Demo: Generative AI helps Radiotherapy Planning with User Preference

TL;DR

This paper presents a generative AI model for radiotherapy planning that allows user preferences to customize dose distributions, improving flexibility and potentially surpassing existing models like Varian RapidPlan.

Contribution

A novel generative model that predicts 3D dose distributions based solely on user-defined preferences, enabling personalized and adaptable radiotherapy plans.

Findings

Outperforms Varian RapidPlan in adaptability and plan quality in some scenarios

Enables customization of trade-offs between organs-at-risk and target volumes

Integrates seamlessly with clinical treatment planning systems

Abstract

Radiotherapy planning is a highly complex process that often varies significantly across institutions and individual planners. Most existing deep learning approaches for 3D dose prediction rely on reference plans as ground truth during training, which can inadvertently bias models toward specific planning styles or institutional preferences. In this study, we introduce a novel generative model that predicts 3D dose distributions based solely on user-defined preference flavors. These customizable preferences enable planners to prioritize specific trade-offs between organs-at-risk (OARs) and planning target volumes (PTVs), offering greater flexibility and personalization. Designed for seamless integration with clinical treatment planning systems, our approach assists users in generating high-quality plans efficiently. Comparative evaluations demonstrate that our method can surpasses the Varian RapidPlan model in both adaptability and plan quality in some scenarios.