Integration of single-click, AI-based brachytherapy auto-planning for cervical cancer within a treatment planning system
Previous work developed an automated cervical brachytherapy treatment planning pipeline consisting of a U-Net dose prediction model and dwell time optimizer. While this method can produce clinically acceptable plans, it relies on time-consuming, manual export and import of DICOM data. This study proposes to increase efficiency by combining scripts into an all-in-one tool that can be used directly within the BrachyVision treatment planning system, producing automated plans in a single click. We developed an AI-based planning tool through four main tasks; data retrieval, model inference, dwell time optimization, and auto-plan import. First, a C# plug-in interacts with the currently open patient in BrachyVision. Next, for data retrieval, model inference, and dwell time optimization, a Python executable operates on the data before the optimized dwell times are copied back into the open plan in BrachyVision. The script was tested on 28 brachytherapy plans spanning 7 applicator types, and auto-plans were compared to clinical plans using mean absolute error (MAE) in voxel-based 3D dose and dwell times. The average (± standard deviation) MAE in 3D dose and dwell times were 3.8 ± 0.7% (normalized to the prescribed dose) and 10.3 ± 7.4 s (2.1 ± 0.9% of the total plan dwell time), respectively. The average runtime of the script was 3.5 ± 1.2 minutes. We developed a script that enables efficient, streamlined auto-planning directly within BrachyVision. After contouring and digitization are performed, the script can be run to produce high-quality, customized plans with a single button-click in a few minutes.