Real-Time AI-Based Radiotherapy Planning for Nasopharyngeal Carcinoma: Development and Validation.
Authors
Affiliations (9)
Affiliations (9)
- State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China.
- The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University/Hunan Cancer Hospital, Changsha 410013, P. R. China.
- Radiotherapy Business Unit, Shanghai United Imaging Healthcare Co. Ltd., Shanghai 201821, P. R. China.
- Jinan University Affiliated Guangdong Second Provincial General Hospital, Guangzhou 510317, P. R. China.
- Department of Oncology, The First Affiliated Hospital of Gannan Medical University, Jiangxi "Flagship" Oncology Department of Synergy for Chinese and Western Medicine, Jiangxi Provincial Unit for Clinical Key Oncology Specialty Development, Jiangxi Clinical Research Center for Cancer, Ganzhou 341000, P. R. China.
- Radiotherapy Laboratory, Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen 518048, P. R. China.
- Zhejiang Engineering Research Center for Innovation and Application of Intelligent Radiotherapy Technology, Wenzhou 325000, P. R. China.
- School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, P. R. China.
- Department of Radiotherapy, Zhejiang Cancer Hospital, Hangzhou 310022, P. R. China.
Abstract
<b>Background:</b> Online all-in-one (AIO) radiotherapy workflows enable same-day treatment by integrating simulation, planning, and delivery into a single session. However, for anatomically complex tumors such as nasopharyngeal carcinoma (NPC), generating high-quality plans within strict time constraints remains a major barrier to clinical adoption. <b>Methods:</b> We developed a deep-learning-based automated planning model specifically tailored for real-time NPC planning in the online AIO workflow. The model was trained on 890 patients and iteratively refined through 4 versions, incorporating innovations such as quantile loss, priority-based constraint encoding, and hybrid central processing unit-graphics processing unit acceleration. Model performance was benchmarked in a 5-center retrospective study, including 125 patients from the model development center and 120 patients from 4 external centers. It was then prospectively validated in 242 consecutively treated patients with NPC using a CT-linear accelerator-based AIO platform. <b>Results:</b> In the 5-center retrospective evaluation, artificial intelligence (AI)-generated plans achieved superior or comparable dosimetric quality relative to expert manual plans, despite variations in imaging, contouring, and prescription practices. In prospective deployment, 95% of plans were clinically accepted after a single optimization cycle, with a mean generation time of 3.5 min. All plans met target coverage criteria and passed both secondary dose verification and in vivo electronic portal imaging device analysis. <b>Conclusion:</b> This study represents the largest prospective validation to date of AI-based treatment planning for NPC, demonstrating real-time feasibility, robust generalizability, and consistent clinical quality. Our development-to-deployment framework supports the scalable adoption of AI-driven precision planning and provides a transferable model for intelligent radiotherapy across disease sites.