Automatic Treatment Planning for Radiation Therapy: A Cross-Modality and Protocol Study

This study investigated the applicability of 3-dimensional dose predictions from a model trained on one modality to a cross-modality automated planning workflow. Additionally, we explore the impact of integrating a multicriteria optimizer (MCO) on adapting predictions to different clinical preferences.

Using a previously created 3-stage U-Net in-house model trained on the 2020 American Association of Physicists in Medicine OpenKBP challenge data set (340 head and neck plans, all planned using 9-field static intensity modulated radiation therapy [IMRT]), we retrospectively generated dose predictions for 20 patients. These dose predictions were, in turn, used to generate deliverable IMRT, VMAT, and tomotherapy plans using the fallback plan functionality in Raystation. The deliverable plans were evaluated against the dose predictions based on primary clinical goals. A new set of plans was also generated using MCO-based optimization with predicted dose values as constraints. Delivery QA was performed on a subset of the plans to assure clinical deliverability.

The mimicking approach accurately replicated the predicted dose distributions across different modalities, with slight deviations in the spinal cord and external contour maximum doses. MCO optimization significantly reduced doses to organs at risk, which were prioritized by our institution while maintaining target coverage. All tested plans met clinical deliverability standards, evidenced by a gamma analysis passing rate >98%.

Our findings show that a model trained only on IMRT plans can effectively contribute to planning across various modalities. Additionally, integrating predictions as constraints in an MCO-based workflow, rather than direct dose mimicking, enables a flexible, warm-start approach for treatment planning, although the benefit is reduced when the training set differs significantly from an institution's preference. Together, these approaches have the potential to significantly decrease plan turnaround time and quality variance, both at high-resource medical centers that can train in-house models and smaller centers that can adapt a model from another institution with minimal effort.