Daily Multi‐Leaf Collimator positional error prediction using machine learning: A Dynalog‐based approach for patient specific quality assurance
5 affiliations
- 1Department of Medical Radiation Engineering Shahid Beheshti University Tehran Iran
- 2Department of Radiation Oncology Cancer Institute School of Medicine Tehran University of Medical Sciences Tehran Iran
- 3Clinical Research Development Unit, Shohada‐e Tajrish Hospital Shahid Beheshti University of Medical Sciences Tehran Iran
- 4Department of Electrical Engineering Shahid Beheshti University Tehran Iran
- 5Department of Biomedical Engineering Amirkabir University of Technology Tehran Iran
Abstract
Background: Accurate positioning of multi‐leaf collimators (MLCs) is critical for ensuring the dosimetric precision of intensity‐modulated radiation therapy (IMRT). Nonetheless, daily MLC positional variations can degrade treatment accuracy, emphasizing the need for robust methodologies to detect and predict these deviations.
Purpose: This study proposes a machine learning (ML) approach to predict daily MLC positional deviations using factors contributing to positional errors, enabling daily patient‐specific quality assurance (PSQA) to assess the dosimetric impact of these discrepancies on patient treatment.
Methods: DICOM‐RT and Dynalog files from 29 IMRT patients were collected, and 78 features were extracted, including aperture‐based features, mechanical parameters, and MLC check data. A LightGBM machine learning model was constructed to predict daily positional errors between planned and delivered MLC positions at each control point. For dosimetric analysis, nine independent IMRT plans were evaluated using dose volume histogram (DVH) parameters such as D98%, and V100% for targets and Dmax, Dmean for Organs at Risk (OARs). Moreover, the Gamma Pass Rate (GPR) was calculated for both the delivered and predicted dose distributions, with regarding the primary planned dose distribution as the reference.
Results: The proposed LightGBM model demonstrated accurate predictions, achieving Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of 0.035 mm and 0.078 mm for the training dataset, 0.070 mm and 0.164 mm for the validation dataset, and 0.054 mm and 0.144 mm for the test dataset, respectively. Leaf velocity, with a Spearman correlation coefficient of 0.703, was the most influential feature. Evaluation on nine independent clinical cases demonstrated good agreement between delivered and predicted dosimetric deviations from the planned values, with mean differences below 0.200 Gy and approximately 1.5% for target structures, and even smaller discrepancies for OARs. The GPR (3%/3 mm criterion) was about 100% for delivered doses and 99.99% for predicted doses.
Conclusions: The proposed ML‐based LightGBM model offers an efficient daily PSQA tool, with the potential to enhance the treatment accuracy and support proactive clinical decision‐making in IMRT.
Related
- A deep learning approach for EPID-based patient-specific quality assurance incorporating daily machine-state variations
- Evidence-based design of a patient-specific quality assurance program through retrospective analysis of pretreatment and in vivo results.
- Beyond Gamma Analysis: An Accessibility-oriented Framework for Comparative Evaluation of Patient-specific Radiotherapy Quality Assurance
- Characterization and Validation of MicroDiamond Detectors in Patient-specific Quality Assurance of Magnetic Resonance-guided Stereotactic Radiotherapy
- Three-dimensional deep learning nomogram for post-plan quality assurance in high-dose-rate prostate brachytherapy.
BibTeX
@article{akizi2026daily,
title = {{Daily Multi‐Leaf Collimator positional error prediction using machine learning: A Dynalog‐based approach for patient specific quality assurance}},
author = {Samira Aghaei Akizi and Seyed Mahmoud Reza Aghamiri and Zahra Siavashpour and Reza Ghaderi and Soharb Barimani},
journal = {Journal of Applied Clinical Medical Physics},
year = {2026},
month = oct,
doi = {10.1002/acm2.70882},
url = {https://doi.org/10.1002/acm2.70882},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Daily Multi‐Leaf Collimator positional error prediction using machine learning: A Dynalog‐based approach for patient specific quality assurance
AU - Samira Aghaei Akizi
AU - Seyed Mahmoud Reza Aghamiri
AU - Zahra Siavashpour
AU - Reza Ghaderi
AU - Soharb Barimani
PY - 2026
DA - 2026/10/27
JO - Journal of Applied Clinical Medical Physics
DO - 10.1002/acm2.70882
UR - https://doi.org/10.1002/acm2.70882
AB - Background: Accurate positioning of multi‐leaf collimators (MLCs) is critical for ensuring the dosimetric precision of intensity‐modulated radiation therapy (IMRT). Nonetheless, daily MLC positional variations can degrade treatment accuracy, emphasizing the need for robust methodologies to detect and predict these deviations. Purpose: This study proposes a machine learning (ML) approach to predict daily MLC positional deviations using factors contributing to positional errors, enabling daily patient‐specific quality assurance (PSQA) to assess the dosimetric impact of these discrepancies on patient treatment. Methods: DICOM‐RT and Dynalog files from 29 IMRT patients were collected, and 78 features were extracted, including aperture‐based features, mechanical parameters, and MLC check data. A LightGBM machine learning model was constructed to predict daily positional errors between planned and delivered MLC positions at each control point. For dosimetric analysis, nine independent IMRT plans were evaluated using dose volume histogram (DVH) parameters such as D98%, and V100% for targets and Dmax, Dmean for Organs at Risk (OARs). Moreover, the Gamma Pass Rate (GPR) was calculated for both the delivered and predicted dose distributions, with regarding the primary planned dose distribution as the reference. Results: The proposed LightGBM model demonstrated accurate predictions, achieving Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of 0.035 mm and 0.078 mm for the training dataset, 0.070 mm and 0.164 mm for the validation dataset, and 0.054 mm and 0.144 mm for the test dataset, respectively. Leaf velocity, with a Spearman correlation coefficient of 0.703, was the most influential feature. Evaluation on nine independent clinical cases demonstrated good agreement between delivered and predicted dosimetric deviations from the planned values, with mean differences below 0.200 Gy and approximately 1.5% for target structures, and even smaller discrepancies for OARs. The GPR (3%/3 mm criterion) was about 100% for delivered doses and 99.99% for predicted doses. Conclusions: The proposed ML‐based LightGBM model offers an efficient daily PSQA tool, with the potential to enhance the treatment accuracy and support proactive clinical decision‐making in IMRT.
SN - 1526-9914
ER -