Impact of database quality in knowledge-based treatment planning for prostate cancer

Determining the library size for the optimal output plan in the RapidPlan knowledge-based planning system using multicriteria optimization

OBJECTIVES

The aim of this study was to determine the number of trade-off explored (TO) library plans required for building a RapidPlan (RP) library that would generate the optimal clinical treatment plan.

METHODS

We developed 2 RP models, 1 each for the 2 clinical sites, head and neck (HN) and cervix. The models were created using 100 plans and were validated using 70 plans (VP) for each site respectively. Each of the 2 libraries comprising 100 TO plans was divided into 5 different subsets of library plans comprising 20, 40, 60, 80, and 100 plans, leading to 5 different RP models for each site. For every validation patient, a TO plan (TO_VP) was created. For every patient, 5 RP plans were automatically generated using RP models. The dosimetric parameters of the 6 plans (TO_VP + 5 RP plans) were compared using Pearson correlation and Greenhouse-Geisser analysis.

RESULTS

Planning target volume (PTV) dose volume parameters PTVD95% in 6 competing plans varied between 97.6 ± 0.7% and 98.1 ± 0.6% in HN cases and 98.8 ± 0.3% and 99.0 ± 0.4% in cervix cases. Overall, for both sites, the mean variations in organ at risk (OAR) doses or volumes were within 50 cGy, 0.5%, and 0.2 cc between library plans, and if TO_VP was included the variations deteriorated to 180 cGy, 0.4%, and 15 cc. All OARs in both sites, except D0.1 ccspine, showed a statistically insignificant variation between all plans.

CONCLUSIONS

Dosimetric variation among various output plans generated from 5 RP libraries is minimal and clinically insignificant. The optimal output plan can be derived from the least-weighted library consisting of 20 plans.

ADVANCES IN KNOWLEDGE

This article shows that, when the constituent plans are subjected to trade-off exploration, the number of constituent plans for a knowledge-based planning module is not relevant in terms of its dosimetric output.

Artificial intelligence applications in intensity modulated radiation treatment planning: an overview

Artificial intelligence (AI) refers to methods that improve and automate challenging human tasks by systematically capturing and applying relevant knowledge in these tasks. Over the past decades, a number of approaches have been developed to address different types and needs of system intelligence ranging from search strategies to knowledge representation and inference to robotic planning. In the context of radiation treatment planning, multiple AI approaches may be adopted to improve the planning quality and efficiency. For example, knowledge representation and inference methods may improve dose prescription by integrating and reasoning about the domain knowledge described in many clinical guidelines and clinical trials reports. In this review, we will focus on the most studied AI approach in intensity modulated radiation therapy (IMRT)/volumetric modulated arc therapy (VMAT)-machine learning (ML) and describe our recent efforts in applying ML to improve the quality, consistency, and efficiency of IMRT/VMAT planning. With the available high-quality data, we can build models to accurately predict critical variables for each step of the planning process and thus automate and improve its outcomes. Specific to the IMRT/VMAT planning process, we can build models for each of the four critical components in the process: dose-volume histogram (DVH), Dose, Fluence, and Human Planner. These models can be divided into two general groups. The first group focuses on encoding prior experience and knowledge through ML and more recently deep learning (DL) from prior clinical plans and using these models to predict the optimal DVH (DVH prediction model), or 3D dose distribution (dose prediction model), or fluence map (fluence map model). The goal of these models is to reduce or remove the trial-and-error process and guarantee consistently high-quality plans. The second group of models focuses on mimicking human planners' decision-making process (planning strategy model) during the iterative adjustments/guidance of the optimization engine. Each critical step of the IMRT/VMAT treatment planning process can be improved and automated by AI methods. As more training data becomes available and more sophisticated models are developed, we can expect that the AI methods in treatment planning will continue to improve accuracy, efficiency, and robustness.

Dose Prediction Models Based on Geometric and Plan Optimization Parameter for Adjuvant Radiotherapy Planning Design in Cervical Cancer Radiotherapy

The prediction of an additional space for the dose sparing of organs at risk (OAR) in radiotherapy is still difficult. In this pursuit, the present study was envisaged to find out the factors affecting the bladder and rectum dosimetry of cervical cancer. Additionally, the relationship between the dose-volume histogram (DVH) parameters and the geometry and plan dose-volume optimization parameters of the bladder/rectum was established to develop the dose prediction models and guide the planning design for lower OARs dose coverage directly. Thirty volume modulated radiation therapy (VMAT) plans from cervical cancer patients were randomly chosen to build the dose prediction models. The target dose coverage was evaluated. Dose prediction models were established by univariate and multiple linear regression among the dosimetric parameters of the bladder/rectum, the geometry parameters (planning target volume (PTV), volume of bladder/rectum, overlap volume of bladder/rectum (OV), and overlapped volume as a percentage of bladder/rectum volume (OP)), and corresponding plan dose-volume optimization parameters of the nonoverlapping structures (the structure of bladder/rectum outside the PTV (NOS)). Finally, the accuracy of the prediction models was evaluated by tracking d = (predicted dose-actual dose)/actual in additional ten VMAT plans. V ₃₀, V ₃₅, and V ₄₀ of the bladder and rectum were found to be multiple linearly correlated with the relevant OP and corresponding dose-volume optimization parameters of NOS (regression R ² > 0.99, P < 0.001). The variations of these models were less than 0.5% for bladder and rectum. Percentage of bladder and rectum within the PTV and the dose-volume optimization parameters of NOS could be used to predict the dose quantitatively. The parameters of NOS as a limited condition could be used in the plan optimization instead of limiting the dose and volume of the entire OAR traditionally, which made the plan optimization more unified and convenient and strengthened the plan quality and consistency.

Outcome-based multiobjective optimization of lymphoma radiation therapy plans

At its core, radiation therapy (RT) requires balancing therapeutic effects against risk of adverse events in cancer survivors. The radiation oncologist weighs numerous disease and patient-level factors when considering the expected risk-benefit ratio of combined treatment modalities. As part of this, RT plan optimization software is used to find a clinically acceptable RT plan delivering a prescribed dose to the target volume while respecting pre-defined radiation dose-volume constraints for selected organs at risk. The obvious limitation to the current approach is that it is virtually impossible to ensure the selected treatment plan could not be bettered by an alternative plan providing improved disease control and/or reduced risk of adverse events in this individual. Outcome-based optimization refers to a strategy where all planning objectives are defined by modeled estimates of a specific outcome's probability. Noting that various adverse events and disease control are generally incommensurable, leads to the concept of a Pareto-optimal plan: a plan where no single objective can be improved without degrading one or more of the remaining objectives. Further benefits of outcome-based multiobjective optimization are that quantitative estimates of risks and benefit are obtained as are the effects of choosing a different trade-off between competing objectives. Furthermore, patient-level risk factors and combined treatment modalities may be integrated directly into plan optimization. Here, we present this approach in the clinical setting of multimodality therapy for malignant lymphoma, a malignancy with marked heterogeneity in biology, target localization, and patient characteristics. We discuss future research priorities including the potential of artificial intelligence.

Assessment of a conventional volumetric-modulated arc therapy knowledge-based planning model applied to the new Halcyon© O-ring linac in locoregional breast cancer radiotherapy

INTRODUCTION

The aim of this study was to evaluate the performance of a knowledge-based planning (KBP) model for breast cancer trained on plans performed on a conventional linac with 6 MV FF (flattening filter) beams and volumetric-modulated arc therapy (VMAT) for plans performed on the new jawless Halcyon© system with 6 MV FFF (flattening filter-free) beams.

MATERIALS AND METHODS

Based on the RapidPlan© (RP) KBP optimization engine, a DVH Estimation Model was first trained using 56 VMAT left-sided breast cancer treatment plans performed on a conventional linac, and validated on another 20 similar cases (without manual intervention). To determine the capacity of the model for Halcyon©, an additional cohort of 20 left-sided breast cancer plans was generated with RP and analyzed for both TrueBeam© and Halcyon© machines. Plan qualities between manual vs RP (followed by manual intervention) Halcyon© plans set were compared qualitatively by blinded review by radiation oncologists for 10 new independent plans.

RESULTS

Halcyon© plans generated with the VMAT model trained with conventional linac plans showed comparable target dose distribution compared to TrueBeam© plans. Organ sparingwas comparable between the 2 devices with a slight decrease in heart dose for Halcyon© plans. Nine out of ten automatically generated Halcyon© plans were preferentially chosen by the radiation oncologists over the manually generated Halcyon© plans.

CONCLUSION

A VMAT KBP model driven by plans performed on a conventional linac with 6 MV FF beams provides high quality plans performed with 6 MV FFF beams on the new Halcyon© linac.

Quality assurance-based optimization (QAO): Towards improving patient-specific quality assurance in volumetric modulated arc therapy plans using machine learning

INTRODUCTION

Previous literature has shown general trade-offs between plan complexity and resulting quality assurance (QA) outcomes. However, existing solutions for controlling this trade-off do not guarantee corresponding improvements in deliverability. Therefore, this work explored the feasibility of an optimization framework for directly maximizing predicted QA outcomes of plans without compromising the dosimetric quality of plans designed with an established knowledge-based planning (KBP) technique.

MATERIALS AND METHODS

A support vector machine (SVM) was developed - using a database of 500 previous VMAT plans - to predict gamma passing rates (GPRs; 3%/3mm percent dose-difference/distance-to-agreement with local normalization) based on selected complexity features. A heuristic, QA-based optimization (QAO) framework was devised by utilizing the SVM model to iteratively modify mechanical treatment features most commonly associated with suboptimal GPRs. Specifically, leaf gaps (LGs) <50 mm were widened by random amounts, which impacts all aperture-based complexity features. 13 prostate KBP-guided VMAT plans were optimized via QAO using user-specified maximum LG displacements before corresponding changes in predicted GPRs and dose were assessed.

RESULTS

Predicted GPRs increased by an average of 1.14 ± 1.25% (p = 0.006) with QAO using a 3 mm maximum random LG displacement. There were small differences in dose, resulting in similarly small changes in tumor control probability (maximum increase = 0.05%) and normal tissue complication probabilities in the bladder, rectum, and femoral heads (maximum decrease = 0.2% in the rectum).

CONCLUSION

This study explored the feasibility of QAO and warrants future investigations of further incorporating QA endpoints into plan optimization.

Generalized approach for radiotherapy treatment planning by optimizing projected health outcome: preliminary results for prostate radiotherapy patients

Research in cancer care increasingly focuses on survivorship issues, e.g. managing disease- and treatment-related morbidity and mortality occurring during and after treatment. This necessitates innovative approaches that consider treatment side effects in addition to tumor cure. Current treatment-planning methods rely on constrained iterative optimization of dose distributions as a surrogate for health outcomes. The goal of this study was to develop a generally applicable method to directly optimize projected health outcomes. We developed an outcome-based objective function to guide selection of the number, angle, and relative fluence weight of photon and proton radiotherapy beams in a sample of ten prostate-cancer patients by optimizing the projected health outcome. We tested whether outcome-optimized radiotherapy (OORT) improved the projected longitudinal outcome compared to dose-optimized radiotherapy (DORT) first for a statistically significant majority of patients, then for each individual patient. We assessed whether the results were influenced by the selection of treatment modality, late-risk model, or host factors. The results of this study revealed that OORT was superior to DORT. Namely, OORT maintained or improved the projected health outcome of photon- and proton-therapy treatment plans for all ten patients compared to DORT. Furthermore, the results were qualitatively similar across three treatment modalities, six late-risk models, and 10 patients. The major finding of this work was that it is feasible to directly optimize the longitudinal (i.e. long- and short-term) health outcomes associated with the total (i.e. therapeutic and stray) absorbed dose in all of the tissues (i.e. healthy and diseased) in individual patients. This approach enables consideration of arbitrary treatment factors, host factors, health endpoints, and times of relevance to cancer survivorship. It also provides a simpler, more direct approach to realizing the full beneficial potential of cancer radiotherapy.

Knowledge-Based Tradeoff Hyperplanes for Head and Neck Treatment Planning

PURPOSE

To develop a tradeoff hyperplane model to facilitate tradeoff decision-making before inverse planning.

METHODS AND MATERIALS

We propose a model-based approach to determine the tradeoff hyperplanes that allow physicians to navigate the clinically viable space of plans with best achievable dose-volume parameters before planning. For a given case, a case reference set (CRS) is selected using a novel anatomic similarity metric from a large reference plan pool. Then, a regression model is built on the CRS to estimate the expected dose-volume histograms (DVHs) for the current case. This model also predicts the DVHs for all CRS cases and captures the variation from the corresponding DVHs in the clinical plans. Finally, these DVH variations are analyzed using the principal component analysis to determine the tradeoff hyperplane for the current case. To evaluate the effectiveness of the proposed approach, 244 head and neck cases were randomly partitioned into reference (214) and validation (30) sets. A tradeoff hyperplane was built for each validation case and evenly sampled for 12 tradeoff predictions. Each prediction yielded a tradeoff plan. The root-mean-square errors of the predicted and the realized plan DVHs were computed for prediction achievability evaluation.

RESULTS

The tradeoff hyperplane with 3 principal directions accounts for 57.8% ± 3.6% of variations in the validation cases, suggesting the hyperplanes capture a significant portion of the clinical tradeoff space. The average root-mean-square errors in 3 tradeoff directions are 5.23 ± 2.46, 5.20 ± 2.52, and 5.19 ± 2.49, compared with 4.96 ± 2.48 of the knowledge-based planning predictions, indicating that the tradeoff predictions are comparably achievable.

CONCLUSIONS

Clinically relevant tradeoffs can be effectively extracted from existing plans and characterized by a tradeoff hyperplane model. The hyperplane allows physicians and planners to explore the best clinically achievable plans with different organ-at-risk sparing goals before inverse planning and is a natural extension of the current knowledge-based planning framework.

Evaluation of complexity and deliverability of prostate cancer treatment plans designed with a knowledge-based VMAT planning technique

PURPOSE

Knowledge-based planning (KBP) techniques have been reported to improve plan quality, efficiency, and consistency in radiation therapy. However, plan complexity and deliverability have not been addressed previously for treatment plans guided by an established in-house KBP system. The purpose of this work was to assess dosimetric, mechanical, and delivery properties of plans designed with a common KBP method for prostate cases treated via volumetric modulated arc therapy (VMAT).

METHODS

Thirty-one prostate patients previously treated with VMAT were replanned with an in-house KBP method based on the overlap volume histogram. VMAT plan complexities of the KBP plans and the reference clinical plans were quantified via monitor units, modulation complexity scores, the edge metric, and average leaf motion per degree of gantry rotation. Each set of plans was delivered to the same diode array and agreement between computed and measured dose distributions was evaluated using the gamma index. Varying percent dose-difference (1-3%) and distance-to-agreement (1 mm to 3 mm) thresholds were assessed for gamma analyses.

RESULTS

Knowledge-based planning (KBP) plans achieved average reductions of 6.4 Gy (P < 0.001) and 8.2 Gy (P < 0.001) in mean bladder and rectum dose compared to reference plans, while maintaining clinically acceptable target dose. However, KBP plans were significantly more complex than reference plans in each evaluated metric (P < 0.001). KBP plans also showed significant reductions (P < 0.05) in gamma passing rates at each evaluated criterion compared to reference plans.

CONCLUSIONS

While KBP plans had significantly reduced bladder and rectum dose, they were significantly more complex and had significantly worse quality assurance outcomes than reference plans. These results suggest caution should be taken when implementing an in-house KBP technique.

A Model-Based Method for Assessment of Salivary Gland and Planning Target Volume Dosimetry in Volumetric-Modulated Arc Therapy Planning on Head-and-Neck Cancer

This study examined the relationship of achievable mean dose and percent volumetric overlap of salivary gland with the planning target volume (PTV) in volumetric-modulated arc therapy (VMAT) plan in radiotherapy for a patient with head-and-neck cancer. The aim was to develop a model to predict the viability of planning objectives for both PTV coverage and organs-at-risk (OAR) sparing based on overlap volumes between PTVs and OARs, before the planning process. Forty patients with head-and-neck cancer were selected for this retrospective plan analysis. The patients were treated using 6 MV photons with 2-arc VMAT plan in prescriptions with simultaneous integrated boost in dose of 70 Gy, 63 Gy, and 58.1 Gy to primary tumor sites, high-risk nodal regions, and low-risk nodal regions, respectively, over 35 fractions. A VMAT plan was generated using Varian Eclipse (V13.6), in optimization with biological-based generalized equivalent uniform dose (gEUD) objective for OARs and targets. Target dose coverage (D₉₅, D_max, conformity index) and salivary gland dose (D_mean and D_max) were evaluated in those plans. With a range of volume overlaps between salivary glands and PTVs and dose constraints applied, results showed that dose D₉₅ for each PTV was adequate to satisfy D₉₅ >95% of the prescription. Mean dose to parotid <26 Gy could be achieved with <20% volumetric overlap with PTV₅₈ (parotid-PTV₅₈). On an average, the D_mean was seen at 15.6 Gy, 21.1 Gy, and 24.2 Gy for the parotid-PTV₅₈ volume at <5%, <10%, and <20%, respectively. For submandibular glands (SMGs), an average D_mean of 27.6 Gy was achieved in patients having <10% overlap with PTV₅₈, and 36.1 Gy when <20% overlap. Mean doses on parotid and SMG were linearly correlated with overlap volume (regression R² = 0.95 and 0.98, respectively), which were statistically significant (P < 0.0001). This linear relationship suggests that the assessment of the structural overlap might provide prospective for achievable planning objectives in the head-and-neck plan.