AI-Powered Radiotherapy for Resource-Limited Settings: Advancing Cervical and Prostate Cancer Treatment Planning with the Radiation Planning Assistant
Abstract
Purpose
Radiotherapy treatment planning is a resource-intensive process characterized by multiple manual steps that can contribute to treatment delays and inter-observer variability. The Radiation Planning Assistant (RPA) is a web-based platform designed to deliver automated contouring and planning approaches tailored to low-resource settings. This work expands the RPA to develop and clinically validate end-to-end, AI-driven workflows for prostate and cervical cancers, designed to improve efficiency, consistency, and accessibility in low- and middle-income countries (LMICs).
Methods
Deep learning–based auto‑contouring models were trained using nnU‑Net on curated clinical datasets (>1,000 prostate and 110 cervical cancer cases) and integrated with knowledge‑based planning (KBP) models to enable automated VMAT plan generation. Prostate workflows accommodated intact and postoperative cases with and without nodal irradiation; cervical workflows accommodated intact cases with and without para‑aortic nodal irradiation. End‑to‑end workflows required only user‑provided CT imaging and prescription, with optional manual input limited to gross nodal disease. Clinical acceptability of automated contours and plans was retrospectively evaluated by expert radiation oncologists using a five‑point Likert scale, and dosimetric compliance was assessed against NRG‑GU009 and EMBRACE II criteria.
Results
Fifty test patients (40 prostate, 10 cervical) were evaluated end-to-end. For prostate cancer, 70% of target auto-contours and 73% of treatment plans were clinically acceptable without edits; for cervical cancer, these rates were 80% and 80%, respectively. For prostate cancer planning, 77% of target and 98% of organ-at-risk structures met all per-protocol compliance criteria. For cervical cancer planning, all protocol hard constraint criteria were met. Bowel and vaginal contours demonstrated lower performance, but these did not compromise plan quality.
Conclusion
We present validated, end-to-end radiotherapy planning workflows for prostate and cervical cancers that leverage the RPA’s infrastructure to streamline treatment planning in a globally accessible platform and demonstrate high clinical acceptability.