Technical Report: Development and Implementation of an Open Source Template Interpretation Class Library for Automated Treatment Planning

Purpose: Widespread implementation of automated treatment planning in radiation therapy remains elusive owing to variability in clinic and physician preferences, making it difficult to ensure consistent plan parameters. We have developed an open-source class library with the aim to improve efficiency and consistency for automated treatment planning in radiation therapy.

Methods and materials: An open-source class library has been developed that interprets clinical templates within a commercial treatment planning system into a treatment plan for automated planning. This code was leveraged for the automated planning of 39 patients and retrospectively compared with the 78 clinically approved manual plans.

Results: From the initial 39 patients, 74 of 78 plans were successfully generated without manual intervention. The target dose was more homogeneous for automated plans, with an average homogeneity index of 3.30 for manual plans versus 3.11 for automated plans (P = .107). The generalized equivalent uniform dose (gEUD) was decreased in the femurs and rectum for automated plans, with a mean gEUD of 3746 cGy versus 3338 cGy (P ≤ 0.001) and 5761 cGy versus 5634 cGy (P ≤ 0.001) for the femurs and rectum, respectively. Dose metrics for the bladder and rectum (V6500 cGy and V4000 cGy) showed recognizable but insignificant improvements. All automated plans delivered for quality assurance passed a gamma analysis (>95%), with an average composite pass rate of 99.3% for pelvis plans and 98.8% for prostate plans. Deliverability parameters such as total monitor units and aperture complexity indicated deliverable plans.

Conclusions: Prostate cancer and pelvic node radiation therapy can be automated using volumetric modulated arc therapy planning and clinical templates based on a standardized clinical workflow. The class library developed in this study conveniently interfaced between the plan template and the treatment planning system to automatically generate high-quality plans on customizable templates.