Automating RT Planning at Scale: High Quality Data For AI Training

TL;DR

The paper addresses the data scarcity and heterogeneity that hinder AI in radiotherapy planning by introducing AIRTP, a scalable end-to-end pipeline that automates contouring, structure creation, beam configuration, optimization, and iterative plan refinement guided by scorecards. It also introduces a method to translate 3D dose predictions into deliverable plans under machine constraints, and demonstrates comparable plan quality to manual planning with substantial time savings. A nine-cohort HMM-RT public dataset is released to support an AAPM 2025 challenge, providing more than an order of magnitude more plans than prior public data and facilitating broad AI research in RT. The work presents a foundation for large-scale AI training in radiotherapy, enabling benchmarking, data-driven improvement, and exploration of related tasks such as dose prediction and fluence optimization.

Abstract

Radiotherapy (RT) planning is complex, subjective, and time-intensive. Advances with artificial intelligence (AI) promise to improve its precision and efficiency, but progress is often limited by the scarcity of large, standardized datasets. To address this, we introduce the Automated Iterative RT Planning (AIRTP) system, a scalable solution for generating high-quality treatment plans. This scalable solution is designed to generate substantial volumes of consistently high-quality treatment plans, overcoming a key obstacle in the advancement of AI-driven RT planning. Our AIRTP pipeline adheres to clinical guidelines and automates essential steps, including organ-at-risk (OAR) contouring, helper structure creation, beam setup, optimization, and plan quality improvement, using AI integrated with RT planning software like Varian Eclipse. Furthermore, a novel approach for determining optimization parameters to reproduce 3D dose distributions, i.e. a method to convert dose predictions to deliverable treatment plans constrained by machine limitations is proposed. A comparative analysis of plan quality reveals that our automated pipeline produces treatment plans of quality comparable to those generated manually, which traditionally require several hours of labor per plan. Committed to public research, the first data release of our AIRTP pipeline includes nine cohorts covering head-and-neck and lung cancer sites to support an AAPM 2025 challenge. To our best knowledge, this dataset features more than 10 times number of plans compared to the largest existing well-curated public dataset. Repo: https://github.com/RiqiangGao/GDP-HMM_AAPMChallenge.

Figures (22)

• Figure 1: Datasets of representative AI models across various domains (see Appendix \ref{['sec:data_scale']} for details). Most existing works in "RT Planning" with AI are based on approximately 1,000 or fewer treatment plans, significantly smaller than the data scale used in representative successful AI models. Additionally, the majority of RT studies rely on private datasets, limiting reproducibility and scalability. "Our RT Datasets with AIRTP" aim to bridge data gaps between RT research and vision domains.
• Figure 2: Illustration of automated iterative RT planning (AIRTP) pipeline. The auto contouring, helper structures are executed with C++/python code. Curated CT and RTSTRUCT data are stored in DICOM format, and then imported into Eclipse system. Beam configuration, RapidPlan setup, photon optimization, dose calculation, quality assessment are conducted with Eclipse Scripting API. A full data curation pipeline are appended in Fig. \ref{['fig:curation']}.
• Figure 3: (a) shows the process that increase the quality of planning iteratively. (b) demonstrates the method translating predicted 3D dose to a deliverable plan. The way of defining objectives of above two pipelines are the same.
• Figure 4: Examples of head-and-neck (upper) and lung (lower) cancer treatment plans. In released HMM-RT dataset, each lung cancer patient is assigned two plans: one IMRT and one VMAT; while each head-and-neck cancer patient receives three plans: two IMRT and one VMAT.
• Figure 5: The DVH comparisons between our plans and clinical plans are shown, with dashed lines representing clinical plans and solid lines representing plans generated by our AIRTP pipeline.