Physics-informed machine learning for predicting MLC and gantry errors in VMAT: a feature engineering approach

This study presents a physics-informed, feature-engineered machine learning (ML) framework to predict multileaf collimator (MLC) and gantry positional errors in volumetric modulated arc therapy (VMAT) METHODS: Data from 32 VMAT trajectory logs (TrueBeam linac, HD120 MLC) were synchronized with DICOMRT plans to extract delivery dynamics. Novel physics-based parameters were introduced: a friction factor, an enhanced gravity vector, and MLC speed-normalized features. Three ML models XGBoost, LightGBM, and deep neural networks (DNNs) were optimized using Optuna and trained on trajectory log and DICOM-RT-derived datasets. Feature importance was evaluated via Spearman correlation, mutual information, and SHapley Additive Explanations (SHAP).

Systematic discrepancies between DICOM-RT and trajectory log data were identified, with mean absolute deviations of 7.0 % (MLC speed), 8.0 % (gantry speed), and 8.5 % (dose rate). MLC speed emerged as the dominant predictor (Spearman: r_s = 0.891), while friction and gravity features exhibited significant correlations (r_s = 0.46 and 0.33, respectively). Mutual information revealed non-monotonic dependencies between gantry error and gantry angle (score: 0.34). LightGBM and XGBoost achieved superior MLC error prediction (MAE: 0.0019 mm, RMSE: 0.0027 mm), capturing > 90 % of observed errors, while DNNs lagged by 30 %. Engineered features reduced residual errors by 30 %. Gantry error predictions showed lower accuracy (MAE: 0.012°-0.015°). SHAP analysis highlighted physics-driven features as top contributors.

This work underscores the critical role of domain knowledge in ML for radiotherapy, achieving a 30% error reduction through physics-based feature engineering. The findings advocate for prioritizing feature space exploration alongside model optimization to enhance VMAT quality assurance.