Abstract 5783: Integration of AI-powered digital pathology and imaging mass cytometry to identify relevant features of the tumor microenvironment

Abstract Digital pathology coupled to artificial intelligence (AI)-powered approaches are receiving great attention in the oncoimmunology field, as their adoption holds promise to improve current diagnostic workflows and potentiate the analytic outputs. In this work, we aimed at combining different histopathological approaches and AI-aided analytic tools to analyze the ecosystem of tumor tissues. By deploying AI-powered standard H&E and high-dimensional imaging-mass cytometry (IMC) to FFPE tissue samples, we could extract quantitative and standardized features that couldn’t have been easily identified and integrated by eye. One tissue microarray (TMA) slide containing 108 spots of NSCLC specimens (both adenocarcinoma and squamous carcinoma) was stained with H&E and scanned through the Axio Scan.Z1 (ZEISS) to generate high-quality virtual images. A deep learning algorithm was trained and applied to H&E images to identify tumor cells. The consecutive tissue section was stained with metal-labeled antibodies and processed through the Hyperion workflow (StandardBiotools), allowing quantitative detection of a panel of 23 markers related to tumor cells (Pan-cytokeratin), tissue architecture (aSMA, Vimentin, CD31, Collagen I, nuclei), CD45+ immune cells, comprehensive of myeloid cells (CD68, CD14, CD16, CD163, CD63, CCR4), lymphoid cells (CD3, CD4, CD8, FOXP3, CD20) and immune activation (S100A8, HLA-DR, Granzyme-B, KI67, Arginase-1). Data were exported as MCD files, visualized using the MCD viewer and further analyzed with the Qupath software. Cell segmentation was performed by the CellProfiler and Ilastik softwares and main cell populations were identified by a supervised approach through Cytomap. On H&E images, we generated a classifier of tumor heterogeneity, by exploring the spatial localization of tumor cells with the K-function summary statistic, which analyzes the distribution of tumor cells as a function of their distance. The resulting K-score value was then used to classify each tumor spot as diffuse, poorly clustered or highly clustered. Multiparametric computational analysis of the IMC images allowed to grasp immune and stromal classifiers, including frequency of immune cell populations in the tumor nests versus fibrotic stroma and immune cell interactions. In conclusion, AI-powered analysis of H&E slides is a robust approach that can improve manual scoring and unlock tissue relevant features opening to new diagnostic possibilities. Meanwhile, the analysis of the immune ecosystem by multiparametric imaging mass cytometry allows investigating spatial patterns and cell interactions at single-cell level. Integration of these approaches is feasible and allows the identification of tumor patient profiles with clinical relevance. Citation Format: Alessandra Rigamonti, Marika Viatore, Rebecca Polidori, Marco Erreni, Maria Fumagalli, Daoud Rahal, Massimo Locati, Alberto Mantovani, Federica Marchesi. Integration of AI-powered digital pathology and imaging mass cytometry to identify relevant features of the tumor microenvironment. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5783.