Highlights
- •115 Pareto-optimal plans were used to assess the prediction accuracy RapidPlan.
- •Prediction models were generated using 20, 30, 45, 55 and 114 plans.
- •Intrinsic accuracy of RapidPlan predictions was estimated for rectum, bladder and anus.
- •For model-114, clinically relevant deviations in DVH predictions were observed.
- •With smaller model size, the prediction showed dependence on the training set.
Abstract
Purpose
Treatment plans manually generated in clinical routine may suffer from variations
and inconsistencies in quality. Using such plans for validating a DVH prediction algorithm
might obscure its intrinsic prediction accuracy. In this study we used a recently
published large database of Pareto-optimal prostate cancer plans to assess the prediction
accuracy of a commercial knowledge-based DVH prediction algorithm, RapidPlan. The
database plans were consistently generated with automated planning using an independent
optimizer, and can be considered as aground truth of plan quality.
Methods
Prediction models were generated using training sets with 20, 30, 45, 55 and 114 Pareto-optimal
plans. Model-20 and Model-30 were built using 5 groups of randomly selected training
patients. For 60 independent Pareto-optimal validation plans, predicted and database
DVHs were compared.
Results
For model-114, differences between predicted and database mean doses of more than ± 10%
in rectum, anus and bladder, occurred for 23.3%, 55.0%, and 6.7% of the validation
plans, respectively. For rectum V65Gy and V75Gy, differences outside the ±10% range were observed in 21.7% and 70.0% of validation
plans, respectively. For 61.7% of validation plans, inaccuracies in predicted rectum
DVHs resulted in a deviation in predicted NTCP for rectal bleeding outside ±10%. With
smaller training sets the DVH prediction performance deteriorated, showing dependence
on the selected training patients.
Conclusion
Even when analysed with Pareto-optimal plans with highly consistent quality, clinically
relevant deviations in DVH predictions were observed. Such deviations could potentially
result in suboptimal plans for new patients. Further research on DVH prediction models
is warranted.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Physica Medica: European Journal of Medical PhysicsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- CG:Point/counterpoint: within the next ten years treatment planning will become fully automated without the need for human intervention.Med Phys. 2014; 42: 120601-120604
- Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning.Phys Medica. 2018; 50: 13-19
- Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy.Phys Medica. 2017; 42 (141–149A)
- On the pre-clinical validation of a commercial model-based optimisation engine: application to volumetric modulated arc therapy for patients with lung or prostate cancer.Radiother Oncol. 2014; 113: 385-391
- Clinical validation and benchmarking of knowledge-based IMRT and VMAT treatment planning in pelvic anatomy.Radiother Oncol. 2016; 120: 473-479
- Knowledge-based treatment planning: an inter-technique and inter-system feasibility study for prostate cancer.Phys Med. 2017; 36: 38-45
- Evaluation of a knowledge-based planning solution for head and neck cancer.Int J Radiat Oncol Biol Phys. 2015; 91: 612-620
- Automatic interactive optimization for volumetric modulated arc therapy planning.Radiat Oncol. 2015; 10: 75
- Assessment of a model based optimization engine for volumetric modulated arc therapy for patients with advanced hepatocellular cancer.Radiat Oncol. 2014; 9: 236
- Automatic treatment planning improves the clinical quality of head and neck cancer treatment plans.Clin Trans Radiat Oncol. 2016; 1: 2-8
- Automatic planning of head and neck treatment plans.J Appl Clin Med Phys. 2016; Jan;; 17: 272-282
- Evaluation of an automated knowledge based treatment planning system for head and neck.Radiad Oncol. 2015; 10: 226
- iCycle: Integrated, multicriterial beam angle, and profile optimization for generation of coplanar and noncoplanar IMRT plans.Med Phys. 2012; 39: 951-963
- Toward fully automated multicriterial plan generation: a prospective clinical study.Int J Radiat Oncol Biol Phys. 2013; 85: 866-872
- Validation of fully automated VMAT plan generation for library-based plan-of-the-day cervical cancer radiotherapy.PLoS ONE. 2016; 11 (e0169202)
- Fully automated VMAT treatment planning for advanced-stage NSCLC patients.Strahlenther Onkol. 2017; https://doi.org/10.1007/s00066-017-1121-1
- Fully automated volumetric modulated arc therapy plan generation for prostate cancer patients.Int J Radiat Oncol Biol Phys. 2014; 88: 1175-1179
- Evaluation of a commercial automatic treatment planning system for liver stereotactic body radiation therapy treatments.Phys Medica. 2018; 46: 153-159
Wang Y., Petit SF. Radiotherapy treatment planning QA. https://www.erasmusmc.nl/radiotherapie/research2/medical-physics/projects/treatment-planning-qa/; 2016.
- Evaluation of plan quality assurance models for prostate cancer patients based on fully automatically generated Pareto-optimal treatment plans.Phys Med Biol. 2016; 61: 4268
Varian Medical System. Eclipse Photon and Electron reference guide v.13.7, 201 Palo Alto CA, 269: 360; 2015.
Varian Model Analytics https://modelanalytics.varian.com/; 2018.
- Can knowledge-based DVH predictions be used for automated, individualized quality assurance of radiotherapy treatment plans?.Radiat Oncol. 2015; 10: 234
- Complication probability as assessed from dose–volume histograms.Radiat Res Suppl. 1985; 8: S13-S19
- Predicting toxicity in radiotherapy for prostate cancer.Physica Med. 2016; 32: 521-532
- Radiation dose-volume effects in radiation-induced rectal injury.Int J Radiat Oncol Biol Phys. 2016; 76: S123-S129
- Modeling the effects of inhomogeneous dose distributions in normal tissues.Semin Radiat Oncol. 2001; 11: 197-209
- Hypofractionated versus conventionally fractionated radiotherapy for patients with prostate cancer (HYPRO): late toxicity results from a randomised, non-inferiority, phase 3 trial.Lancet Oncol. 2016; 17: 464-474
- Effect of dosimetric outliers on the performance of a commercial knowledgebased planning solution.Int J Radiat Oncol Biol Phys. 2016; 94: 469-477
- RapidPlan head and neck model: the objectives and possible clinical benefit.Radiat Oncol. 2017; 12: 73
- Sample size requirements for knowledge-based treatment planning.Med Phys. 2016; 43: 1212
- Predicting dose-volume histograms for organs-at-risk in IMRT planning.Med Phys. 2012; 39: 7446-7461https://doi.org/10.1118/1.4761864
Article info
Publication history
Accepted:
November 3,
2018
Received in revised form:
October 1,
2018
Received:
April 24,
2018
Identification
Copyright
© 2018 Published by Elsevier Ltd on behalf of Associazione Italiana di Fisica Medica.
