Bi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning

Moreno, Juan José; Puertas-Martín, Savíns; Redondo, Juana L.; Ortigosa, Pilar M.; Zawadzka, Anna; Kukołowicz, Pawel; Szmurło, Robert; Kaliszewski, Ignacy; Miroforidis, Janusz; Garzón, Ester M.

doi:10.15388/24-INFOR560

Informatica

Bi-Level Optimization to Enhance Intensity Modulated Radiation Therapy Planning

Volume 36, Issue 1 (2025), pp. 99–124

Juan José Moreno Savíns Puertas-Martín Juana L. Redondo Pilar M. Ortigosa Anna Zawadzka Pawel Kukołowicz Robert Szmurło Ignacy Kaliszewski Janusz Miroforidis Ester M. Garzón

https://doi.org/10.15388/24-INFOR560

Pub. online: 18 September 2024 Type: Research Article

Open Access

Received
1 November 2023

Accepted
1 June 2024

Published
18 September 2024

Abstract

Intensity Modulated Radiation Therapy is an effective cancer treatment. Models based on the Generalized Equivalent Uniform Dose (gEUD) provide radiation plans with excellent planning target volume coverage and low radiation for organs at risk. However, manual adjustment of the parameters involved in gEUD is required to ensure that the plans meet patient-specific physical restrictions. This paper proposes a radiotherapy planning methodology based on bi-level optimization. We evaluated the proposed scheme in a real patient and compared the resulting irradiation plans with those prepared by clinical planners in hospital devices. The results in terms of efficiency and effectiveness are promising.

References

Ahmad, S.U., Bergen, S.W.A. (2010). A genetic algorithm approach to the inverse problem of treatment planning for intensity-modulated radiotherapy. Biomedical Signal Processing and Control, 5(3), 189–195. https://doi.org/10.1016/j.bspc.2010.03.001.

Alber, M., Nüssli, F. (1999). An objective function for radiation treatment optimization based on local biological measure. Physics in Medicine & Biology, 44(2), 479–493. https://doi.org/10.1088/0031-9155/44/2/014.

Bortfeld, T. (1999). Optimized planning using physical objectives and constraints. Seminars in Radiation Oncology, 9(1), 20–34. https://doi.org/10.1016/S1053-4296(99)80052-6.

Breedveld, S., Heijmen, B. (2017). Data for TROTS – The Radiotherapy Optimisation Test Set. Data in Brief, 12, 143–149. https://doi.org/10.1016/j.dib.2017.03.037.

Breedveld, S., Craft, D., van Haveren, R., Heijmen, B. (2019). Multi-criteria optimization and decision-making in radiotherapy. European Journal of Operational Research, 277(1), 1–19. https://doi.org/10.1016/j.ejor.2018.08.019.

Cho, B. (2018). Intensity-modulated radiation therapy: a review with a physics perspective. Radiation Oncology Journal, 36(1), 1–10. https://doi.org/10.3857/roj.2018.00122.

Choi, B., Deasy, J.O. (2002). The generalized equivalent uniform dose function as a basis for intensity-modulated treatment planning. Physics in Medicine and Biology, 47(20), 3579–3589. https://doi.org/10.1088/0031-9155/47/20/302.

Durillo, J.J., Nebro, A.J. (2011). jMetal: a Java framework for multi-objective optimization. Advances in Engineering Software, 42, 760–771. https://doi.org/10.1016/j.advengsoft.2011.05.014.

Ehrgott, M., Guler, C., Hamacher, H.W., Shao, L. (2010). Mathematical optimization in intensity modulated radiation therapy. Annals of Operations Research, 175(1), 309–365. https://doi.org/10.1007/s10479-009-0659-4.

Fu, A., Ungun, B., Xing, L., Boyd, S. (2019). A convex optimization approach to radiation treatment planning with dose constraints. Optimization and Engineering, 20, 277–300. https://doi.org/10.1007/s11081-018-9409-2.

Huang, C., Nomura, Y., Yang, Y., Xing, L. (2022). Meta-optimization for fully automated radiation therapy treatment planning. Physics in Medicine & Biology, 67(5). https://doi.org/10.1088/1361-6560/ac5672.

Jourdan, L., Basseur, M., Talbi, E.-G. (2009). Hybridizing exact methods and metaheuristics: a taxonomy. European Journal of Operational Research, 199(3), 620–629. https://doi.org/10.1016/j.ejor.2007.07.035.

Kaliszewski, I., Miroforidis, J., Podkopaev, D. (2016). Multiple Criteria Decision Making by Multiobjective Optimization – A Toolbox. Springer. https://doi.org/10.1007/978-3-319-32756-3.

Moreno, J.J., Miroforidis, J., Filatovas, E., Kaliszewski, I., Garzón, E.M. (2021). Parallel radiation dose computations with GENOCOP III on GPUs. Journal of Supercomputing, 77, 66–76. https://doi.org/10.1007/s11227-020-03254-6.

Moreno, J.J., Miroforidis, J., Kaliszewski, I., Garzón, E.M. (2022). Parallel EUD models for accelerated IMRT planning on modern HPC platforms. In: 14th International Conference on Parallel Processing and Applied Mathematics (PPAM 2022). https://doi.org/10.1007/978-3-031-30445-3_12.

Mukherjee, S., Hong, L., Deasy, J., M., Z. (2020). Integrating soft and hard dose-volume constraints into hierarchical constrained IMRT optimization. Medical Physics, 47(2), 414–421. https://doi.org/10.1002/mp.13908.

Niemierko, A. (1996). Reporting and analyzing dose distributions: a concept of equivalent uniform dose. Medical Physics, 24(1), 103–110. https://doi.org/10.1118/1.598063.

NVIDIA (2023). CUDA Toolkit Documentation v11.7.1. https://docs.nvidia.com/cuda/index.html. Last Accessed on 2023/11/17.

Ólafsson, A., Wright, S.J. (2006). Linear programing formulations and algorithms for radiotherapy treatment planning. Optimization Methods and Software, 21(2), 201–231. https://doi.org/10.1080/10556780500134725.

Ólafsson, A., Jeraj, R., Wright, S.J. (2005). Optimization of intensity-modulated radiation therapy with biological objectives. Physics in Medicine and Biology, 50(22), 5357–5379. https://doi.org/10.1088/0031-9155/50/22/010.

OpenMP (2023). The OpenMP API specification for parallel programming. https://www.openmp.org/. Last Accessed on 2023/11/17.

Romeijn, H., Dempsey, J., Li, J. (2004). A unifying framework for multi-criteria fluence map optimization models. Physics in Medicine and Biology, 49(10), 1991–2013. https://doi.org/10.1088/0031-9155/49/10/011.

Romeijn, H.E., Ahuja, R.K., Dempsey, J.F., Kumar, A. (2006). A new linear programming approach to radiation therapy treatment planning problems. Operations Research, 54(2), 201–216. https://doi.org/10.1287/opre.1050.0261.

Saberian, F., Ghate, A., Kim, M. (2015). Optimal fractionation in radiotherapy with multiple normal tissues. Mathematical Medicine and Biology: A Journal of the IMA, 33(2), 211–252. https://doi.org/10.1093/imammb/dqv015.

Starzyński, J., Szmurło, R., Chaber, B., Krawczyk, Z. (2015). Open access system for radiotherapy planning. In: 2015 16th International Conference on Computational Problems of Electrical Engineering (CPEE), pp. 204–206. https://doi.org/10.1109/CPEE.2015.7333376.

Wang, H., Bai, X., Wang, Y., Lu, Y., Wang, B. (2023a). An integrated solution of deep reinforcement learning for automatic IMRT treatment planning in non-small-cell lung cancer. Frontiers in Oncology, 13. https://doi.org/10.3389/fonc.2023.1124458.

Wang, Q., Wang, R., Liu, J., Jiang, F., Yue, H., Du, Y., Wu, H. (2023b). High-dimensional automated radiation therapy treatment planning via Bayesian optimization. Medical Physics, 50(6), 3773–3787. https://doi.org/10.1002/mp.16289.

Won, Y.J., Lee, E., Cho, S.J., Kim, K.S. (2021). Generalized equivalent uniform dose-based biological optimization in hippocampus-sparing whole-brain radiation therapy. Journal of the Korean Physical Society, 79, 1171–1179. https://doi.org/10.1007/s40042-021-00321-w.

Wu, Q., Mohan, R., Niemierko, A., Schmidt-Ullrich, R. (2002). Optimization of intensity-modulated radiotherapy plans based on the equivalent uniform dose. International Journal of Radiation Oncology Biology Physics, 52, 224–235. https://doi.org/10.1016/S0360-3016(01)02585-8.

Yihua Lan, Y., Li, C., Ren, H., Zhang, Y., Min, Z. (2006). Fluence map optimization (FMO) with dose–volume constraints in IMRT using the geometric distance sorting method. Physics in Medicine and Biology, 57(20), 201–231. https://doi.org/10.1088/0031-9155/57/20/6407.

ZeroMQ (2023). ØMQ – The Guide. https://zguide.zeromq.org/. Last Accessed on 2023/11/17.

Zhang, Q., Li, H. (2007). MOEA/D: a multiobjective evolutionary algorithm based on decomposition. IEEE Transactions on Evolutionary Computation, 11(6), 712–731. https://doi.org/10.1109/TEVC.2007.892759.

Biographies

Moreno Juan José

juanjomoreno@ual.es

J.J. Moreno is a doctoral researcher in the Department of Informatics at the University of Almería (UAL), Spain. He obtained his BSc and MSc in computer science from UAL in 2015 and 2018, respectively. Since 2017, he has been actively engaged in research as a member of the Supercomputing–Algorithms research group at UAL. His areas of research expertise encompass High-Performance Computing (HPC), radiotherapy optimization, and electron tomography image processing.

Puertas-Martín Savíns

savinspm@ual.es

S. Puertas-Martín is a post-doctoral researcher at the Department of Informatics of the University of Almería, Spain. He obtained his PhD in computer science at the University of Almería in 2020. He is a member of the Supercomputing–Algorithms Research Group at the University of Almeria in Spain and the Chemoinformatics Research Group at the University of Sheffield in the United Kingdom. His research interests are drug discovery, global optimization and high-performance computing.

Redondo Juana L.

jlredondo@ual.es

J.L. Redondo holds the position of full professor at the Department of Informatics at the University of Almería, Spain. She earned her PhD in computer science from the same university and is an esteemed member of the Supercomputing-Algorithms Research Group. Her research focuses on High-Performance Computing, global optimization, and their diverse applications.

Ortigosa Pilar M.

ortigosa@ual.es

P.M. Ortigosa is a full professor of architecture and computer technology of the University of Almería, Spain. She received MSc degrees in physics and electronic engineering from the University of Granada in 1994 and 1996, respectively, and a PhD in computer science from the University of Málaga in 1999. She is a member of the Supercomputing-Algorithms Research Group of the University of Almería. Her research focuses on high-performance computing, metaheuristic global optimization, computational intelligence, deep learning, and the application to several real problems. Recently she has been working on the Internet of Things.

Zawadzka Anna

anna.zawadzka.fizyk@nio.gov.pl

A. Zawadzka, a distinguished medical physicist, currently serves in the Medical Physics Department at the Maria Skłodowska-Curie National Research Institute of Oncology. In addition to her role, she holds the position of head of the Treatment Planning Laboratory within the same institution. Her academic journey led to the successful completion of a PhD in medical physics from the Maria Skłodowska-Curie National Research Institute of Oncology in 2018. A. Zawadzka is actively engaged as a lecturer at Warsaw University and contributes as a regional consultant in the field of medical physics. Her scientific pursuits are concentrated on treatment planning, dosimetry, and the quality control of radiotherapy treatments.

Kukołowicz Pawel

Pawel.Kukolowicz@nio.gov.pl

P. Kukołowicz serves as a medical physicist at the Medical Physics Department of the Maria Skłodowska-Curie National Research Institute of Oncology, an institution with a rich history dating back to 1934. As a prominent figure, he holds the position of the head of this esteemed institution. Notably, he has been the president of the Polish Society of Medical Physics from 2011 to 2014 and then again from 2014 to 2018. Since 2018, he is a consultant in medical physics for the Ministry of Health. P. Kukolowicz is also recognized for his role as an advisor to 14 PhD candidates in the field of medical physics. His scientific pursuits primarily revolve around treatment planning, dosimetry, and the quality control of radiotherapy treatments.

Szmurło Robert

robert.szmurlo@pw.edu.pl

R. Szmurło holds the position of an assistant professor at the Warsaw University of Technology, Poland. He has actively contributed to over 10 research projects, funded by entities such as the Polish Ministry of Science, commercial enterprises, and European Union grants, all related to computer simulation methods. The subjects of the projects were related to modelling applications of electromagnetic fields in medical treatment, modelling electric impulse power supply systems, artificial intelligence in medicine for Radiotherapy planning, methods of modelling information systems, among others.

Kaliszewski Ignacy

ignacy.kaliszewski@ibspan.waw.pl

I. Kaliszewski is a full professor in the Systems Research Institute of the Polish Academy of Sciences and in Warsaw School of Information Technology. His scientific interests are optimization, multiple criteria decision making, computer-aided decision making, and also identification, quantification, and management of risk in business organizations.

Miroforidis Janusz

janusz.miroforidis@ibspan.waw.pl

J. Miroforidis is an associate professor at the Systems Research Institute of the Polish Academy of Sciences, Poland. He obtained his PhD in computer science from the same institution in 2010. His scientific interests are multi-objective optimization, multiple criteria decision making, and computer-aided decision making.

Garzón Ester M.

gmartin@ual.es

E.M. Garzón is a full professor at the Department of Informatics of the University of Almería, Spain. She obtained her PhD in computer science from the University of Almería in 2000. She is the head of the Supercomputing-Algorithms Research Group at the same institution. Her research activity is centred on high-performance computing (HPC) addressed to extend applications of scientific computation. Her works have been related to different fields and disciplines.

Full article Related articles

Open access article under the CC BY license.

Keywords

Intensity Modulated Radiation Therapy (IMRT) Genetic Algorithms Generalized Equivalent Uniform Dose (gEUD) Multi-Objective Optimization Bi-Level Optimization

Funding

This work has been supported by Grant PID2021-123278OB-I00 funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”; and by projects PDC2022-133370-I00 and TED2021-132020B-I00 funded by MCIN/AEI/ 10.13039/5011 00011033 and by European Union Next GenerationEU/PRTR. Savíns Puertas Martín is a fellow of the “Margarita Salas” grant (RR_A_2021_21), financed by the European Union (NextGenerationEU).

Metrics

since January 2020

230

Article info
views

Full article
views

PDF
downloads

XML
downloads

RSS

Authors

Abstract

References

Biographies

Export citation

Copy and paste formatted citation

Download citation in file