Machine learning-based automatic proton therapy planning: Impact of post-processing and dose-mimicking in plan robustness.
automatic planning
dose mimicking
proton therapy
robustness
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Jul 2023
Jul 2023
Historique:
revised:
12
03
2023
received:
09
10
2022
accepted:
25
03
2023
medline:
11
7
2023
pubmed:
9
4
2023
entrez:
8
4
2023
Statut:
ppublish
Résumé
Automated treatment planning strategies are being widely implemented in clinical routines to reduce inter-planner variability, speed up the optimization process, and improve plan quality. This study aims to evaluate the feasibility and quality of intensity-modulated proton therapy (IMPT) plans generated with four different knowledge-based planning (KBP) pipelines fully integrated into a commercial treatment planning system (TPS). A data set containing 60 oropharyngeal cancer patients was split into 11 folds, each containing 47 patients for training, five patients for validation, and five patients for testing. A dose prediction model was trained on each of the folds, resulting in a total of 11 models. Three patients were left out in order to assess if the differences introduced between models were significant. From voxel-based dose predictions, we analyze the two steps that follow the dose prediction: post-processing of the predicted dose and dose mimicking (DM). We focused on the effect of post-processing (PP) or no post-processing (NPP) combined with two different DM algorithms for optimization: the one available in the commercial TPS RayStation (RSM) and a simpler isodose-based mimicking (IBM). Using 55 test patients (five test patients for each model), we evaluated the quality and robustness of the plans generated by the four proposed KBP pipelines (PP-RSM, PP-IBM, NPP-RSM, NPP-IBM). After robust evaluation, dose-volume histogram (DVH) metrics in nominal and worst-case scenarios were compared to those of the manually generated plans. Nominal doses from the four KBP pipelines showed promising results achieving comparable target coverage and improved dose to organs at risk (OARs) compared to the manual plans. However, too optimistic post-processing applied to the dose prediction (i.e. important decrease of the dose to the organs) compromised the robustness of the plans. Even though RSM seemed to partially compensate for the lack of robustness in the PP plans, still 65% of the patients did not achieve the expected robustness levels. NPP-RSM plans seemed to achieve the best trade-off between robustness and OAR sparing. PP and DM strategies are crucial steps to generate acceptable robust and deliverable IMPT plans from ML-predicted doses. Before the clinical implementation of any KBP pipeline, the PP and DM parameters predefined by the commercial TPS need to be modified accordingly with a comprehensive feedback loop in which the robustness of the final dose calculations is evaluated. With the right choice of PP and DM parameters, KBP strategies have the potential to generate IMPT plans within clinically acceptable levels comparable to plans manually generated by dosimetrists.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4480-4490Subventions
Organisme : Fonds Baillet Latour
Organisme : Waalse Gewest (Walloon Region)
ID : PROTHERWAL/CHARP 7289
Informations de copyright
© 2023 American Association of Physicists in Medicine.
Références
Meyer P, Biston M-C, Khamphan C, et al. Automation in radiotherapy treatment planning: examples of use in clinical practice and future trends for a complete automated workflow. Cancer Radiother. 2021;25:617-622.
Ge Y, Wu QJ. Knowledge-based planning for intensity-modulated radiation therapy: a review of data-driven approaches. Med Phys. 2019;46:2760-2775.
McIntosh C, Welch M, McNiven A, Jaffray DA, Purdie TG. Fully automated treatment planning for head and neck radiotherapy using a voxel-based dose prediction and dose mimicking method. Phys Med Biol. 2017;62:5926-5944.
Petersson K, Nilsson P, Engström P, Knöös T, Ceberg C. Evaluation of dual-arc VMAT radiotherapy treatment plans automatically generated via dose mimicking. Acta Oncol. 2016;55:523-525.
Babier A, Mahmood R, McNiven AL, Diamant A, Chan TCY. The importance of evaluating the complete automated knowledge-based planning pipeline. Phys Med. 2020;72:73-79.
Barragán-Montero AM, Thomas M, Defraene G, et al. Deep learning dose prediction for IMRT of esophageal cancer: the effect of data quality and quantity on model performance. Phys Med. 2021;83:52-63.
Nguyen D, Jia X, Sher D, et al. 3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture. Phys Med Biol. 2019;64:065020.
Fan J, Wang J, Chen Z, Hu C, Zhang Z, Hu W. Automatic treatment planning based on three-dimensional dose distribution predicted from deep learning technique. Med Phys. 2019;46:370-381.
Draguet C, Barragán-Montero AM, Chocan Vera M, et al. Automated clinical decision support system with deep learning dose prediction and NTCP models to evaluate treatment complications in patients with esophageal cancer. Radiother Oncol. 2022;176:101-107. http://doi.org/10.1016/j.radonc.2022.08.031
Wang W, Chang Y, Liu Y, et al. Feasibility study of fast intensity-modulated proton therapy dose prediction method using deep neural networks for prostate cancer. Med Phys. 2022;49:5451-5463.
Guerreiro F, Seravalli E, Janssens GO, et al. Deep learning prediction of proton and photon dose distributions for paediatric abdominal tumours. Radiother Oncol. 2021;156:36-42.
Lomax AJ. Intensity modulated proton therapy and its sensitivity to treatment uncertainties 1: the potential effects of calculational uncertainties. Phys Med Biol. 2008;53(4):1027-1042. http://doi.org/10.1088/0031-9155/53/4/014
Lomax AJ. Intensity modulated proton therapy and its sensitivity to treatment uncertainties 2: the potential effects of inter-fraction and inter-field motions. Phys Med Biol. 2008;53:1043-1056.
Liu W, Frank SJ, Li X, et al. Effectiveness of robust optimization in intensity-modulated proton therapy planning for head and neck cancers. Med Phys. 2013;40:051711.
Fredriksson A, Forsgren A, Hårdemark B. Minimax optimization for handling range and setup uncertainties in proton therapy. Med Phys. 2011;8(3):1672-1684. http://doi.org/10.1118/1.3556559
Pflugfelder D, Wilkens JJ, Oelfke U. Worst case optimization: a method to account for uncertainties in the optimization of intensity modulated proton therapy. Phys Med Biol. 2008;53:1689-1700.
Stuschke M, Kaiser A, Abu Jawad J, Pöttgen C, Levegrün S, Farr J. Multi-scenario based robust intensity-modulated proton therapy (IMPT) plans can account for set-up errors more effectively in terms of normal tissue sparing than planning target volume (PTV) based intensity-modulated photon plans in the head and neck region. Radiat Oncol. 2013;8:145.
Eriksson O, Zhang T. Robust automated radiation therapy treatment planning using scenario-specific dose prediction and robust dose mimicking. Med Phys. 2022;49:3564-3573.
Paganetti H. Range uncertainties in proton therapy and the role of Monte Carlo simulations. Phys Med Biol. 2012;57:R99-117.
Korevaar EW, Habraken SJM, Scandurra D, et al. Practical robustness evaluation in radiotherapy - A photon and proton-proof alternative to PTV-based plan evaluation. Radiother Oncol. 2019;141:267-274. http://doi.org/10.1016/j.radonc.2019.08.005
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 2016:424-432. http://doi.org/10.1007/978-3-319-46723-8_49
RaySearch Laboratories. Machine learning planning model RSL-IMPT-OROPHARYNX-7000-SIB (3.0)* [Internet]. [cited 2022 Jul 14]. https://www.raysearchlabs.com/496c6e/siteassets/raystation-landing-page/machine-learning/available-pretrained-models/rsl-impt-oropharynx-7000-sib-3.0-model-flyer.pdf
Bernatowicz K, Geets X, Barragan A, Janssens G, Souris K, Sterpin E. Feasibility of online IMPT adaptation using fast, automatic and robust dose restoration. Phys Med Biol. 2018;63(8):085018. http://doi.org/10.1088/1361-6560/aaba8c
Borderías-Villarroel E, Taasti V, Van Elmpt W, Teruel-Rivas S, Geets X, Sterpin E. Evaluation of the clinical value of automatic online dose restoration for adaptive proton therapy of head and neck cancer. Radiother Oncol. 2022;170:190-197.
Langendijk JA, Doornaert P, Verdonck-de Leeuw IM, Leemans CR, Aaronson NK, Slotman BJ. Impact of late treatment-related toxicity on quality of life among patients with head and neck cancer treated with radiotherapy. J Clin Oncol. 2008;26:3770-3776.
Dirix P, Nuyts S. Evidence-based organ-sparing radiotherapy in head and neck cancer. Lancet Oncol. 2010;11:85-91.
Goitein M, Niemierko A. Intensity modulated therapy and inhomogeneous dose to the tumor: a note of caution. Int J Radiat Oncol Biol Phys. 1996;36(2):519-522. http://doi.org/10.1016/s0360-3016(96)00348-3
Kierkels RGJ, Fredriksson A, Both S, Langendijk JA, Scandurra D, Korevaar EW. Automated robust proton planning using dose-volume histogram-based mimicking of the photon reference dose and reducing organ at risk dose optimization. Int J Radiat Oncol Biol Phys. 2019;103:251-258.
Barragán-Montero AM, Nguyen D, Lu W, et al. Three-dimensional dose prediction for lung IMRT patients with deep neural networks: robust learning from heterogeneous beam configurations. Med Phys. 2019;46(8):3679-3691. http://doi.org/10.1002/mp.13597
Hu J, Song Y, Wang Q, Bai S, Yi Z. Incorporating historical sub-optimal deep neural networks for dose prediction in radiotherapy. Med Image Anal. 2021;67:101886.
Vandewinckele L, Willems S, Lambrecht M, Berkovic P, Maes F, Crijns W. Treatment plan prediction for lung IMRT using deep learning based fluence map generation. Phys Med. 2022;99:44-54.
Ma L, Chen M, Gu X, Lu W. Deep learning-based inverse mapping for fluence map prediction. Phys Med Biol. 2020;65(23):235035. http://doi.org/10.1088/1361-6560/abc12c
Wang W, Sheng Y, Palta M, et al. Deep learning-based fluence map prediction for pancreas stereotactic body radiation therapy with simultaneous integrated boost. Adv Radiat Oncol. 2021;6:100672.
Barragán-Montero A, Bibal A, Dastarac MH, et al. Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency. Phys Med Biol. 2022;67:11TR01. http://doi.org/10.1088/1361-6560/ac678a
Huet-Dastarac M, Barragan-Montero AM, Michiels S, et al. Automatic decision tool for head and neck patient referral based on dose prediction with deep learning. [abstract PTC60-0422] PTCOG 60, Miami (United States).
Sher DJ, Godley A, Park Y, et al. Prospective study of artificial intelligence-based decision support to improve head and neck radiotherapy plan quality. Clin Transl Radiat Oncol. 2021;29:65-70.
Chen L, Liang X, Shen C, Nguyen D, Jiang S, Wang J. Synthetic CT generation from CBCT images via unsupervised deep learning. Phys Med Biol. 2021;47(3):115019. http://doi.org/10.1088/1361-6560/ac01b6
Park Y, Sharp GC, Phillips J, Winey BA. Proton dose calculation on scatter-corrected CBCT image: feasibility study for adaptive proton therapy. Med Phys. 2015;42(8):4449-4459. http://doi.org/10.1118/1.4923179
Kurz C, Maspero M, Savenije MHF, et al. CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation. Phys Med Biol. 2019;64:225004.