Integrated radiogenomics analyses allow for subtype classification and improved outcome prognosis of patients with locally advanced HNSCC

Abstract

Patients with locally advanced head and neck squamous cell carcinoma (HNSCC) may benefit from personalised treatment, requiring biomarkers that characterize the tumour and predict treatment response. We integrate pre-treatment CT radiomics and whole-transcriptome data from a multicentre retrospective cohort of 206 patients with locally advanced HNSCC treated with primary radiochemotherapy to classify tumour molecular subtypes based on radiomics, develop surrogate radiomics signatures for gene-based signatures related to different biological tumour characteristics and evaluate the potential of combining radiomics features with full-transcriptome data for the prediction of loco-regional control (LRC). Using end-to-end machine-learning, we developed and validated a model to classify tumours of the atypical subtype (AUC [95% confidence interval] 0.69 [0.53–0.83]) based on CT imaging, observed that CT-based radiomics models have limited value as surrogates for six selected gene signatures (AUC < 0.60), and showed that combining a radiomics signature with a transcriptomics signature consisting of two metagenes representing the hedgehog pathway and E2F transcriptional targets improves the prognostic value for LRC compared to both individual sources (validation C-index [95% confidence interval], combined: 0.63 [0.55–0.73] vs radiomics: 0.60 [0.50–0.71] and transcriptomics: 0.59 [0.49–0.69]). These results underline the potential of multi-omics analyses to generate reliable biomarkers for future application in personalized oncology.

Application of radiogenomics in head and neck cancer: A new tool toward diagnosis and therapy

“…In the ongoing pursuit of biomarker development through the lens of radiogenomics, Meneghetti et al. [56] organized molecular subtypes and employed 10 distinct representative CT scans to categorize 206 patients with untreated HNSCC. The objective of this categorization was to train machine learning algorithms to recognize these distinct features, facilitating subsequent assessments of the prognostic value of locoregional control in HNSCC model validation.…”

“…Meneghetti et al. [56] improved both risk stratification and model calibration by combining CT‐based radiomics with transcriptome metagenes. They found that higher hedgehog metagene values were associated with increased recurrence risk, whereas E2F metagenes showed the opposite trend.…”

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

“…They found out that integrative multiomics (radiomics, genomics, transcriptomics, and proteomics) data have the best OS prediction power followed by radiomics + omics, and single omics. OS analysis via multiomics data and advanced ML modeling is rapidly advancing in other cancer types, such as HNSCC, 28 pancreatic cancer, 29 liver and breast cancer, 25 etc.…”

Application of radiomics-based multiomics combinations in the tumor microenvironment and cancer prognosis

“…Rabasco et al conducted a study on the molecular subtypes of locally advanced HNSCC using radiomics. They successfully improved the prognostic value of localized regional control by combining radiomic and transcriptomic features [ 121 ]. Huang et al employed CT radiomics to differentiate between various molecular subtypes of HNSCC, including RNA-defined HPV status, five DNA methylation isoforms, four gene expression isoforms, and five somatic gene mutations.…”