Medical Radiology and Radiation Safety. 2026. Vol. 71. № 2

DOI:10.33266/1024-6177-2026-71-2-147-152

Zh.Zh. Smirnova, D.Yu. Bobrov, A.A. Zavialov

Predicting Gamma Passing Rate for Patient Specific Quality Assurance Using Machine and Deep Learning: A Review of Methodological Approaches

A.I. Burnazyan Federal Medical Biophysical Center, Moscow, Russia

Contact person: Zh.Zh. Smirnova, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

ABSTRACT

Introduction: In radiation therapy using advanced techniques such as intensity modulated radiation therapy (IMRT) and volumetric‐arc radiation therapy (VMAT), patient specific quality assurance (QA) should be performed before treatment. The measured and planned dose distributions are commonly quantified by means of a gamma analysis (Gamma Passing Rate, GPR). However, patient‐specific QA procedures are requiring significant time and effort by the physicists. Various ML and DL models have shown promising prediction accuracy and a high potential as time‐efficient virtual QA tool.

Purpose: In this paper, we review the ML and DL based models that were developed for patient specific IMRT and VMAT QA GPR predictions, as well as to identify perspective directions for future research in the field of virtual QA.

Conclusion: The prediction of Gamma Passing Rates (GPR) using Machine Learning (ML) and Deep Learning (DL) is a rapidly evolving and highly promising field. This review demonstrates the evolution of methodological approaches, from the analysis of individual plan complexity metrics to the application of ensemble regression models, and further to sophisticated deep learning architectures. Research confirms that these predictive models can accurately identify plans at risk of verification failure, paving the way for a risk-based approach and a significant reduction in routine measurements. Key challenges for broader clinical integration remain, including ensuring model interpretability, overcoming class imbalance in datasets, improving model generalizability, and their integration into clinical workflows. Successfully addressing these challenges will enable the creation of intelligent decision-support systems capable of enhancing the efficiency, safety, and standardization of radiotherapy.

Keywords: radiotherapy, PSQA, GPR, gamma analysis, prediction, Machine Learning, Deep Learning, virtual QA

For citation: Smirnova ZhZh, Bobrov DYu, Zavialov AA. Predicting Gamma Passing Rate for Patient Specific Quality Assurance Using Machine and Deep Learning: A Review of Methodological Approaches. Medical Radiology and Radiation Safety. 2026;71(2):147–152. (In Russian). DOI:10.33266/1024-6177-2026-71-2-147-152

References

1. Otto K. Volumetric Modulated Arc Therapy: IMRT in a Single Gantry Arc. Med Phys. 2008 Jan;35;1:310-7. Doi: 10.1118/1.2818738.
2. Miften M., Olch A., Mihailidis D., Moran J., Pawlicki T., Molineu A., Li H., Wijesooriya K., Shi J., Xia P., Papanikolaou N., A Low D. Tolerance Limits and Methodologies for IMRT Measurement-Based Verification QA: Recommendations of AAPM Task Group No. 218. Med Phys. 2018 Apr; 45;4:e53-e83. Doi: 10.1002/mp.12810.
3. Olch A.J. Dosimetric Performance of an Enhanced Dose Range Radiographic Film for Intensity‐Modulated Radiation Therapy Quality Assurance. Med Phys. 2002 Sep;29;9:2159-68. Doi: 10.1118/1.1500398.
4. Wouter van Elmpt, McDermott L., Nijsten S., Wendling M., Lambin P., Mijnheer B. A Literature Review of Electronic Portal Imaging for Radiotherapy Dosimetry. Radiother Oncol. 2008 Sep;88;3:289-309. Doi: 10.1016/j.radonc.2008.07.008.
5. Low D.A., Harms W.B., Mutic S., Purdy J.A. A Technique for the Quantitative Evaluation of Dose Distributions. Med Phys. 1998 May;25;5:656-61. Doi: 10.1118/1.598248.
6. Depuydt T., Van Esch A., Pierre Huyskens D. A Quantitative Evaluation of IMRT Dose Distributions: Refinement and Clinical Assessment of the Gamma Evaluation. Radiother Oncol. 2002 Mar;62;3:309-19. Doi: 10.1016/s0167-8140(01)00497-2.
7. Ford E.C., Terezakis S., Souranis A., Harris K., Gay H., Mutic S. Quality Control Quantification (QCQ): a Tool to Measure the Value of Quality Control Checks in Radiation Oncology. Int J Radiat Oncol Biol Phys. 2012 Nov 1;84;3:e263-9. Doi: 10.1016/j.ijrobp.2012.04.036.
8. Chan M.F., Witztum A., Valdes G. Integration of AI and Machine Learning in Radiotherapy QA. Front Artif Intell. 2020 Sep 29:3:577620. Doi: 10.3389/frai.2020.577620.
9. Valdes G., Chan M.F., Boh Lim Seng, Scheuermann R., O Deasy J., D Solberg T. IMRT QA Using Machine Learning: a Multi-Institutional Validation. J Appl Clin Med Phys. 2017 Sep;18;5:279-284. Doi: 10.1002/acm2.12161.
10. Международное агентство по атомной энергии. Искусственный интеллект в медицинской физике. Функции, обязанности, образование и подготовка медицинских физиков клинической квалификации: Серия учебных курсов №83. Вена: МАГАТЭ, 2025. 54 с. [Mezhdunarodnoye Agentstvo po Atomnoy Energii. Iskusstvennyy Intellekt v Meditsinskoy Fizike. Funktsii, Obyazannosti, Obrazovaniye i Podgotovka Meditsinskikh Fizikov Klinicheskoy Kvalifikatsii = Artificial Intelligence in Medical Physics. Roles, Responsibilities, Education, and Training of Clinically Qualified Medical Physicists. Training Course Series No. 83. Vienna, IAEA Publ., 2025. 54 p. (In Russ.)].
11. Younge K.C., Roberts D., Janes L.A., Anderson C., Moran J.M., Matuszak M.M. Predicting Deliverability of Volumetric-Modulated arc Therapy (VMAT) Plans Using Aperture Complexity Analysis. J Appl Clin Med Phys. 2016 Jul 8;17;4:124-31. Doi: 10.1120/jacmp.v17i4.6241.
12. McNiven A.L., Sharpe M.B., Purdie T.G. A New Metric for Assessing IMRT Modulation Complexity and Plan Deliverability. Med Phys. 2010 Feb;37;2:505-15. Doi: 10.1118/1.3276775.
13. Park J.M., Park S.-Y., Kim H. Modulation Index for VMAT Considering both Mechanical and Dose Calculation Uncertainties. Physics in Medicine & Biology. 2015;60;18:7101–7125. Doi: 10.1088/0031-9155/60/18/7101.
14. Park J.M., Wu H.G., Kim J.H., Carlson J.N., Kim K. The Effect of MLC Speed and Acceleration on the Plan Delivery Accuracy of VMAT. Br J Radiol. 2015 May; 88;1049:20140698. Doi: 10.1259/bjr.20140698.
15. Nyflot M.J., Thammasorn P., Wootton L.S., Ford E.C., Chaovalitwongse W.A. Deep Learning for Patient-Specific Quality Assurance: Identifying Errors in Radiotherapy Delivery by Radiomic Analysis of Gamma Images with Convolutional Neural Networks. Med Phys. 2019 Feb;46;2:456-464. Doi: 10.1002/mp.13338.
16. Hideaki Hirashima, Tomohiro Ono, Mitsuhiro Nakamura, Yuki Miyabe, Nobutaka Mukumoto, Hiraku Iramina, Takashi Mizowaki. Improvement of Prediction and Classification Performance for Gamma Passing Rate by Using Plan Complexity and Dosiomics Features. Radiother Oncol. 2020 Dec:153:250-257. Doi: 10.1016/j.radonc.2020.07.031.
17. Valdes G., Scheuermann R., Hung C.Y., Olszanski A., Bellerive M., Solberg T.D. A Mathematical Framework for Virtual IMRT QA Using Machine Learning. Med Phys. 2016 Jul;43;7:4323. Doi: 10.1118/1.4953835.
18. Jiaqi Li, Le Wang, Xile Zhang, Lu Liu, Jun Li, Maria F Chan, Jing Sui, Ruijie Yang. Machine Learning for Patient-Specific Quality Assurance of VMAT: Prediction and Classification Accuracy. Int J Radiat Oncol Biol Phys. 2019 Nov 15;105;4:893-902. Doi: 10.1016/j.ijrobp.2019.07.049.
19. Bin S., Zhang J., Shen L., Zhang Jand Wang Q. Study of the Prediction of Gamma Passing Rate in Dosimetric Verification of Intensity-Modulated Radiotherapy Using Machine Learning Models Based on Plan Complexity. Front Oncol. 2023 Jul;21;13:1094927. Doi: 10.3389/fonc.2023.1094927.
20. Sangutid Thongsawad, Somyot Srisatit , Todsaporn Fuangrod. Predicting Gamma Evaluation Results of Patient-Specific Head and Neck Volumetric-Modulated Arc Therapy Quality Assurance Based on Multileaf Collimator Patterns and Fluence Map Features: a Feasibility Study. J Appl Clin Med Phys. 2022 Jul;23;7:e13622. Doi: 10.1002/acm2.13622.
21. Shane McCarthy, Brent Harrison, Damodar Pokhrel. A Predictive Quality Assurance Model for Patient-Specific Gamma Passing Rate of Hyperarc-Based Stereotactic Radiotherapy and Radiosurgery of Brain Metastases. J Appl Clin Med Phys. 2025 Sep; 26;9:e70225. Doi: 10.1002/acm2.70225.
22. Tomohiro Kajikawa, Noriyuki Kadoya, Kengo Ito, Yoshiki Takayama, Takahito Chiba, Seiji Tomori, Hikaru Nemoto, Suguru Dobashi, Ken Takeda, Keiichi Jingu. A Convolutional Neural Network Approach for IMRT Dose Distribution Prediction in Prostate Cancer Patients. J Radiat Res. 2019 Oct 23;60;5:685-693. Doi: 10.1093/jrr/rrz051.
23. Haibo He, Yang Bai, Edwardo A. Garcia, Shutao Li. ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning In. IEEE International Joint Conference on Neural Networks. 2008:1322-1328. Doi: 10.1109/IJCNN.2008.4633969.
24. Chawla N.V., et al. SMOTE: Synthetic Minority Over-Sampling Technique. Journal of Artificial Intelligence Research. 2002;16;1:321-357. Doi: 10.1613/jair.953.
25. Alexander F I Osman, Nabil M Maalej. Applications of Machine and Deep Learning to Patient‐Specific IMRT/VMAT Quality Assurance. Appl Clin Med Phys. 2021 Aug 3;22;9:20–36. Doi: 10.1002/acm2.13375.

 PDF (RUS) Full-text article (in Russian)

Conflict of interest. The authors declare no conflict of interest.

Financing. The study had no sponsorship.

Contribution. Article was prepared with equal participation of the authors.

Article received: 20.01.2026. Accepted for publication: 25.02.2026.