OBJECTIVE: To improve risk prediction for oropharyngeal cancer (OPC) patients using cluster analysis on the radiomic features extracted from pre-treatment Computed Tomography (CT) scans.
MATERIALS AND METHODS: OPC Patients were classified into 2 or 3 risk groups by applying hierarchical clustering over the co-occurrence matrix obtained from a random survival forest (RSF) trained over 301 radiomic features. The cluster label was included together with other clinical data to train an ensemble model using five predictive models (Cox, random forest, RSF, logistic regression, and logistic-elastic net). Ensemble performance was evaluated over an independent test set for both recurrence free survival (RFS) and overall survival (OS).
RESULTS: The Kaplan-Meier curves for OS stratified by cluster label show significant differences for both training (p-val<0.0001) and testing (p-val=0.005). Inclusion of the cluster label outperforms clinical data only improving AUC from .60 to .76 and from .63 to .75 for OS and RFS, respectively.
CONCLUSION: The extraction of a single feature, namely a cluster label, to represent the high-dimensional radiomic feature space reduces the dimensionality and sparsity of the data. Moreover, inclusion of the cluster label improves model performance compared to clinical data only and compares to the raw radiomic features performance.