2248 - Development of an Automated Simulation-Free Platform for Emergent Radiotherapy

R. C. Tegtmeier¹, E. L. Clouser¹, A. Labbe¹, J. S. Aguilar Jr.¹, W. G. Rule², S. A. Vora², S. K. Ahmed¹, C. R. Buckey¹, S. J. Chungbin¹, J. Yan¹, Q. Chen¹, and Y. Rong¹; ¹Department of Radiation Oncology, Mayo Clinic AZ, Phoenix, AZ, ²Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ

Purpose/Objective(s): Palliative radiotherapy (RT) for oncologic emergencies poses distinct patient safety challenges due to limited access to standard clinical resources beyond normal treatment hours. This clinic has historically utilized a vendor-provided unplanned treatment mode (UTM) available on the linac console to deliver emergent RT after-hours. However, this workflow necessitates significant user intervention and is susceptible to a heightened risk of mistreatment given the condensed timeline, complexity, and infrequency of care. As such, an automated simulation-free platform was developed to better assist on-call teams in planning and delivering expedited procedures. The practical development of this tool and initial observations are described herein. Materials/

Methods: The in-house platform was designed using a C#-based application programming interface (API), enabling access to scripting tools integrated directly with the planning system. Generated scripts were compiled as a stand-alone executable, and a graphical user interface was customized via an integrated development environment. The software is designed as a framework for accelerated cone-beam CT (CBCT)-based RT (no standard simulation image acquired), and streamlined workflows within the tool adhere to all processes within standard planning procedures as the application systematically guides users through each step of the RT process. When achievable, full automation is utilized to limit user intervention (e.g., for plan generation, documentation, physics second check) supplemented by detailed graphical instructions for tasks requiring manual execution. Upon completing each step, an automatic audit is conducted to ensure all needed tasks have been performed prior to proceeding. Over several months, numerous phantom-based dry runs (for palliative spine RT) were conducted to refine this tool and quantify relevant timing metrics.
Results: Dry runs indicate the entire RT workflow can be completed in under an hour (~50 min on average) with use of the in-house tool, compared to 1.5-3.5 hours for similar treatments with UTM. The software generates satisfactory multi-field CBCT-based 3D treatment plans (for spine) in ~20 seconds following definition of the desired treatment area, whereas manual plan generation on 2D radiographs with UTM (based on hand calculations) requires ~10 min. Overall, therapist/physician feedback indicates the platform is far less complex than UTM and requires fewer steps to accomplish the identical task of emergent RT delivery.
Conclusion: A novel in-house platform for emergent RT was successfully developed utilizing an API and is undergoing clinical implementation pending departmental approval. By introducing full automation when feasible, this application can improve the quality and safety of after-hours RT while greatly reducing workflow duration. Additional work has commenced to extend use of this platform to more complex treatment techniques and sites beyond emergent care.