PARETO: A novel evolutionary optimization approach to multiobjective IMRT planning

Comparing Multi-Objective Local Search Algorithms for the Beam Angle Selection Problem

In intensity-modulated radiation therapy, treatment planners aim to irradiate the tumour according to a medical prescription while sparing surrounding organs at risk as much as possible. Although this problem is inherently a multi-objective optimisation (MO) problem, most of the models in the literature are single-objective ones. For this reason, a large number of single-objective algorithms have been proposed in the literature to solve such single-objective models rather than multi-objective ones. Further, a difficulty that one has to face when solving the MO version of the problem is that the algorithms take too long before converging to a set of (approximately) non-dominated points. In this paper, we propose and compare three different strategies, namely random PLS (rPLS), judgement-function-guided PLS (jPLS) and neighbour-first PLS (nPLS), to accelerate a previously proposed Pareto local search (PLS) algorithm to solve the beam angle selection problem in IMRT. A distinctive feature of these strategies when compared to the PLS algorithms in the literature is that they do not evaluate their entire neighbourhood before performing the dominance analysis. The rPLS algorithm randomly chooses the next non-dominated solution in the archive and it is used as a baseline for the other implemented algorithms. The jPLS algorithm first chooses the non-dominated solution in the archive that has the best objective function value. Finally, the nPLS algorithm first chooses the solutions that are within the neighbourhood of the current solution. All these strategies prevent us from evaluating a large set of BACs, without any major impairment in the obtained solutions’ quality. We apply our algorithms to a prostate case and compare the obtained results to those obtained by the PLS from the literature. The results show that algorithms proposed in this paper reach a similar performance than PLS and require fewer function evaluations.

Clinical Use of A Priori Knowledge of OAR Sparing During Radiotherapy Treatment for Oropharyngeal Cancer: Dosimetric and Patient Reported Outcome Improvements

PURPOSE

To prospectively assess dosimetric and clinical impacts of treatment planners having a priori knowledge of the maximum achievable dose sparing for organs at risk for patients with oropharynx cancer receiving IMRT.

METHODS AND MATERIALS

We examined oropharynx cancer patients treated on prospective clinical trials from February 2012 to April 2019 at our institution. A tool that generates estimates of maximum achievable dose sparing for organs at risk (Feasibility-DVH; FDVH) was used clinically starting July 2016. Patients were divided into cohorts:pre-FDVH (i.e. baseline) and post-FDVH (i.e. FDVH-guided). Doses received by various OARs were compared to those estimated to be achievable per FDVH and that difference was defined as the 'excess of feasible dose'. Patient reported outcomes (PRO) questionnaires were completed at 3, 6 and 12 months post-treatment. The baseline and FDVH-guided cohorts were compared in terms of excess of feasible dose, plan quality metrics, and post-RT PRO assessments.

RESULTS

One hundred thirty-nine patients were included in the analysis (60-baseline cohort, 79-FDVH-guided cohort). The FDVH-guided cohort had lower excess of feasible dose to the contralateral parotid by 4.1Gy, the ipsilateral parotid by 10.6Gy, the larynx by 4.3Gy, the oral cavity by 1.5Gy, and the contralateral submandibular gland by 0.4Gy. Plan quality metrics were similar between the cohorts. Less variation of excess of feasible dose was seen in the FDVH-guided cohort for the parotid glands and contralateral submandibular gland (p<0.05). The average post-RT PROs were better in the FVHD cohort vs baseline (particularly at the 6 month time point for dry mouth frequency, sticky saliva, meal enjoyment, severity of pain, and EAT10 composite (swallowing); p<0.05).

CONCLUSIONS

Use of FDVH was associated with improved and less variable OAR sparing for clinically delivered plans. FDVH-guided patients had improved PROs compared to baseline with a variety of outcomes significantly improved at 6 months post-treatment.

Using Emulation to Engineer and Understand Simulations of Biological Systems

Modeling and simulation techniques have demonstrated success in studying biological systems. As the drive to better capture biological complexity leads to more sophisticated simulators, it becomes challenging to perform statistical analyses that help translate predictions into increased understanding. These analyses may require repeated executions and extensive sampling of high-dimensional parameter spaces: analyses that may become intractable due to time and resource limitations. Significant reduction in these requirements can be obtained using surrogate models, or emulators, that can rapidly and accurately predict the output of an existing simulator. We apply emulation to evaluate and enrich understanding of a previously published agent-based simulator of lymphoid tissue organogenesis, showing an ensemble of machine learning techniques can reproduce results obtained using a suite of statistical analyses within seconds. This performance improvement permits incorporation of previously intractable analyses, including multi-objective optimization to obtain parameter sets that yield a desired response, and Approximate Bayesian Computation to assess parametric uncertainty. To facilitate exploitation of emulation in simulation-focused studies, we extend our open source statistical package, spartan, to provide a suite of tools for emulator development, validation, and application. Overcoming resource limitations permits enriched evaluation and refinement, easing translation of simulator insights into increased biological understanding.

Voxel-based automatic multi-criteria optimization for intensity modulated radiation therapy

Background

Automatic multi-criteria optimization is necessary for intensity modulated radiation therapy (IMRT) because of low planning efficiency and large plan quality uncertainty in current clinical practice. Most studies focused on imitating dosimetrists’ planning procedures to automate this process and ignored the fact that organ-based objective functions typically used in commercial treatment planning systems (such as dose-volume function) usually lead to sub-optimal plans. To guarantee the optimum results and to automate this process, we incorporate an improved automation strategy and a voxel-based optimization algorithm to generate a novel automatic multi-criteria optimization framework. We then evaluate it in clinical cases.

Methods

This novel automatic multi-criteria optimization framework incorporates a ranked priority-list based automatic constraints adjustment strategy and an in-house developed voxel-based optimization algorithm. Constraints are sequentially adjusted following a pre-defined priority list. Afterward, a voxel-based fluence map optimization (FMO) with an orientation to the newly updated constraints is launched to find a Pareto optimal solution. Loops of constraints adjustment are repeated until each of them could not be relaxed or tightened. The feasibility of the framework is evaluated with 10 automatic generated gynecology (GYN) cancer IMRT cases by comparing the dosimetric performance with the original.

Results

Plan quality improvement is observed for our automatic multi-criteria optimization method. Comparable DVHs are found for the planning target volume (PTV), but with better organs-at-risk (OAR) dose sparing. Among 13 evaluated dosimetric endpoints, 5 of them show significant improvements in automatically generated plans compared with the original plans. Investigation of improvement tendency during optimization exhibits gradual change as the optimization stage proceeds. An initial voxel-based optimization stage and in-low-priority dosimetric criteria tighten can significantly contribute to the optimization procedure.

Conclusions

We have successfully developed an automatic multi-criteria optimization framework that can dramatically reduce the current trial-and-error patterned planning workload while affording an efficient method to assure high plan quality consistency. This optimization framework is expected to greatly facilitate precise radiation therapy because of its advantages of planning efficiency and plan quality improvement.

Adaptive method for multicriteria optimization of intensity-modulated proton therapy

PURPOSE

Provide an adaptive multicriteria optimization (MCO) method for intensity-modulated proton therapy (IMPT) utilizing GPU technology. Previously described limitations of MCO such as Pareto approximation and limitation on the number of objectives were addressed.

METHODS

The treatment planning process for IMPT must account for multiple objectives, which requires extensive treatment planning resources. Often a large number of objectives (>10) are required. Hence the need for an MCO algorithm that can handle large number of objectives. The novelty of the MCO method presented here lies on the introduction of the adaptive weighting scheme that can generate a well-distributed and dense representation of the Pareto surface for a large number of objectives in an efficient manner. In our approach the generated Pareto surface is constructed for a set of DVH objectives. The MCO algorithm is based on the augmented weighted Chebychev metric (AWCM) method with an adaptive weighting scheme. This scheme uses the differential evolution (DE) method to generate a set of well-distributed Pareto points. The quality of the Pareto points' distribution in the objective space was assessed quantitatively using the Pareto sampling metric. The MCO algorithm was developed to perform multiple parallel searches to achieve a rapid mapping of the Pareto surface, produce clinically deliverable plans, and was implemented on a GPU cluster. The MCO algorithm was tested on two clinical cases with 10 and 18 objectives. For each case one of the MCO-generated plans was selected for comparison with the clinically generated plan. The MCO plan was randomly selected out of the set of MCO plans that had target coverage similar to the clinically generated plan and the same or better sparing of the organs at risk (OAR). Additionally, a validation study of the AWCM method vs the weighted sum method was performed.

RESULTS

The adaptive MCO algorithm generated Pareto points on the Pareto hypersurface in a fast (2-3 hr) and efficient manner for 2 cases with 10 and 18 objectives. The MCO algorithm generated a dense and well-distributed set of Pareto points on the objective space, and was able to achieve minimization of the Pareto sampling metric. The selected MCO plan showed an improvement of the DVH objectives in comparison to the clinically optimized plan in both cases. For case one, the MCO plan showed a 48% reduction of the 50% dose to OARs and a 16% reduction of the 1% dose to OARs. For case 2, the MCO plan showed a 72% reduction of the 50% dose to OARs and a 42% reduction of the 1% dose to OARs. The comparison of AWCM to WS showed that the AWCM method has a dosimetric advantage over WS for both patient cases.

CONCLUSION

We introduced an adaptive MCO algorithm for IMPT accelerated using GPUs. The algorithm is based on an adaptive method for generating Pareto plans in the objective space. We have shown that the algorithm can provide rapid and efficient mapping of the multicriteria Pareto surface with clinically deliverable plans.

Investigating multi-objective fluence and beam orientation IMRT optimization

Radiation Oncology treatment planning requires compromises to be made between clinical objectives that are invariably in conflict. It would be beneficial to have a 'bird's-eye-view' perspective of the full spectrum of treatment plans that represent the possible trade-offs between delivering the intended dose to the planning target volume (PTV) while optimally sparing the organs-at-risk (OARs). In this work, the authors demonstrate Pareto-aware radiotherapy evolutionary treatment optimization (PARETO), a multi-objective tool featuring such bird's-eye-view functionality, which optimizes fluence patterns and beam angles for intensity-modulated radiation therapy (IMRT) treatment planning. The problem of IMRT treatment plan optimization is managed as a combined monolithic problem, where all beam fluence and angle parameters are treated equally during the optimization. To achieve this, PARETO is built around a powerful multi-objective evolutionary algorithm, called Ferret, which simultaneously optimizes multiple fitness functions that encode the attributes of the desired dose distribution for the PTV and OARs. The graphical interfaces within PARETO provide useful information such as: the convergence behavior during optimization, trade-off plots between the competing objectives, and a graphical representation of the optimal solution database allowing for the rapid exploration of treatment plan quality through the evaluation of dose-volume histograms and isodose distributions. PARETO was evaluated for two relatively complex clinical cases, a paranasal sinus and a pancreas case. The end result of each PARETO run was a database of optimal (non-dominated) treatment plans that demonstrated trade-offs between the OAR and PTV fitness functions, which were all equally good in the Pareto-optimal sense (where no one objective can be improved without worsening at least one other). Ferret was able to produce high quality solutions even though a large number of parameters, such as beam fluence and beam angles, were included in the optimization.

Fully automated VMAT treatment planning for advanced-stage NSCLC patients

PURPOSE

To develop a fully automated procedure for multicriterial volumetric modulated arc therapy (VMAT) treatment planning (autoVMAT) for stage III/IV non-small cell lung cancer (NSCLC) patients treated with curative intent.

MATERIALS AND METHODS

After configuring the developed autoVMAT system for NSCLC, autoVMAT plans were compared with manually generated clinically delivered intensity-modulated radiotherapy (IMRT) plans for 41 patients. AutoVMAT plans were also compared to manually generated VMAT plans in the absence of time pressure. For 16 patients with reduced planning target volume (PTV) dose prescription in the clinical IMRT plan (to avoid violation of organs at risk tolerances), the potential for dose escalation with autoVMAT was explored.

RESULTS

Two physicians evaluated 35/41 autoVMAT plans (85%) as clinically acceptable. Compared to the manually generated IMRT plans, autoVMAT plans showed statistically significant improved PTV coverage (V_95% increased by 1.1% ± 1.1%), higher dose conformity (R₅₀ reduced by 12.2% ± 12.7%), and reduced mean lung, heart, and esophagus doses (reductions of 0.9 Gy ± 1.0 Gy, 1.5 Gy ± 1.8 Gy, 3.6 Gy ± 2.8 Gy, respectively, all p < 0.001). To render the six remaining autoVMAT plans clinically acceptable, a dosimetrist needed less than 10 min hands-on time for fine-tuning. AutoVMAT plans were also considered equivalent or better than manually optimized VMAT plans. For 6/16 patients, autoVMAT allowed tumor dose escalation of 5-10 Gy.

CONCLUSION

Clinically deliverable, high-quality autoVMAT plans can be generated fully automatically for the vast majority of advanced-stage NSCLC patients. For a subset of patients, autoVMAT allowed for tumor dose escalation.

Application programming in C# environment with recorded user software interactions and its application in autopilot of VMAT/IMRT treatment planning

An autopilot scheme of volumetric‐modulated arc therapy (VMAT)/intensity‐modulated radiation therapy (IMRT) planning with the guidance of prior knowledge is established with recorded interactions between a planner and a commercial treatment planning system (TPS). Microsoft (MS) Visual Studio Coded UI is applied to record some common planner‐TPS interactions as subroutines. The TPS used in this study is a Windows‐based Eclipse system. The interactions of our application program with Eclipse TPS are realized through a series of subroutines obtained by prerecording the mouse clicks or keyboard strokes of a planner in operating the TPS. A strategy to autopilot Eclipse VMAT/IMRT plan selection process is developed as a specific example of the proposed “scripting” method. The autopiloted planning is navigated by a decision function constructed with a reference plan that has the same prescription and similar anatomy with the case at hand. The calculation proceeds by alternating between the Eclipse optimization and the outer‐loop optimization independent of the Eclipse. In the C# program, the dosimetric characteristics of a reference treatment plan are used to assess and modify the Eclipse planning parameters and to guide the search for a clinically sensible treatment plan. The approach is applied to plan a head and neck (HN) VMAT case and a prostate IMRT case. Our study demonstrated the feasibility of application programming method in C# environment with recorded interactions of planner‐TPS. The process mimics a planner's planning process and automatically provides clinically sensible treatment plans that would otherwise require a large amount of manual trial and error of a planner. The proposed technique enables us to harness a commercial TPS by application programming via the use of recorded human computer interactions and provides an effective tool to greatly facilitate the treatment planning process.

PACS number(s): 87.55.D‐, 87.55.kd, 87.55.de

A surrogate-based metaheuristic global search method for beam angle selection in radiation treatment planning

An important element of radiation treatment planning for cancer therapy is the selection of beam angles (out of all possible coplanar and non-coplanar angles in relation to the patient) in order to maximize the delivery of radiation to the tumor site and minimize radiation damage to nearby organs-at-risk. This category of combinatorial optimization problem is particularly difficult because direct evaluation of the quality of treatment corresponding to any proposed selection of beams requires the solution of a large-scale dose optimization problem involving many thousands of variables that represent doses delivered to volume elements (voxels) in the patient. However, if the quality of angle sets can be accurately estimated without expensive computation, a large number of angle sets can be considered, increasing the likelihood of identifying a very high quality set. Using a computationally efficient surrogate beam set evaluation procedure based on single-beam data extracted from plans employing equallyspaced beams (eplans), we have developed a global search metaheuristic process based on the nested partitions framework for this combinatorial optimization problem. The surrogate scoring mechanism allows us to assess thousands of beam set samples within a clinically acceptable time frame. Tests on difficult clinical cases demonstrate that the beam sets obtained via our method are of superior quality.

Reduced-order constrained optimization (ROCO): clinical application to head-and-neck IMRT

PURPOSE

The authors present the application of the reduced order constrained optimization (ROCO) method, previously successfully applied to the prostate and lung sites, to the head-and-neck (H&N) site, demonstrating that it can quickly and automatically generate clinically competitive IMRT plans. We provide guidelines for applying ROCO to larynx, oropharynx, and nasopharynx cases, and report the results of a live experiment that demonstrates how an expert planner can save several hours of trial-and-error interaction using the proposed approach.

METHODS

The ROCO method used for H&N IMRT planning consists of three major steps. First, the intensity space of treatment plans is sampled by solving a series of unconstrained optimization problems with a parameter range based on previously treated patient data. Second, the dominant modes in the intensity space are estimated by dimensionality reduction using principal component analysis (PCA). Third, a constrained optimization problem over this basis is quickly solved to find an IMRT plan that meets organ-at-risk (OAR) and target coverage constraints. The quality of the plan is assessed using evaluation tools within Memorial Sloan-Kettering Cancer Center (MSKCC)'s treatment planning system (TPS).

RESULTS

The authors generated ten H&N IMRT plans for previously treated patients using the ROCO method and processed them for deliverability by a dynamic multileaf collimator (DMLC). The authors quantitatively compared the ROCO plans to the previously achieved clinical plans using the TPS tools used at MSKCC, including DVH and isodose contour analysis, and concluded that the ROCO plans would be clinically acceptable. In our current implementation, ROCO H&N plans can be generated using about 1.6 h of offline computation followed by 5-15 min of semiautomatic planning time. Additionally, the authors conducted a live session for a plan designated by MSKCC performed together with an expert H&N planner. A technical assistant set up the first two steps, which were performed without further human interaction, and then collaborated in a virtual meeting with the expert planner to perform the third (constrained optimization) step. The expert planner performed in-depth analysis of the resulting ROCO plan and deemed it to be clinically acceptable and in some aspects superior to the clinical plan. This entire process took 135 min including two constrained optimization runs, in comparison to the estimated 4 h that would have been required using traditional clinical planning tools.

CONCLUSIONS

The H&N site is very challenging for IMRT planning, due to several levels of prescription and a large, variable number (6-20) of OARs that depend on the location of the tumor. ROCO for H&N shows promise in generating clinically acceptable plans both more quickly and with substantially less human interaction.

Confronting deep uncertainties in risk analysis

How can risk analysts help to improve policy and decision making when the correct probabilistic relation between alternative acts and their probable consequences is unknown? This practical challenge of risk management with model uncertainty arises in problems from preparing for climate change to managing emerging diseases to operating complex and hazardous facilities safely. We review constructive methods for robust and adaptive risk analysis under deep uncertainty. These methods are not yet as familiar to many risk analysts as older statistical and model-based methods, such as the paradigm of identifying a single "best-fitting" model and performing sensitivity analyses for its conclusions. They provide genuine breakthroughs for improving predictions and decisions when the correct model is highly uncertain. We demonstrate their potential by summarizing a variety of practical risk management applications.