Evaluation of a Knowledge-Based Planning Solution for Head and Neck Cancer

PurposeTo test if a RapidPlan DVH estimation model and its training plans can be improved interactively through a closed‐loop evolution process.Methods and materialsEighty‐one manual plans (P0) that were used to configure an initial rectal RapidPlan model (M0) were reoptimized using M0 (closed‐loop), yielding 81 P1 plans. The 75 improved P1 (P1+) and the remaining 6 P0 were used to configure model M1. The 81 training plans were reoptimized again using M1, producing 23 P2 plans that were superior to both their P0 and P1 forms (P2+). Hence, the knowledge base of model M2 composed of 6 P0, 52 P1+, and 23 P2+. Models were tested dosimetrically on 30 VMAT validation cases (Pv) that were not used for training, yielding Pv(M0), Pv(M1), and Pv(M2) respectively. The 30 Pv were also optimized by M2_new as trained by the library of M2 and 30 Pv(M0).ResultsBased on comparable target dose coverage, the first closed‐loop reoptimization significantly (P < 0.01) reduced the 81 training plans’ mean dose to femoral head, urinary bladder, and small bowel by 2.65 Gy/15.63%, 2.06 Gy/8.11%, and 1.47 Gy/6.31% respectively, which were further reduced significantly (P < 0.01) in the second closed‐loop reoptimization by 0.04 Gy/0.28%, 0.18 Gy/0.77%, 0.22 Gy/1.01% respectively. However, open‐loop VMAT validations displayed more complex and intertwined plan quality changes: mean dose to urinary bladder and small bowel decreased monotonically using M1 (by 0.34 Gy/1.47%, 0.25 Gy/1.13%) and M2 (by 0.36 Gy/1.56%, 0.30 Gy/1.36%) than using M0. However, mean dose to femoral head increased by 0.81 Gy/6.64% (M1) and 0.91 Gy/7.46% (M2) than using M0. The overfitting problem was relieved by applying model M2_new.ConclusionsThe RapidPlan model and its constituent plans can improve each other interactively through a closed‐loop evolution process. Incorporating new patients into the original training library can improve the RapidPlan model and the upcoming plans interactively.

Section: Discussionsupporting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

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

Wang

Huang

et al. 2018

“…The plans included in model libraries may be consistent with what has been historically delivered, but may not be representative of what is dosimetrically achievable/optimal. A study by Tol et al found that there were strong correlations between predicted and achieved mean doses when using RapidPlan 10. However, this does not address whether the data from these types of tools led to near‐optimal sparing of OARs.…”

Section: Discussionmentioning

confidence: 99%

Assessment of PlanIQ Feasibility DVH for head and neck treatment planning

Fried

Chera

Das

2017

IntroductionDesigning a radiation plan that optimally delivers both target coverage and normal tissue sparing is challenging. There are limited tools to determine what is dosimetrically achievable and frequently the experience of the planner/physician is relied upon to make these determinations. PlanIQ software provides a tool that uses target and organ at risk (OAR) geometry to indicate the difficulty of achieving different points for organ dose–volume histograms (DVH). We hypothesized that PlanIQ Feasibility DVH may aid planners in reducing dose to OARs.Methods and materialsClinically delivered head and neck treatments (clinical plan) were re‐planned (re‐plan) putting high emphasis on maximally sparing the contralateral parotid gland, contralateral submandibular gland, and larynx while maintaining routine clinical dosimetric objectives. The planner was blinded to the results of the clinically delivered plan as well as the Feasibility DVHs from PlanIQ. The re‐plan treatments were designed using 3‐arc VMAT in Raystation (RaySearch Laboratories, Sweden). The planner was then given the results from the PlanIQ Feasibility DVH analysis and developed an additional plan incorporating this information using 4‐arc VMAT (IQ plan). The DVHs across the three treatment plans were compared with what was deemed “impossible” by PlanIQ's Feasibility DVH (Impossible DVH). The impossible DVH (red) is defined as the DVH generated using the minimal dose that any voxel outside the targets must receive given 100% target coverage.ResultsThe re‐plans performed blinded to PlanIQ Feasibilty DVH achieved superior sparing of aforementioned OARs compared to the clinically delivered plans and resulted in discrepancies from the impossible DVHs by an average of 200–700 cGy. Using the PlanIQ Feasibility DVH led to additional OAR sparing compared to both the re‐plans and clinical plans and reduced the discrepancies from the impossible DVHs to an average of approximately 100 cGy. The dose reduction from clinical to re‐plan and re‐plan to IQ plan were significantly different even when taking into account multiple hypothesis testing for both the contralateral parotid and the larynx (P < 0.004 for all comparisons). No significant differences were observed between the three plans for the contralateral parotid when considering multiple hypothesis testing.ConclusionsClinical treatment plans and blinded re‐plans were found to suboptimally spare OARs. PlanIQ could aid planners in generating treatment plans that push the limits of OAR sparing while maintaining routine clinical target coverage goals.

“…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.…”

Section: Discussionmentioning

confidence: 99%

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

Huang

Yue

Wang

et al. 2018

PurposeEclipse treatment planning system has not been able to optimize the jaw positions for Volumetric Modulated Arc Therapy (VMAT). The arbitrary and planner‐dependent jaw placements define the maximum field size within which multi‐leaf‐collimator (MLC) sequences can be optimized to modulate the beam. Considering the mechanical constraints of MLC transitional speed and range, suboptimal X jaw settings may impede the optimization or undermine the deliverability. This work searches optimal VMAT jaw settings automatically based on Eclipse Scripting Application Programming Interface (ESAPI) and RapidPlan knowledge‐based planning.Methods and materialsUsing an ESAPI script, the X jaws of rectal VMAT plans were initially set to conform the planning‐target‐volume (PTV), and were gradually extended toward the isocenter (PTV center) in 5–7 mm increments. Using these jaw pairs, 592 plans were automatically created for 10 patients and quantitatively evaluated using a comprehensive scoring function. A published RapidPlan model was evoked by ESAPI to generate patient‐specific optimization objectives without manual intervention. All candidate plans were first stored as text files to save storage space, and only the best, worst, and conformal plans were consequently recreated for comparison.ResultsAlthough RapidPlan estimates dose‐volume histogram (DVH) based on individual anatomy, the geometry‐based expected dose (GED) algorithm does not recognize different jaw settings but uses PTV‐conformal jaws as default; hence, identical DVHs were observed regardless of planner‐defined jaws. Therefore, ESAPI finalized dose‐volume calculation and eliminated the plans with unacceptable hotspots before comparison. The plan quality varied dramatically with different jaw settings. Trade‐offs among different organs‐at‐risk (OARs) were collectively considered by the proposed scoring method, which identified the best and worst plans correctly. The plans using conformal jaws were neither the best nor the worst of all candidates.Conclusions VMAT plans using optimal jaw locations can be created automatically using ESAPI and RapidPlan. Conformal jaws are not the optimal choice.