Related Experiment Video
Updated: Feb 26, 2026
08:54
Treatment of Liver Metastases Using an Internal Target Volume Method for Stereotactic Body Radiotherapy
Published on: May 8, 2018
15.1K
Heuristic knowledge-based planning for single-isocenter stereotactic radiosurgery to multiple brain metastases
Benjamin P Ziemer1, Parag Sanghvi1, Jona Hattangadi-Gluth1
1Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, USA.
Medical Physics
|July 22, 2017
Summary
Automated knowledge-based planning (KBP) for multiple brain metastases using volumetric-modulated arc therapy (VMAT) stereotactic radiosurgery (SRS) maintained or improved treatment plan quality. This approach adapts single-target dose predictions for complex multimet cases, streamlining patient care.
Area of Science:
- Radiation Oncology
- Medical Physics
- Computational Biology
Background:
- Single-isocenter volumetric-modulated arc therapy (VMAT) stereotactic radiosurgery (SRS) offers precise dose delivery for multiple brain metastases (multimets).
- Treatment planning for multimets is complex due to variations in lesion number, size, and proximity to organs-at-risk (OARs).
Purpose of the Study:
- To automate VMAT planning for multimet cases using a knowledge-based planning (KBP) approach.
- To adapt single-target SRS dose predictions for multiple target scenarios.
Main Methods:
- An artificial neural network (ANN) KBP system trained on single-target SRS plans was used to generate multimet dose predictions.
- Individual lesion dose predictions were merged, and the optimal combination factor was determined by minimizing RMS difference with clinical plans.
- Quality metrics (QMs), including the gradient measure (GM), were compared between clinical and KBP plans; blinded physician review was also conducted.
Main Results:
- The KBP approach yielded dose predictions with minimal difference (ΔGM = 0.00 ± 0.08 cm) compared to clinical plans after conversion to deliverable plans.
- Most QMs were equivalent or showed modest improvements in KBP plans, with notable improvements in normal tissue sparing (e.g., V5Gy, brainstem D0.1cc, chiasm D1%).
- Blinded physician review found KBP plans to be equivalent or superior in 78.1% of cases.
Conclusions:
- Heuristic KBP-driven automated planning effectively maintains or enhances plan quality for linac-based, single-isocenter treatments of multiple brain metastases.
- This automated approach offers a viable solution for the complex planning challenges in multimet SRS.
