Automated Cyberknife Planning for Complex Central Nervous System Radiosurgery Using a Heuristic Optimization Framework
Abstract
Purpose
CyberKnife radiosurgery provides sub-millimeter targeting accuracy but relies on highly manual planning, often requiring several days and limiting throughput and consistency for time-sensitive cases. Currently, no commercial treatment planning system offers fully automated planning for CyberKnife. This study develops and evaluates a RayStation scripting–based automated planning workflow for complex spine and brain metastases (BM) cases.
Methods
A clinical-goal–driven heuristic CyberKnife planning workflow was implemented in RayStation using scripting for MLC-based treatments. The workflow (i) partitions the PTV into subregions to guide node arrangement and generates shell rings to control conformity and dose fall-off; (ii) translates clinical goals into optimization objectives; and (iii) performs iterative optimization by progressively increasing weights for unmet objectives, tightening OAR constraints, and refining external dose gradients. Multiple candidate plans with varying segment-per-node settings and modulation levels were generated automatically. The optimal plan, balancing dosimetric quality and delivery efficiency, was selected and refined with minimal manual intervention. Planner time and dosimetric metrics (CI, GI, HI, and OAR doses) were compared against clinically delivered CyberKnife Precision plans.
Results
The workflow was evaluated on 11 spine cases (PTV 46.3–438.1 cm³) and 6 BM cases (PTV 1.3–50.9 cm³). Average planner time was reduced to <25 minutes for both spine and BM cases, compared to 0.5–3 days for manual planning. Automated plans achieved comparable or improved plan quality. For spine cases, CI improved from 1.24 to 1.15, HI from 1.75 to 1.69, and GI from 4.40 to 3.92. For BM cases, CI, HI and GI were comparable. OAR maximum doses were comparable. Average treatment time was reduced from 90 to 42 minutes.
Conclusion
This RayStation scripting–based automated CyberKnife planning framework reduces planning time by more than an order of magnitude while maintaining plan quality, offering a practical approach to improve efficiency and standardize high-quality CyberKnife planning.