Development and evaluation of a unified machine-learning model for predicting normal brain toxicity in single isocenter multi-target stereotactic radiosurgery
Zhuoyun Huang, Jingtong Zhao, Ke Lu, John S Ginn, Zhenyu Yang, Yibo Xie, Yongbok Kim, Trey C Mullikin and Chunhao Wang
Purpose: To develop and evaluate a machine learning model for normal brain dose outcome in linear-accelerator-based single isocenter multiple target (SIMT) stereotactic radiosurgery (SRS).
Methods: SIMT SRS cases collected totaled 231, and 181/50 cases were randomly assigned for model training/testing. The model characterizes SIMT cases using seven geometric and statistical features describing prescription, target burden, and inter-target spatial relationships. Gradient boosted tree (GBT) regression was employed to predict three dosimetric outcomes: overall V50%, V60%, and V66.7%. Five hyperparameters were optimized through grid search and 10-fold cross-validation.
Four models were trained: the first model (Ma,s) predicts all three outcomes as a single output, and the second model (Ma,m) uses three GBTs to report each outcome. In the third (Mc,s) and fourth (Mc,m) models, unsupervised k-means cluster partitioned training samples into geometrically distinct groups based on statistical features, and the models were trained using clustered samples for single or multiple outputs, respectively. Model performance was evaluated using normalized mean absolute error (MAE), mean prediction uncertainty (MPU), and R2.
Results: Ma,s achieved the best overall performance, with an average MAE of 6.12 cm3, MPU of 7.81 cm3 and R2 = 0.88. Clustering slightly improved relative error in Mc,m but increased absolute errors and reduced overall performance in Mc,s. Each prediction required under 5 s. An Eclipse Scripting Application Programming Interface script was developed to integrate the model into the EclipseTM treatment planning system.
Conclusions: The machine-learning framework was developed and validated for predicting SIMT SRS normal-brain dose. By providing accurate and reliable dosimetric predictions, the model supports efficient treatment planning and reduces plan quality variability.
Keywords: SRS, SIMT, machine learning, GBT, plan quality
Full Text (IP)
Purchase Article (PDF)