Journal article
Machine learning driven index of tumor multinucleation correlates with survival and suppressed anti-tumor immunity in head and neck squamous cell carcinoma patients
Oral oncology, Vol.143, pp.106459-106459
08/01/2023
DOI: 10.1016/j.oraloncology.2023.106459
PMCID: PMC10330801
PMID: 37307602
Abstract
•Multinucleation levels vary as a function of disease site and intrinsic tumor biology (e.g. TP53 mutational status).•Multinucleation correlates strongly with survival across head and neck disease sites.•Multinucleation may represent a phenotypic manifestation of exhausted immunity.
Matching treatment intensity to tumor biology is critical to precision oncology for head and neck squamous cell carcinoma (HNSCC) patients. We sought to identify biological features of tumor cell multinucleation, previously shown by us to correlate with survival in oropharyngeal (OP) SCC using a machine learning approach.
Hematoxylin and eosin images from an institutional OPSCC cohort formed the training set (DTr). TCGA HNSCC patients (oral cavity, oropharynx and larynx/hypopharynx) formed the validation set (DV). Deep learning models were trained in DTr to calculate a multinucleation index (MuNI) score. Gene set enrichment analysis (GSEA) was then used to explore correlations between MuNI and tumor biology.
MuNI correlated with overall survival. A multivariable nomogram that included MuNI, age, race, sex, T/N stage, and smoking status yielded a C-index of 0.65, and MuNI was prognostic of overall survival (2.25, 1.07–4.71, 0.03), independent of the other variables. High MuNI scores correlated with depletion of effector immunocyte subsets across all HNSCC sites independent of HPV and TP53 mutational status although the correlations were strongest in wild-type TP53 tumors potentially due to aberrant mitotic events and activation of DNA-repair mechanisms.
MuNI is associated with survival in HNSCC across subsites. This may be driven by an association between high levels of multinucleation and a suppressive (potentially exhausted) tumor immune microenvironment. Mechanistic studies examining the link between multinucleation and tumor immunity will be required to characterize biological drivers of multinucleation and their impact on treatment response and outcomes.
Details
- Title: Subtitle
- Machine learning driven index of tumor multinucleation correlates with survival and suppressed anti-tumor immunity in head and neck squamous cell carcinoma patients
- Creators
- Can F. Koyuncu - The Wallace H. Coulter Department of Biomedical EngineeringMitchell J. Frederick - Baylor College of MedicineLester D.R. Thompson - Head and Neck Pathology Consultations, Woodland Hills, CA, United StatesGermán Corredor - The Wallace H. Coulter Department of Biomedical EngineeringSirvan Khalighi - The Wallace H. Coulter Department of Biomedical EngineeringZelin Zhang - Georgia Institute of TechnologyBolin Song - The Wallace H. Coulter Department of Biomedical EngineeringCheng Lu - The Wallace H. Coulter Department of Biomedical EngineeringReetoja Nag - The Wallace H. Coulter Department of Biomedical EngineeringVidya Sankar Viswanathan - Emory UniversityMichael Gilkey - Atlanta Veterans Administration Medical Center, Atlanta, GA, United StatesKailin Yang - Cleveland ClinicShlomo A. Koyfman - Cleveland ClinicDeborah J. Chute - Cleveland ClinicPatricia Castro - Baylor College of MedicineJames S. Lewis - Vanderbilt University Medical CenterAnant Madabhushi - The Wallace H. Coulter Department of Biomedical EngineeringVlad C. Sandulache - Michael E. DeBakey VA Medical Center
- Resource Type
- Journal article
- Publication Details
- Oral oncology, Vol.143, pp.106459-106459
- DOI
- 10.1016/j.oraloncology.2023.106459
- PMID
- 37307602
- PMCID
- PMC10330801
- NLM abbreviation
- Oral Oncol
- ISSN
- 1368-8375
- eISSN
- 1879-0593
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 08/01/2023
- Academic Unit
- Radiation Oncology
- Record Identifier
- 9984696707702771
Metrics
9 Record Views