A dosiomics approach to treatment outcome modeling in carbon ion radiotherapy for skull base chordomas

To investigate the role of dosiomics features extracted from physical dose (D_PHYS), RBE-weighted dose (D_RBE) and dose-averaged Linear Energy Transfer (LET_d), to predict the risk of local recurrence (LR) in skull base chordoma (SBC) treated with Carbon Ion Radiotherapy (CIRT). Thus, define and evaluate dosiomics-driven tumor control probability (TCP) models.

54 SBC patients were retrospectively selected for this study. A regularized Cox proportional hazard model (r-Cox) and Survival Support Vector Machine (s-SVM) were tuned within a repeated Cross Validation (CV) and patients were stratified in low/high risk of LR. Models' performance was evaluated through Harrell's concordance statistic (C-index), and survival was represented through Kaplan-Meier (KM) curves. A multivariable logistic regression was fit to the selected feature sets to generate a dosiomics-driven TCP model for each map. These were compared to a reference model built with clinical parameters in terms of f-score and accuracy.

The LETd maps reached a test C-index of 0.750 and 0.786 with r-Cox and s-SVM, and significantly separated KM curves. D_PHYS maps and clinical parameters showed promising CV outcomes with C-index above 0.8, despite a poorer performance on the test set and patients stratification. The LETd-based TCP showed a significatively higher f-score (0.67[0.52-0.70], median[IQR]) compared to the clinical model (0.4[0.32-0.63], p < 0.025), while D_PHYS achieved a significatively higher accuracy (D_PHYS: 0.73[0.65-0.79], Clinical: 0.6 [0.52-0.72]).

This analysis supports the role of LETd as relevant source of prognostic factors for LR in SBC treated with CIRT. This is reflected in the TCP modeling, where LETd and D_PHYS showed an improved performance with respect to clinical models.