Research on error classification in gamma analysis on the basis of dosimetric feature engineering and deep learning.

Purpose Gamma analysis serves as a critical safety assurance tool in radiotherapy, yet its broader clinical implementation remains constrained by insufficient error analysis capabilities. To address this limitation, this study proposes a gamma passing rate (GPR) prediction method with error analysis capabilities by integrating dose feature engineering with a dose prediction model. Method The study cohort comprised 26 clinical cases, with 6 cases (1,515 static segments generated from volumetric modulated arc therapy​ (VMAT) plans) allocated for model training and 20 cases (10 step-and-shoot plans with 415 segments and 10 VMAT plans) allocated for testing. A dosimetric feature engineering protocol was used to partition each static segment into five distinct regions on the basis of physical characteristics and error susceptibility patterns. These regional dose distributions served as both model inputs and independent variables for error analysis. The predicted segment doses were subsequently aggregated for plan-level GPR calculations. Model accuracy was first validated through test set predictions, followed by comparative analysis of dose discrepancies at failure and passing points for both measured and predicted values. Results The prediction model demonstrated GPR deviations from measurements of 4.21±12.26%, 2.82±1.91%, and -1.01±2.52% for the segment, step-and-shoot, and VMAT plans, respectively. Regional dose analysis revealed statistically significant differences (p<0.05) in the measured values for Regions 2-5, with classification AUC values of 0.69, 0.64, 0.65, and 0.63, respectively. The predicted values showed comparable discriminative capacities, with AUCs of 0.66, 0.50, 0.59, and 0.57 for the respective regions. Conclusions The integrated approach enables accurate GPR prediction while providing actionable error localization at the control point level. The quantitative error source analysis offers valuable guidance for modifying high-risk treatment plans and demonstrates significant potential for enhancing clinical radiotherapy quality assurance protocols. .