A broad scope knowledge based model for optimization of VMAT in esophageal cancer: validation and assessment of plan quality among different treatment centers

Abstract

BackgroundTo evaluate the performance of a broad scope model-based optimisation process for volumetric modulated arc therapy applied to esophageal cancer.Methods and materialsA set of 70 previously treated patients in two different institutions, were selected to train a model for the prediction of dose-volume constraints. The model was built with a broad-scope purpose, aiming to be effective for different dose prescriptions and tumour localisations. It was validated on three groups of patients from the same institution and from another clinic not providing patients for the training phase. Comparison of the automated plans was done against reference cases given by the clinically accepted plans.ResultsQuantitative improvements (statistically significant for the majority of the analysed dose-volume parameters) were observed between the benchmark and the test plans. Of 624 dose-volume objectives assessed for plan evaluation, in 21 cases (3.3 %) the reference plans failed to respect the constraints while the model-based plans succeeded. Only in 3 cases (<0.5 %) the reference plans passed the criteria while the model-based failed. In 5.3 % of the cases both groups of plans failed and in the remaining cases both passed the tests.ConclusionsPlans were optimised using a broad scope knowledge-based model to determine the dose-volume constraints. The results showed dosimetric improvements when compared to the benchmark data. Particularly the plans optimised for patients from the third centre, not participating to the training, resulted in superior quality. The data suggests that the new engine is reliable and could encourage its application to clinical practice.Electronic supplementary materialThe online version of this article (doi:10.1186/s13014-015-0530-5) contains supplementary material, which is available to authorized users.

A dosimetric evaluation of knowledge‐based VMAT planning with simultaneous integrated boosting for rectal cancer patients

“…RapidPlan‐associated dose reduction to the bladder 7 , 13 and femoral head 7 , 12 , 13 were macroscopic and significant. Similar improvement of OAR sparing and consistency has also been widely reported in other clinical sites 14 , 15 , 16 , 17 …”

“…As other potential limitations of RapidPlan, some critical parameters such as the beam energy and field geometry are not optimizable by the model, which may vary dramatically among different centers and planners. That was why custom models were more popular in the previous publications 12 , 13 , 14 , 15 , 16 , 17 . As for this study, the historical plans represent the average quality that is currently and reasonably achievable, and the improvement may be mostly attributable to the personalized objective as estimated by RapidPlan, which passes on the expertise as incorporated in the model to prospective plans.…”

“…Relative to the conventional experience‐based planning, superior or comparable results of RapidPlan have been reported in the preliminary applications to head and neck, lung, oesophageal, breast, hepatocellular, and prostate cancer patients 12 , 13 , 14 , 15 , 16 , 17 . However, consensus has been reached by these studies that both the model training and plan evaluation should be investigated further in a larger population and other cancer types in order to gain more experience and confidence before it is extensively applied clinically world‐wide.…”

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

“…Knowledge‐based radiotherapy treatment planning is deemed to reduce the inter‐planner varieties of plan quality1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13 and expedite the planning process 14, 15, 16, 1718, 19 and displayed good compatibility across patient orientations, treatment techniques, and systems 20, 21…”

Fully automated searching for the optimal VMAT jaw settings based on Eclipse Scripting Application Programming Interface (ESAPI) and RapidPlan knowledge‐based planning

“…Although the RapidPlan model generated identical optimization objectives for the same patient anatomy and beam geometry (except jaws), the knowledge‐based planning module in the proposed optimal jaw searching method is intended to avoid subjective planner dependence, and to personalize the automated optimization in case of different patient anatomy, prescription, field geometry and energies, which were all modeled by RapidPlan in dose prediction 9, 17, 18, 19, 20. However, it is highly desired that, the next versions of RapidPlan should model the actual jaw settings for more accurate dose estimation, which may potentially serve as a fast and sensitive indicator of dosimetric changes with various jaw settings.…”