Automatic treatment planning for radiotherapy: a cross-modality and protocol study

This study investigates the applicability of 3D dose predictions from a model trained on one modality to a cross-modality automated planning workflow. Additionally, we explore the impact of integrating a multi-criteria optimizer on adapting predictions to different clinical preferences. Using a previously created three-stage UNet in-house model trained on the 2020 AAPM OpenKBP challenge dataset (340 head and neck plans, planned using 9-field static IMRT), we retrospectively generated dose predictions for 20 patients. These dose predictions were 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. The mimicking approach accurately replicated the predicted dose distributions across different modalities, with slight deviations in spinal cord and external contour maximum doses. MCO customization significantly reduced doses to OARs prioritized by our institution while maintaining target coverage. All tested plans met clinical deliverability standards, evidenced by a delivery QA gamma analysis passing rate above 98 Our findings show that a model trained only on IMRT plans can 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. 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.