A Radiomics Approach to Identify Immunologically Active Tumor in Patients with Head and Neck Squamous Cell Carcinomas

Simple Summary: We recently established a biological classification of head and neck cancers into hot and cold tumors, which were associated with different responses to immunotherapy (a type of cancer treatment helping the immune system fight cancer). Because this classification requires a tumor biopsy, the development of a non-invasive approach, based on imaging data, would be relevant to determine this hot/cold tumor status without performing an invasive biopsy. Thus, our goal was to determine whether imaging data from computed tomography (CT) scans can distinguish hot and cold head and neck squamous cell carcinomas (HNSCCs). Using biological and clinical imaging data from two independent cohorts, we established a computational model to determine the hot/cold status from the CT scan. This non-invasive approach, based on a "virtual" biopsy, could help for the identification and monitoring of patients with HNSCC who may benefit from immunotherapy. Background: We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC. Method: We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitie-Salpetriere (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort. Results: A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset. Conclusions and Relevance: We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.