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

Jakob Einhaus; Dyani K Gaudilliere; Julien Hedou; Dorien Feyaerts; Michael G Ozawa; Masaki Sato; Edward A Ganio; Amy S Tsai; Ina A Stelzer; Karl C Bruckman; Jonas N Amar; Maximilian Sabayev; Thomas A Bonham; Joshua Gillard; Maïgane Diop; Amelie Cambriel; Zala N Mihalic; Tulio Valdez; Stanley Y Liu; Leticia Feirrera; David K Lam; John B Sunwoo; Christian M Schürch; Brice Gaudilliere; Xiaoyuan Han

doi:10.1016/j.isci.2023.108486

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

iScience. 2023 Nov 20;26(12):108486. doi: 10.1016/j.isci.2023.108486. eCollection 2023 Dec 15.

Authors

Jakob Einhaus^{1

2}, Dyani K Gaudilliere³, Julien Hedou¹, Dorien Feyaerts¹, Michael G Ozawa⁴, Masaki Sato¹, Edward A Ganio¹, Amy S Tsai⁵, Ina A Stelzer¹, Karl C Bruckman³, Jonas N Amar¹, Maximilian Sabayev¹, Thomas A Bonham¹, Joshua Gillard¹, Maïgane Diop¹, Amelie Cambriel¹, Zala N Mihalic¹, Tulio Valdez⁶, Stanley Y Liu^{3

7}, Leticia Feirrera⁸, David K Lam⁸, John B Sunwoo⁹, Christian M Schürch^{2

10}, Brice Gaudilliere¹, Xiaoyuan Han¹¹

Affiliations

¹ Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University School of Medicine, Stanford, CA, USA.
² Department of Pathology and Neuropathology, University Hospital and Comprehensive Cancer Center Tübingen, Tübingen, Germany.
³ Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA.
⁴ Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA.
⁵ Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA.
⁶ Division of Pediatrics, Department of Otolaryngology, Stanford University School of Medicine, Stanford, CA, USA.
⁷ Division of Sleep Surgery, Department of Otolaryngology, Stanford University School of Medicine, Stanford, CA, USA.
⁸ Department of Oral and Maxillofacial Surgery, University of the Pacific, Arthur A. Dugoni School of Dentistry, San Francisco, CA, USA.
⁹ Division of Head and Neck Surgery, Department of Otolaryngology, Stanford University School of Medicine, Stanford, CA, USA.
¹⁰ Cluster of Excellence iFIT (EXC 2180) "Image-Guided and Functionally Instructed Tumor Therapies", University of Tübingen, Tübingen, Germany.
¹¹ Department of Biomedical Sciences, University of the Pacific, Arthur A. Dugoni School of Dentistry, San Francisco, CA, USA.

Abstract

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.

Keywords: Cancer; Cell biology; Immunology; Machine learning.

Abstract

Grants and funding