an import feature to measure for differentiating immune phenotypes which may predict patient response to immune modulating therapy. Computational pathology data sets and unsupervised machine learning approaches are capable of describing immune cell clustering using a variety of methods. However, it has not been clear how such measurements might be applied to generate a validated computational pathology score that truly captures the immune phenotype sought to score. This work explores a methodology for the development and analytical validation of digital pathology scores for immune cell clustering derived from the application of unsupervised learning to digital pathology data sets. Methods and Experimental Design: Computational pathology data derived with Flagship's cTA™ (Computational Tissue Analysis) platform from 12 NSCLC biopsy samples stained with a validated CD8 -Ki67 duplex IHC assay was used to create a virtual library of scores that described the clustering of CD8+ staining cells. The library was created by using different combinations of clustering methods, parameters, and scoring schemes. Scores with high distinguishability measured through a two-way intraclass correlation coefficient, inter-run precision measured through the coefficient of variation, and dynamic range were considered analytically validated. Principal component analysis and hierarchical clustering of the analytically validated scores were used to further optimize selection of the most informative subset of clustering scores from the library. Results and Conclusions: 17 clustering scores passed the validation criteria. 4 of these 17 scores appear to be relatively uncorrelated with each other and capture unique information about the spatial relationships of CD8 positive cells. A further analysis of these scores demonstrates the ability to distinguish different immune cell clustering profiles in samples that contain similar biomarker expression levels using the common scoring methods of both overall percentage of positive cells and percentage of positive cells per tissue area. This process for screening and analytically validating a virtual library of computational biomarker scores appears to hold much promise for bringing cluster-derived computational pathology scores into future clinical applications in a way that is analogous to analytical validation of traditional IHC assays in support of oncology drug development. Citation Format: Logan Cerkovnik, Karen Ryall, G David Young, Kristen Wilson, Joseph Krueger. A methodology for designing and validating computational pathology scores for immune cell clustering in tumor biopsies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 5684.