Poster Poster Program Therapy Physics

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.

People

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
Python-Based Automation Framework for Annual Machine QA Data Archiving In Qatrack+

Annual water-tank measurements help ensure beam characteristics remain consistent with commissioning baselines. However, the lack of a standardized processing workflow and decentralized data storage makes it difficult to analyze...

Syed Bilal Ahmad, PhD
Therapy Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
User Expectations and Current Availability of HDR Brachytherapy Audits In Europe

The aim of this work was to evaluate the need to implement more dosimetric audits in high‐dose‐rate brachytherapy (HDR-BT) in Europe and to identify which characteristics such audits should meet according to users.

Javier Vijande, PhD Laura Oliver Cañamás
Therapy Physics 0 people interested