Related Experiment Video
Updated: Jun 12, 2025
Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies
Published on: February 6, 2019
Online Adaptive Proton Therapy Facilitated by Artificial Intelligence-Based Autosegmentation in Pencil Beam Scanning
Hongying Feng1, Jie Shan2, Carlos E Vargas2
1Department of Radiation Oncology, Mayo Clinic, Phoenix, Arizona; College of Science, China Three Gorges University, Yichang, Hubei, China; Department of Radiation Oncology, Guangzhou Concord Cancer Center, Guangzhou, Guangdong, China.
Purpose:
Online adaptive proton therapy (oAPT) is essential to address interfractional anatomical changes in patients receiving pencil beam scanning proton therapy. Artificial intelligence (AI)-based autosegmentation can increase the efficiency and accuracy. Linear energy transfer (LET)-based biological effect evaluation can potentially mitigate possible adverse events caused by high LET. New spot arrangement based on the verification computed tomography (vCT) can further improve the replan quality. We propose an oAPT workflow that incorporates all these functionalities and validate its clinical implementation feasibility with patients with prostate cancer.
Methods And Materials:
AI-based autosegmentation tool AccuContour (Manteia) was seamlessly integrated into oAPT. Initial spot arrangement tool on the vCT for reoptimization was implemented using raytracing. An LET-based biological effect evaluation tool was developed to assess the overlap region of high dose and high LET in selected organs at risk. Eleven patients with prostate cancer were retrospectively selected to verify the efficacy and efficiency of the proposed oAPT workflow. The time cost of each component in the workflow was recorded for analysis.
Results:
The verification plan showed significant degradation of the clinical target volume coverage and rectum and bladder sparing due to the interfractional anatomical changes. Reoptimization on the vCT resulted in great improvement of the plan quality. No overlap regions of high dose and high LET distributions were observed in bladder or rectum in replans. Three-dimensional γ analyses in patient-specific quality assurance confirmed the accuracy of the replan doses before delivery (γ passing rate, 99.57% ± 0.46%) and after delivery (98.59% ± 1.29%). The robustness of the replans passed all clinical requirements. The average time for the complete execution of the workflow was 9.12 ± 0.85 minutes, excluding manual intervention time.
Conclusions:
The AI-facilitated oAPT workflow demonstrated to be both efficient and effective by generating a replan that significantly improved the plan quality in prostate cancer treated with pencil beam scanning proton therapy.
