Related Experiment Video
Updated: Jun 8, 2025
Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies
Published on: February 6, 2019
Assessment of pencil beam scanning proton therapy beam delivery accuracy through machine learning and log file
Ranjith C P1, Mayakannan Krishnan2, Vysakh Raveendran3
1Department of Medical Physics, Centre for Interdisciplinary Research, D. Y. Patil Education Society (Deemed to be University), Kolhapur, Maharashtra, India; Department of Radiation Oncology, Advanced Centre for Treatment Research and Education in Cancer, Homi Bhabha National Institute, Mumbai, Maharashtra, India.
Purpose:
Comprehensive Quality Assurance (QA) protocols are necessary for complex beam delivery systems like Pencil Beam Scanning (PBS) proton therapy. This study focuses on automating the evaluation of beam delivery accuracy using irradiation log files and machine learning (ML) models.
Methods:
Irradiation log files of 935 clinical treatment fields and routine QA beams were analysed to evaluate spot parameters and Monitor Unit (MU) accuracy. ML models predicted spot size along the X, Y, major, and minor axes. In-house scripts automated log file analysis and spot size predictions. Predicted spot sizes were compared with expected baselines, and the accuracy of spot position, symmetry, and MU for each spot in the beam was evaluated.
Results:
More than 99.5 % of spot positions were accurate within a 1 mm. The mean and Standard Deviation (SD) of X positional error were -0.021 mm (SD: 0.181 mm), and for Y positional error, they were -0.002 mm (SD: 0.132 mm). ML models accurately predicted spot sizes, with over 95 % of spots demonstrating size variations within 10 % of the baseline. The Root Mean Squared Error (RMSE) of X and Y spot size differences were 0.15 mm and 0.16 mm, respectively. Spot symmetry was within 10 %, and MU accuracy showed 95 % of spots with MU per spot variation less than 2 %.
Conclusion:
This method can validate the vendor's beam delivery safety interlock system and serve as a quick alternative to patient-specific QA in adaptive treatment, where time is limited, as well as for routine QA spot parameter evaluations.
