Abstract

Background: The incidence of oropharyngeal squamous cell carcinoma (OPSCC) has been rapidly increasing. Disease stage and smoking history are often used in current clinical trials to select patients for de-intensification therapy, but these features lack sufficient accuracy for predicting disease relapse. Purpose: To develop an imaging signature to assess early response and predict outcomes of OPSCC. Methods: We retrospectively analyzed 162 OPSCC patients treated with concurrent chemoradiotherapy, equally divided into separate training and validation cohorts with similar clinical characteristics. A robust consensus clustering approach was used to spatially partition the primary tumor and involved lymph nodes into subregions (i.e., habitats) based on fluorine 18 (18F) fluorodeoxyglucose (FDG) PET and contrast CT imaging. We proposed quantitative image features to characterize the temporal volumetric change of the habitats and peritumor/nodal tissue between baseline and mid-treatment. The reproducibility of these features was evaluated. We developed an imaging signature to predict progression-free survival (PFS) by fitting an L1-regularized Cox regression model. Results: We identified three phenotypically distinct intratumoral habitats, which were (1) metabolically active and heterogeneous, (2) enhancing and heterogeneous, and (3) metabolically inactive and homogeneous. The final Cox model consisted of four habitat evolution-based features. In both cohorts, this imaging signature significantly outperformed traditional imaging metrics including mid-treatment metabolic tumor volume for predicting PFS, with C-index: 0.72 vs 0.67 (training) and 0.66 vs 0.56 (validation). The imaging signature stratified patients into high-risk vs low-risk groups with 2-year PFS rates: 59.1% vs 89.4% (HR=4.4, 95% CI: 1.4-13.4, training), and 61.4% vs 87.8% (HR=4.6, 95% CI: 1.7-12.1, validation). It remained an independent predictor of PFS in multivariable analysis adjusting for stage, human papillomavirus status, and smoking history. Conclusion: The proposed imaging signature allows more accurate prediction of disease progression and, if prospectively validated, may refine OPSCC patient selection for risk-adaptive therapy.

View details for DOI 10.2967/jnumed.119.230037

View details for PubMedID 31420498