Spatial subsetting enables integrative modeling of oral squamous cell carcinoma multiplex imaging data

• Published in: iScience 2023-12, Vol.26 (12), p.108486, Article 108486
• Main Authors: Einhaus, Jakob, Gaudilliere, Dyani K., Hedou, Julien, Feyaerts, Dorien, Ozawa, Michael G., Sato, Masaki, Ganio, Edward A., Tsai, Amy S., Stelzer, Ina A., Bruckman, Karl C., Amar, Jonas N., Sabayev, Maximilian, Bonham, Thomas A., Gillard, Joshua, Diop, Maïgane, Cambriel, Amelie, Mihalic, Zala N., Valdez, Tulio, Liu, Stanley Y., Feirrera, Leticia, Lam, David K., Sunwoo, John B., Schürch, Christian M., Gaudilliere, Brice, Han, Xiaoyuan
• Format: Article
• Language: English
• Subjects: Cancer; Cell biology; Immunology; Machine learning
• ISSN: 2589-0042; 2589-0042
• DOI: 10.1016/j.isci.2023.108486

Oral squamous cell carcinoma (OSCC), a prevalent and aggressive neoplasm, poses a significant challenge due to poor prognosis and limited prognostic biomarkers. Leveraging highly multiplexed imaging mass cytometry, we investigated the tumor immune microenvironment (TIME) in OSCC biopsies, characterizing immune cell distribution and signaling activity at the tumor-invasive front. Our spatial subsetting approach standardized cellular populations by tissue zone, improving feature reproducibility and revealing TIME patterns accompanying loss-of-differentiation. Employing a machine-learning pipeline combining reliable feature selection with multivariable modeling, we achieved accurate histological grade classification (AUC = 0.88). Three model features correlated with clinical outcomes in an independent cohort: granulocyte MAPKAPK2 signaling at the tumor front, stromal CD4+ memory T cell size, and the distance of fibroblasts from the tumor border. This study establishes a robust modeling framework for distilling complex imaging data, uncovering sentinel characteristics of the OSCC TIME to facilitate prognostic biomarkers discovery for recurrence risk stratification and immunomodulatory therapy development. [Display omitted] •We developed a robust framework for integrative, multivariable analysis of IMC data•Subsetting of IMC images into spatial tissue zones improves feature reproducibility•Cell type-specific immune activation differs between tissue zones in OSCC•Immune features of OSCC tissue zones are associated with tumor grade and outcomes Immunology; Cell biology; Cancer; Machine learning