vestiftИзвестия Национальной академии наук Беларуси. Серия физико-технических наукProceedings of the National Academy of Sciences of Belarus. Physical-technical series1561-83582524-244XThe Republican Unitary Enterprise Publishing House "Belaruskaya Navuka"10.29235/1561-8358-2026-71-2-166-176vestift-948Research ArticleИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ И СИСТЕМЫINFORMATION TECHNOLOGIES AND SYSTEMSИтеративное обучение модели дозиметрического планирования стерео- таксической лучевой терапии при патологиях грудного и поясничного отделов позвоночникаIterative training of an automated dosimetric planning model for stereotactic radiotherapy in thoracic and lumbar spine pathologiesЮшкевичВ. Ю.YushkevichV. Yu.

Юшкевич Виктория Юрьевна – медицинский физик отдела по инженерному обеспечению лучевой терапии г

аг. Лесной, 223040, Минский район, Минская область

Viktoryia Yu. Yushkevich – Medical Physicist of the Department for Engineering Support of Radiation Therapy

agro-town Lesnoy, 223040, Minsk district

yushkevich.ur@gmail.comhttps://orcid.org/0000-0002-5137-3064ПеткевичМ. Н.PietkevichM. N.

Петкевич Максим Николаевич – кандидат технических наук, начальник отдела по инженерному обеспечению лучевой терапии 

аг. Лесной, 223040, Минский район, Минская область

Maksim N. Pietkevich – Cand. Sci. (Engineering), Head of the Department for Engineering Support of Radiation Therapy 

agro-town Lesnoy, 223040, Minsk district

maxpetkevichn@gmail.comТарутинИ. Г.TarutinI. G.

Тарутин Игорь Германович – доктор технических наук, профессор, медицинский физик отдела по инженерному обеспечению лучевой

аг. Лесной, 223040, Минский район, Минская область

Ihar G. Tarutin – Dr. Sci. (Engineering), Professor, Medical Physicist of the Medical Physicist and Engineering Department 

agro-town Lesnoy, 223040, Minsk district

itarutin1940@mail.ruГосударственное учреждение «Республиканский научно-практический центр онкологии и медицинской радиологии имени Н. Н. Александрова»БеларусьN. N. Alexandrov National Cancer CentreBelarus202609072026712166176Copyright © Юшкевич В.Ю., Петкевич М.Н., Тарутин И.Г., 20262026Юшкевич В.Ю., Петкевич М.Н., Тарутин И.Г.Yushkevich V.Y., Pietkevich M.N., Tarutin I.G.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestift.belnauka.by/jour/article/view/948

Представлены результаты применения итеративного подхода к оптимизации многокритериальных моделей распределения дозы ионизирующего излучения для стереотаксической лучевой терапии позвоночника. В исследовании использовались две модели: базовая многокритериальная модель (SRT_Vert_BM, от англ. Baseline Multicriteria Model) и усовершенствованная многокритериальная модель (SRT_Vert_IM, от англ. Iterative Multicriteria Model). Первая построена на основе клинической выборки дозиметрических планов, вторая создана итеративным методом, при котором обучающая выборка формировалась из планов, сгенерированных исходной моделью. Валидация показала, что SRT_Vert_IM обеспечивает статистически значимое улучшение прогностических характеристик (повышение коэффициента детерминации R², снижение среднеквадратичной ошибки MSE) и дозиметрических параметров для билатеральных паренхиматозных органов риска (p < 0,05) при сохранении клинически приемлемого покрытия целевого объема облучения. Итеративное обучение позволило повысить воспроизводимость и достоверность качества дозиметрических планов, что подтверждает перспективность данного подхода для совершенствования процесса планирования стереотаксической лучевой терапии.

The study presents the results of applying an iterative approach to optimizing automated multi-criteria ionizing radiation dose distribution models for stereotactic spine radiotherapy. Two models were used: SRT_Vert_BM (Baseline Multicriteria Model) and SRT_Vert_IM (Iterative Multicriteria Model). The former was built on a clinical dataset of dosimetric plans, while the latter was created using an iterative method where the training dataset was formed from plans generated by the baseline model. Validation demonstrated that SRT_Vert_IM provides statistically significant improvements in predictive performance (increased coefficient of determination R², reduced mean squared error MSE) and dosimetric parameters for bilateral parenchymal organs at risk (p < 0.05) while maintaining clinically acceptable target volume coverage. Iterative training enhanced the reproducibility and reliability of dosimetric plan quality, confirming the potential of this approach for advancing automated treatment planning.

итеративный метод обучениямногокритериальная модельмоделирование трехмерного распределения дозыионизирующее излучениемодуль RapidPlan v16.1компьютерная система планирования облучения Eclipse v16.1машинное обучениеiterative learning methodmulti-criteria modelthree-dimensional dose distribution modelingionizing radiationRapidPlan v16.1 moduleEclipse v16.1 radiation treatment planning systemmachine learningReferencesVolumetric modulated arc therapy: a review of current literature and clinical use in practice / M. Teoh, C. H. Clark, K. Wood [et al.] // The British Journal of Radiology. – 2011. – Vol. 84, № 1007. – P. 967–996. https://doi.org/10.1259/bjr/22373346Teoh M., Clark C.H., Wood K., Whitaker S., Nisbet A. Volumetric modulated arc therapy: a review of current literature and clinical use in practice. The British Journal of Radiology, 2011, vol. 84, no. 1007, pp. 967–996. https://doi.org/10.1259/bjr/22373346Intercenter validation of a knowledge based model for automated planning of volumetric modulated arc therapy for prostate cancer. The experience of the German RapidPlan Consortium / C. Schubert, O. Waletzko, C. Weiss [et al.] // PLoS One. – 2017. – Vol. 12, № 5. – Art. ID e0178034. https://doi.org/10.1371/journal.pone.0178034Schubert C., Waletzko O., Weiss C., Voelzke D., Toperim S., Roeser A., Puccini S. [et al.]. Intercenter validation of a knowledge based model for automated planning of volumetric modulated arc therapy for prostate cancer. The experience of the German RapidPlan Consortium. PLoS One, 2017, vol. 12, no. 5, art. ID e0178034. https://doi.org/10.1371/journal.pone.0178034Is it possible for knowledge-based planning to improve intensity modulated radiation therapy plan quality for planners with different planning experiences in left-sided breast cancer patients? / J. Wang, W. Hu, Z. Yang [et al.] // Radiation Oncology. – 2017. – Vol. 12, № 1. – Art. ID 85. https://doi.org/10.1186/s13014-017-0822-zWang J., Hu W., Yang Z., Chen X., Wu Z., Yu X., Guo X. [et al.]. Is it possible for knowledge-based planning to improve intensity modulated radiation therapy plan quality for planners with different planning experiences in left-sided breast cancer patients? Radiation Oncology, 2017, vol. 12, no. 1, art. ID 85. https://doi.org/10.1186/s13014-017-0822-zReducing inter- and intra-planner variability in radiotherapy plan output with a commercial knowledge-based planning solution / A. Scaggion, M. Fusella, A. Roggio [et al.] // Physica Medica. – 2018. – Vol. 53. – P. 86–93. https://doi.org/10.1016/j.ejmp.2018.08.011Scaggion A., Fusella M., Roggio A., Bacco S., Pivato N., Rossato M. A., Peñaa L. M. A., Paiusco M. Reducing inter- and intra-planner variability in radiotherapy plan output with a commercial knowledge-based planning solution. Physica Medica, 2018, vol. 53, pp. 86–93. https://doi.org/10.1016/j.ejmp.2018.08.011Lahanas, M. Multiobjective inverse planning for intensity modulated radiotherapy with constraint-free gradient-based optimization algorithms / M. Lahanas, E. Schreibmann, D. Baltas // Physics in Medicine and Biology. – 2003. – Vol. 48, № 17. – P. 2843–2871. https://doi.org/10.1088/0031-9155/48/17/307Lahanas M., Schreibmann E., Baltas D. Multiobjective inverse planning for intensity modulated radiotherapy with constraint-free gradient-based optimization algorithms. Physics in Medicine and Biology, 2003, vol. 48, no. 17, pp. 2843–2871. https://doi.org/10.1088/0031-9155/48/17/307Петкевич, М. Н. Разработка и машинное обучение многокритериальной модели распределения дозы ионизирующего излучения в системе планирования лечения Eclipse / М. Н. Петкевич, В. Ю. Юшкевич // Весці Нацыянальнай акадэміі навук Беларусі. Серыя фізіка-тэхнічных навук. – 2025. – Т. 70, № 2. – С. 166–176. https://doi.org/10.29235/15618358-2025-70-2-166-176Pietkevich M. N., Yushkevich V. Yu. Development and machine learning of a multi-criteria ionizing radiation dose distribution model in the Eclipse treatment planning system. Vestsi Natsyyanal’nai akademii navuk Belarusi. Seryya fizikatekhnichnykh navuk = Proceedings of the National Academy of Sciences of Belarus. Physical-technical series, 2025, vol. 70, no. 2, pp. 166–176 (in Russian). https://doi.org/10.29235/1561-8358-2025-70-2-166-176Shiraishi, S. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy / S. Shiraishi, K. L. Moore // Medical Physics. – 2016. – Vol. 43, № 1. – Art. ID 378. https://doi.org/10.1118/1.4938583Shiraishi S., Moore K.L. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy. Medical Physics, 2016, vol. 43, no. 1, art. ID 378. https://doi.org/10.1118/1.4938583Pareto navigation – algorithmic foundation of interactive multi-criteria IMRT planning / M. Monz, K. H. Küfer, T. R. Bortfeld, C. Thieke // Physics in Medicine and Biology. – 2008. – Vol. 53, № 4. – P. 985–998. https://doi.org/10.1088/00319155/53/4/011Monz M., Küfer K. H., Bortfeld T. R., Thieke C. Pareto navigation – algorithmic foundation of interactive multicriteria IMRT planning. Physics in Medicine and Biology, 2008, vol. 53, no. 4, pp. 985–998. https://doi.org/10.1088/00319155/53/4/011Assessment of a model based optimization engine for volumetric modulated arc therapy for patients with advanced hepatocellular cancer / A. Fogliata, P. M. Wang, F. Belosi [et al.] // Radiation Oncology. – 2014. – Vol. 9. – Art. ID 236. https://doi.org/10.1186/s13014-014-0236-0Fogliata A., Wang P. M., Belosi F., Clivio A., Nicolini G., Vanetti E., Cozzi L. Assessment of a model based optimization engine for volumetric modulated arc therapy for patients with advanced hepatocellular cancer. Radiation Oncology, 2014, vol. 9, art. ID 236. https://doi.org/10.1186/s13014-014-0236-0RapidPlan head and neck model: the objectives and possible clinical benefit / A. Fogliata, G. Reggiori, A. Stravato [et al.] // Radiation Oncology. – 2017. – Vol. 12, № 1. – Art. ID 73. https://doi.org/10.1186/s13014-017-0805-0Fogliata A., Reggiori G., Stravato A., Lobefalo F., Franzese C., Franceschini D., Tomatis S. [et al.]. RapidPlan head and neck model: the objectives and possible clinical benefit. Radiation Oncology, 2017, vol. 12, no. 1, art. ID 73. https://doi.org/10.1186/s13014-017-0805-0A broad scope knowledge based model for optimization of VMAT in esophageal cancer: validation and assessment of plan quality among different treatment centers / A. Fogliata, G. Nicolini, A. Clivio [et al.] // Radiation Oncology. – 2015. – Vol. 10. – Art. ID 234. https://doi.org/10.1186/s13014-015-0545-yFogliata A., Nicolini G., Clivio A., Vanetti E., Laksar S., Tozzi A., Scorsetti A. C., Cozzi L. A broad scope knowledge based model for optimization of VMAT in esophageal cancer: validation and assessment of plan quality among different treatment centers. Radiation Oncology, 2015, vol. 10, art. ID 234. https://doi.org/10.1186/s13014-015-0545-yAn analysis of knowledge-based planning for stereotactic body radiation therapy of the spine / J. J. Foy, R. Marsh, R. K. Ten Haken [et al.] // Practical Radiation Oncology. – 2017. – Vol. 7, № 5. – P. 355–360. https://doi.org/10.1016/j.prro.2017.02.007Foy J. J., Marsh R., Ten Haken R. K., Younge K. C., Schipper M., Sun Y., Owen D., Matuszak M. M. An analysis of knowledge-based planning for stereotactic body radiation therapy of the spine. Practical Radiation Oncology, 2017, vol. 7, no. 5, pp. 355–360. https://doi.org/10.1016/j.prro.2017.02.007Highly efficient training, refinement, and validation of a knowledge-based planning quality-control system for radiation therapy clinical trials / N. Li, R. Carmona, I. Sirak [et al.] // International Journal of Radiation Oncology – Biology – Physics. – 2017. – Vol. 97, № 1. – P. 164–172. https://doi.org/10.1016/j.ijrobp.2016.09.022Li N., Carmona R., Sirak I., Kasaova L., Followill D., Michalski J., Bosch W. R. [et al.]. Highly efficient training, refinement, and validation of a knowledge-based planning quality-control system for radiation therapy clinical trials. International Journal of Radiation Oncology – Biology – Physics, 2017, vol. 97, no 1, pp. 164–172. https://doi.org/10.1016/j.ijrobp.2016.09.022DVH Estimation Algorithm for RapidPlan // Eclipse Photon and Electron Algorithms Reference Guide. – Palo Alto, CA: Varian Medical Systems, 2014. – P. 219–229. URL: https://www.varian.com/sites/default/files/resource_attachments/EclipsePhotonElectronAlgorithmsRef_0.pdf (date of access: 01.02.2025).DVH Estimation Algorithm for RapidPlan. Eclipse Photon and Electron Algorithms Reference Guide. Palo Alto, CA, Varian Medical Systems, 2014, pp. 219–229. Available from: https://www.varian.com/sites/default/files/resource_attachments/EclipsePhotonElectronAlgorithmsRef_0.pdf (accessed: 1 February 2025).Machine learning and modeling: Data, validation, communication challenges / I. El Naqa, D. Ruan, G. Valdes [et al.] // Medical Physics. – 2018. – Vol. 45, № 10. – P. 834–840. https://doi.org/10.1002/mp.12811El Naqa I., Ruan D., Valdes G., Dekker A., McNutt T., Ge Ya., Wu Q. J. [et al.]. Machine learning and modeling: Data, validation, communication challenges. Medical Physics, 2018, vol. 45, no. 10, pp. 834–840. https://doi.org/10.1002/mp.12811

The authors declare that there are no conflicts of interest present.