ESTRO 2025 - Abstract Book

S2846

Physics - Dose prediction, optimisation and applications of photon and electron planning

ESTRO 2025

Conclusion: We introduce the first LLM-powered plugin that mimics the behavior of expert human planners within a widely used commercial TPS like Eclipse. By automating the treatment planning process, including adjusting optimization parameters and modifying planning objectives, GPT-RadPlan streamlines workflow and has the potential to standardize plan quality.

Keywords: Autoplanning, large language models, deep learning