Tissue-based investigations can prove to be challenging due to complex tissue architecture, heterogeneous biomarker expression, visual and cognitive “traps” that affect interpretive precision, and subjective assessments that affect reproducibility. A major concern is that these challenges could increase the risk of failure for therapeutic/diagnostic codevelopment and clinical use since the biomarker measurements continue to increase in complexity and require increasingly precise diagnostic cut-points. Image analysis tools have been developed to overcome some of the challenges of conventional anatomic pathology practices, capitalizing on the objectivity and computational power of a digital platform. A computer, however, lacks the cognitive ability and experience of a human to interpret tissue architecture and context. Flagship Biosciences’ Computational Tissue Analysis (cTA™) platform integrates the power of its Tissue Image Analysis (tIA™) technology with the contextual experience of an anatomic pathologist to produce robust, precise, quantitative results that demonstrate biomarker content in the tissue context. Flagship Biosciences envisions the integration of its cTA™ technology into a computer aided clinical pathology workflow as a method to improve the precision of scoring for even some of the most challenging tissue-based biomarker measurements.
In a proof-of-concept study, Flagship Biosciences evaluated the performance of manual versus digital scoring approaches in a cohort of non–small cell lung cancer (NSCLC) samples stained with the immunohistochemistry (IHC) protocol for the PD-L1 28-8 pharmDx complementary diagnostic. A comparison of the 2 modalities demonstrated that in nearly all cases, the within sample standard deviation of the cTA™ digital score was less than that of the manual score (median interpathologist percent coefficients of variation [%CVs] were reduced from 124.9% to 7.8% and intrapathologist %CVs were reduced from 65.4% to 7.6% for manual and digital scores, respectively). As an additional exploratory examination, the effect of heterogeneity on PD-L1 interpretation was also investigated. Pathologists evaluated the same whole-tissue slides within 5 high-powered fields (HPFs) using both manual and cTA™-derived scoring. Scores from these HPFs were combined to create a single score of percent positive PD-L1 cells and were compared with whole-slide scores derived by both manual scoring estimations and cTA™-based whole-slide calculations. Results demonstrated that the use of cTA™ provides improved agreement between HPF and whole-slide assessments. Finally, when both modalities are compared to a reference standard, each method demonstrates a positive correlation to the orthogonal method, with image analysis showing a slightly better correlation than manual scoring (Spearman correlations were 0.80 and 0.74, respectively). Taken together, these studies demonstrate that the use of cTA™ as opposed to manual scoring can significantly reduce variability in PD-L1 scoring.