Simultaneous navigation of multiple Pareto surfaces, with an application to multicriteria IMRT planning with multiple beam angle configurations

Optimizing volumetric modulated arc therapy prostate planning using an automated Fine-Tuning process through dynamic adjustment of optimization parameters

In radiotherapy treatment planning, optimization is essential for achieving the most favorable plan by adjusting optimization criteria. This study introduced an innovative approach to automatically fine-tune optimization parameters for volumetric modulated arc therapy prostate planning, ensuring all constraints were met. A knowledge-based planning model was invoked, and the fine-tuning process was applied through an in-house developed script. Among 25 prostate plans, this fine-tuning increased the number of plans meeting all constraints from 10/25 to 22/25, with a reduction in mean monitor units per gray without increasing plan's complexity. This automation improved efficiency by saving time and resources in treatment planning.

TrDosePred: A deep learning dose prediction algorithm based on transformers for head and neck cancer radiotherapy

BACKGROUND

Intensity-Modulated Radiation Therapy (IMRT) has been the standard of care for many types of tumors. However, treatment planning for IMRT is a time-consuming and labor-intensive process.

PURPOSE

To alleviate this tedious planning process, a novel deep learning based dose prediction algorithm (TrDosePred) was developed for head and neck cancers.

METHODS

The proposed TrDosePred, which generated the dose distribution from a contoured CT image, was a U-shape network constructed with a convolutional patch embedding and several local self-attention based transformers. Data augmentation and ensemble approach were used for further improvement. It was trained based on the dataset from Open Knowledge-Based Planning Challenge (OpenKBP). The performance of TrDosePred was evaluated with two mean absolute error (MAE) based scores utilized by OpenKBP challenge (i.e., Dose score and DVH score) and compared to the top three approaches of the challenge. In addition, several state-of-the-art methods were implemented and compared to TrDosePred.

RESULTS

The TrDosePred ensemble achieved the dose score of 2.426 Gy and the DVH score of 1.592 Gy on the test dataset, ranking at 3rd and 9th respectively in the leaderboard on CodaLab as of writing. In terms of DVH metrics, on average, the relative MAE against the clinical plans was 2.25% for targets and 2.17% for organs at risk.

CONCLUSIONS

A transformer-based framework TrDosePred was developed for dose prediction. The results showed a comparable or superior performance as compared to the previous state-of-the-art approaches, demonstrating the potential of transformer to boost the treatment planning procedures.

A reinforcement learning application of a guided Monte Carlo Tree Search algorithm for beam orientation selection in radiation therapy

Current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature because of the size of the combinatorial problem, which leads to suboptimal solutions. We propose a reinforcement learning strategy using a Monte Carlo Tree Search (MCTS) that can find a better beam orientation set in less time than CG. We utilize a reinforcement learning structure involving a supervised learning network to guide the MCTS and to explore the decision space of beam orientation selection problems. We previously trained a deep neural network (DNN) that takes in the patient anatomy, organ weights, and current beams, then approximates beam fitness values to indicate the next best beam to add. Here, we use this DNN to probabilistically guide the traversal of the branches of the Monte Carlo decision tree to add a new beam to the plan. To assess the feasibility of the algorithm, we used a test set of 13 prostate cancer patients, distinct from the 57 patients originally used to train and validate the DNN, to solve five-beam plans. To show the strength of the guided MCTS (GTS) compared to other search methods, we also provided the performances of Guided Search, Uniform Tree Search and Random Search algorithms. On average, GTS outperformed all the other methods. It found a better solution than CG in 237 s on average, compared to 360 s for CG, and outperformed all other methods in finding a solution with a lower objective function value in less than 1000 s. Using our GTS method, we could maintain planning target volume (PTV) coverage within 1% error similar to CG, while reducing the organ-at-risk mean dose for body, rectum, left and right femoral heads; the mean dose to bladder was 1% higher with GTS than with CG.

Multiobjective, Multidelivery Optimization for Radiation Therapy Treatment Planning

Purpose

To introduce multiobjective, multidelivery optimization (MODO), which generates alternative patient-specific plans emphasizing dosimetric trade-offs and conformance to quasi-constrained (QC) conditions for multiple delivery techniques.

Methods and Materials

For M delivery techniques and N organs at risk (OARs), MODO generates M (N + 1) alternative treatment plans per patient. For 30 locally advanced lung cancer cases, the algorithm was investigated based on dosimetric trade-offs to 4 OARs: each lung, heart, and esophagus (N = 4) and 4 delivery techniques (4-field coplanar intensity modulated radiation therapy [IMRT], 9-field coplanar IMRT, 27-field noncoplanar IMRT, and noncoplanar arc IMRT) and conformance to QC conditions, including dose to 95% (D95) of the planning target volume (PTV), maximum dose (Dmax) to PTV (PTV-Dmax), and spinal cord Dmax. The MODO plan set was evaluated for conformance to QC conditions while simultaneously revealing dosimetric trade-offs. Statistically significant dosimetric trade-offs were defined such that the coefficient of determination was >0.8 with dosimetric indices that varied by at least 5 Gy.

Results

Plans varied mean dose by >5 Gy to ipsilateral lung for 24 of 30 patients, contralateral lung for 29 of 30 patients, esophagus for 29 of 30 patients, and heart for 19 of 30 patients. In the 600 plans, average PTV-D95 = 67.6 ± 2.1 Gy, PTV-Dmax = 79.8 ± 5.2 Gy, and spinal cord Dmax among all plans was 51.4 Gy. Statistically significant dosimetric trade-offs reducing OAR mean dose by >5 Gy were evident in 19 of 30 patients, including multiple OAR trade-offs of at least 5 Gy in 7 of 30 cases. The most common statistically significant trade-off was increasing PTV-Dmax to reduce dose to OARs (15 of 30). The average 4-field plan reduced total lung V20 by 10.4% ± 8.3% compared with 9-field plans, 7.7% ± 7.9% compared with 27-field noncoplanar plans, and 11.7% ± 10.3% compared with 2-arc noncoplanar plans, with corresponding increases in PTV-Dmax of 5.3 ± 5.9 Gy, 4.6 ± 5.6 Gy, and 9.3 ± 7.3 Gy.

Conclusions

The proposed optimization method produces clinically relevant treatment plans that meet QC conditions and demonstrate variations in OAR doses.

A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity-modulated radiation therapy

PURPOSE

Beam orientation selection, whether manual or protocol-based, is the current clinical standard in radiation therapy treatment planning, but it is tedious and can yield suboptimal results. Many algorithms have been designed to optimize beam orientation selection because of its impact on treatment plan quality, but these algorithms suffer from slow calculation of the dose influence matrices of all candidate beams. We propose a fast beam orientation selection method, based on deep learning neural networks (DNN), capable of developing a plan comparable to those developed by the state-of-the-art column generation (CG) method. Our model's novelty lies in its supervised learning structure (using CG to teach the network), DNN architecture, and ability to learn from anatomical features to predict dosimetrically suitable beam orientations without using dosimetric information from the candidate beams. This may save hours of computation.

METHODS

A supervised DNN is trained to mimic the CG algorithm, which iteratively chooses beam orientations one-by-one by calculating beam fitness values based on Karush-Kush-Tucker optimality conditions at each iteration. The DNN learns to predict these values. The dataset contains 70 prostate cancer patients - 50 training, 7 validation, and 13 test patients - to develop and test the model. Each patient's data contains 6 contours: PTV, body, bladder, rectum, and left and right femoral heads. Column generation was implemented with a GPU-based Chambolle-Pock algorithm, a first-order primal-dual proximal-class algorithm, to create 6270 plans. The DNN trained over 400 epochs, each with 2500 steps and a batch size of 1, using the Adam optimizer at a learning rate of 1 × 10-5 and a sixfold cross-validation technique.

RESULTS

The average and standard deviation of training, validation, and testing loss functions among the six folds were 0.62 ± 0.09%, 1.04 ± 0.06%, and 1.44 ± 0.11%, respectively. Using CG and supervised DNN, we generated two sets of plans for each scenario in the test set. The proposed method took at most 1.5 s to select a set of five beam orientations and 300 s to calculate the dose influence matrices for 5 beams and finally 20 s to solve the fluence map optimization (FMO). However, CG needed around 15 h to calculate the dose influence matrices of all beams and at least 400 s to solve both the beam orientation selection and FMO problems. The differences in the dose coverage of PTV between plans generated by CG and by DNN were 0.2%. The average dose differences received by organs at risk were between 1 and 6 percent: Bladder had the smallest average difference in dose received (0.956 ± 1.184%), then Rectum (2.44 ± 2.11%), Left Femoral Head (6.03 ± 5.86%), and Right Femoral Head (5.885 ± 5.515%). The dose received by Body had an average difference of 0.10 ± 0.1% between the generated treatment plans.

CONCLUSIONS

We developed a fast beam orientation selection method based on a DNN that selects beam orientations in seconds and is therefore suitable for clinical routines. In the training phase of the proposed method, the model learns the suitable beam orientations based on patients' anatomical features and omits time intensive calculations of dose influence matrices for all possible candidate beams. Solving the FMO to get the final treatment plan requires calculating dose influence matrices only for the selected beams.

Automatic VMAT planning for post-operative prostate cancer cases using particle swarm optimization: A proof of concept study

OBJECTIVE

To investigate the potential of Particle Swarm Optimization (PSO) for fully automatic VMAT radiotherapy (RT) treatment planning.

MATERIAL AND METHODS

In PSO a solution space of planning constraints is searched for the best possible RT plan in an iterative, statistical method, optimizing a population of candidate solutions. To identify the best candidate solution and for final evaluation a plan quality score (PQS), based on dose volume histogram (DVH) parameters, was introduced. Automatic PSO-based RT planning was used for N = 10 postoperative prostate cancer cases, retrospectively taken from our clinical database, with a prescribed dose of EUD = 66 Gy in addition to two constraints for rectum and one for bladder. Resulting PSO-based plans were compared dosimetrically to manually generated VMAT plans.

RESULTS

PSO successfully proposed treatment plans comparable to manually optimized ones in 9/10 cases. The median (range) PTV EUD was 65.4 Gy (64.7-66.0) for manual and 65.3 Gy (62.5-65.5) for PSO plans, respectively. However PSO plans achieved significantly lower doses in rectum D_2% 67.0 Gy (66.5-67.5) vs. 66.1 Gy (64.7-66.5, p = 0.016). All other evaluated parameters (PTV D_98% and D_2%, rectum V_40Gy and V_60Gy, bladder D_2% and V_60Gy) were comparable in both plans. Manual plans had lower PQS compared to PSO plans with -0.82 (-16.43-1.08) vs. 0.91 (-5.98-6.25).

CONCLUSION

PSO allows for fully automatic generation of VMAT plans with plan quality comparable to manually optimized plans. However, before clinical implementation further research is needed concerning further adaptation of PSO-specific parameters and the refinement of the PQS.

Automatically configuring the reference point method for automated multi-objective treatment planning

Automated treatment planning algorithms have demonstrated capability in generating consistent and high-quality treatment plans. Their configuration (i.e. determining the algorithm's parameters), however, can be a labour-intensive and time-consuming trial-and-error procedure. Previously, we introduced the reference point method (RPM) for fast automated multi-objective treatment planning. The RPM generates a single Pareto optimal plan for each patient. When the RPM is configured appropriately, this plan has clinically favourable trade-offs between all plan objectives. This paper proposes a new procedure to automatically generate a single configuration of the RPM per tumour site. The procedure was tested for prostate cancer. Planning CT scans of 287 previously treated patients were included in a database, together with corresponding Pareto optimal plans generated using our clinically applied two-phase [Formula: see text]-constraint method (part of Erasmus-iCycle) for automated multi-objective treatment planning. The procedure developed acquires plan characteristics observed in a training set. Based on these, an RPM configuration is automatically generated according to user preferences which specify acceptable differences between training set plans and corresponding RPM generated plans. For example, compared to the training set plans, the RPM generated plans need to have similar PTV coverage, and preferably reduced high rectum dose while slight deteriorations in other objectives are allowed. Training sets of different sizes were tested, and the quality of the resulting RPM configurations was evaluated on the test set (subset of the database not used for training). Using the new procedure, an RPM configuration was generated for each training set. The quality of RPM generated plans was similar or slightly better than that of the corresponding test set plans. The proposed automated configuration procedure greatly reduces the manual configuration workload, and thereby improves the efficiency and effectiveness of an automated clinical treatment planning workflow.

Automation in intensity modulated radiotherapy treatment planning-a review of recent innovations

Radiotherapy treatment planning of complex radiotherapy techniques, such as intensity modulated radiotherapy and volumetric modulated arc therapy, is a resource-intensive process requiring a high level of treatment planner intervention to ensure high plan quality. This can lead to variability in the quality of treatment plans and the efficiency in which plans are produced, depending on the skills and experience of the operator and available planning time. Within the last few years, there has been significant progress in the research and development of intensity modulated radiotherapy treatment planning approaches with automation support, with most commercial manufacturers now offering some form of solution. There is a rapidly growing number of research articles published in the scientific literature on the topic. This paper critically reviews the body of publications up to April 2018. The review describes the different types of automation algorithms, including the advantages and current limitations. Also included is a discussion on the potential issues with routine clinical implementation of such software, and highlights areas for future research.

Automated volumetric modulated arc therapy planning for whole pelvic prostate radiotherapy

Background

For several tumor entities, automated treatment planning has improved plan quality and planning efficiency, and may enable adaptive treatment approaches. Whole-pelvic prostate radiotherapy (WPRT) involves large concave target volumes, which present a challenge for volumetric arc therapy (VMAT) optimization. This study evaluates automated VMAT planning for WPRT-VMAT and compares the results with manual expert planning.

Methods

A system for fully automated multi-criterial plan generation was configured for each step of sequential-boost WPRT-VMAT, with final “autoVMAT” plans being automatically calculated by the Monaco treatment planning system (TPS; Elekta AB, Stockholm, Sweden). Configuration was based on manually generated VMAT plans (manualVMAT) of 5 test patients, the planning protocol, and discussions with the treating physician on wishes for plan improvements. AutoVMAT plans were then generated for another 30 evaluation patients and compared to manualVMAT plans. For all 35 patients, manualVMAT plans were optimized by expert planners using the Monaco TPS.

Results

AutoVMAT plans exhibited strongly improved organ sparing and higher conformity compared to manualVMAT. On average, mean doses (D_mean) of bladder and rectum were reduced by 10.7 and 4.5 Gy, respectively, by autoVMAT. Prostate target coverage (V_95%) was slightly higher (+0.6%) with manualVMAT. In a blinded scoring session, the radiation oncologist preferred autoVMAT plans to manualVMAT plans for 27/30 patients. All treatment plans were considered clinically acceptable. The workload per patient was reduced by > 70 min.

Conclusion

Automated VMAT planning for complex WPRT dose distributions is feasible and creates treatment plans that are generally dosimetrically superior to manually optimized plans.

Electronic supplementary material

The online version of this article (10.1007/s00066-017-1246-2) contains supplementary material, which is available to authorized users.

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 treatment planning of spinal metastases - A comparison to manual planning of Volumetric Modulated Arc Therapy for conventionally fractionated irradiation

Background

Planning for Volumetric Modulated Arc Therapy (VMAT) may be time consuming and its use is limited by available staff resources. Automated multicriterial treatment planning can eliminate this bottleneck. We compared automatically created (auto) VMAT plans generated by Erasmus-iCycle to manually created VMAT plans for treatment of spinal metastases.

Methods

Forty-two targets in 32 patients were analyzed. Lungs and kidneys were defined as organs at risk (OARs). Twenty-two patients received radiotherapy on kidney levels, 17 on lung levels, and 3 on both levels.

Results

All Erasmus-iCycle plans were clinically acceptable. When compared to manual plans, planning target volume (PTV) coverage of auto plans was significantly better. The Homogeneity Index did not differ significantly between the groups. Mean dose to OARs was lower in auto plans concerning both kidneys and the left lung. One hotspot (>110% of D_50%) occurred in the spinal cord of one auto plan (33.2 Gy, D_50%: 30 Gy). Treatment time was 7% longer in auto plans.

Conclusions

Erasmus-iCycle plans showed better target coverage and sparing of OARs at the expense of minimally longer treatment times (for which no constraint was set).

Electronic supplementary material

The online version of this article (doi:10.1186/s13014-017-0767-2) contains supplementary material, which is available to authorized users.

A multicriteria framework with voxel-dependent parameters for radiotherapy treatment plan optimization

PURPOSE

To establish a new mathematical framework for radiotherapy treatment optimization with voxel-dependent optimization parameters.

METHODS

In the treatment plan optimization problem for radiotherapy, a clinically acceptable plan is usually generated by an optimization process with weighting factors or reference doses adjusted for a set of the objective functions associated to the organs. Recent discoveries indicate that adjusting parameters associated with each voxel may lead to better plan quality. However, it is still unclear regarding the mathematical reasons behind it. Furthermore, questions about the objective function selection and parameter adjustment to assure Pareto optimality as well as the relationship between the optimal solutions obtained from the organ-based and voxel-based models remain unanswered. To answer these questions, the authors establish in this work a new mathematical framework equipped with two theorems.

RESULTS

The new framework clarifies the different consequences of adjusting organ-dependent and voxel-dependent parameters for the treatment plan optimization of radiation therapy, as well as the impact of using different objective functions on plan qualities and Pareto surfaces. The main discoveries are threefold: (1) While in the organ-based model the selection of the objective function has an impact on the quality of the optimized plans, this is no longer an issue for the voxel-based model since the Pareto surface is independent of the objective function selection and the entire Pareto surface could be generated as long as the objective function satisfies certain mathematical conditions; (2) All Pareto solutions generated by the organ-based model with different objective functions are parts of a unique Pareto surface generated by the voxel-based model with any appropriate objective function; (3) A much larger Pareto surface is explored by adjusting voxel-dependent parameters than by adjusting organ-dependent parameters, possibly allowing for the generation of plans with better trade-offs among different clinical objectives.

CONCLUSIONS

The authors have developed a mathematical framework for radiotherapy treatment optimization using voxel-based parameters. The authors can improve the plan quality by adjusting voxel-based weighting factors and exploring the unique and large Pareto surface which include all the Pareto surfaces that can be generated by organ-based model using different objective functions.

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.

Deliverable navigation for multicriteria step and shoot IMRT treatment planning

We consider Pareto surface based multi-criteria optimization for step and shoot IMRT planning. By analyzing two navigation algorithms, we show both theoretically and in practice that the number of plans needed to form convex combinations of plans during navigation can be kept small (much less than the theoretical maximum number needed in general, which is equal to the number of objectives for on-surface Pareto navigation). Therefore a workable approach for directly deliverable navigation in this setting is to segment the underlying Pareto surface plans and then enforce the mild restriction that only a small number of these plans are active at any time during plan navigation, thus limiting the total number of segments used in the final plan.

Sensitivity analysis for lexicographic ordering in radiation therapy treatment planning

PURPOSE

To introduce a method to efficiently identify and calculate meaningful tradeoffs between criteria in an interactive IMRT treatment planning procedure. The method provides a systematic approach to developing high-quality radiation therapy treatment plans.

METHODS

Treatment planners consider numerous dosimetric criteria of varying importance that, when optimized simultaneously through multicriteria optimization, yield a Pareto frontier which represents the set of Pareto-optimal treatment plans. However, generating and navigating this frontier is a time-consuming, nontrivial process. A lexicographic ordering (LO) approach to IMRT uses a physician's criteria preferences to partition the treatment planning decisions into a multistage treatment planning model. Because the relative importance of criteria optimized in the different stages may not necessarily constitute a strict prioritization, the authors introduce an interactive process, sensitivity analysis in lexicographic ordering (SALO), to allow the treatment planner control over the relative sequential-stage tradeoffs. By allowing this flexibility within a structured process, SALO implicitly restricts attention to and allows exploration of a subset of the Pareto efficient frontier that the physicians have deemed most important.

RESULTS

Improvements to treatment plans over a LO approach were found by implementing the SALO procedure on a brain case and a prostate case. In each stage, a physician assessed the tradeoff between previous stage and current stage criteria. The SALO method provided critical tradeoff information through curves approximating the relationship between criteria, which allowed the physician to determine the most desirable treatment plan.

CONCLUSIONS

The SALO procedure provides treatment planners with a directed, systematic process to treatment plan selection. By following a physician's prioritization, the treatment planner can avoid wasting effort considering clinically inferior treatment plans. The planner is guided by criteria importance, but given the information necessary to accurately adjust the relative importance at each stage. Through these attributes, the SALO procedure delivers an approach well balanced between efficiency and flexibility.

Introducing multiple treatment plan-based comparison to investigate the performance of gantry angle optimisation (GAO) in IMRT for head and neck cancer

BACKGROUND AND PURPOSE

The purpose of this study was to evaluate the performance of gantry angle optimisation (GAO) compared to equidistant beam geometry for two inverse treatment planning systems (TPSs) by utilising the information obtained from a range of treatment plans.

MATERIAL AND METHODS

The comparison was based on treatment plans generated for four different head and neck (H&N) cancer cases using two inverse treatment planning systems (TPSs); Varian Eclipse™ representing dynamic MLC intensity modulated radiotherapy (IMRT) and Oncentra® Masterplan representing segmented MLC-based IMRT. The patient cases were selected on the criterion of representing different degrees of overlap between the planning target volume (PTV) and the investigated organ at risk, the ipsilateral parotid gland. For each case, a number of 'Pareto optimal' plans were generated in order to investigate the trade-off between the under-dosage to the PTV (V(PTV,D < 95%)) or the decrease in dose homogeneity (D(5)-D(95)) to the PTV as a function of the mean absorbed dose to the ipsilateral parotid gland (<D>(parotid gland)).

RESULTS

For the Eclipse system, GAO had a clear advantage for the cases with smallest overlap (Cases 1 and 2). The set of data points, representing the underlying trade-offs, generated with and without using GAO were, however, not as clearly separated for the cases with larger overlap (Cases 3 and 4). With the OMP system, the difference was less pronounced for all cases. The Eclipse GAO displays the most favourable trade-off for all H&N cases.

CONCLUSIONS

We have found differences in the effectiveness of GAO as compared to equidistant beam geometry, in terms of handling conflicting trade-offs for two commercial inverse TPSs. A comparison, based on a range of treatment plans, as developed in this study, is likely to improve the understanding of conflicting trade-offs and might apply to other thorough comparison techniques.

iCycle: Integrated, multicriterial beam angle, and profile optimization for generation of coplanar and noncoplanar IMRT plans

PURPOSE

To introduce iCycle, a novel algorithm for integrated, multicriterial optimization of beam angles, and intensity modulated radiotherapy (IMRT) profiles.

METHODS

A multicriterial plan optimization with iCycle is based on a prescription called wish-list, containing hard constraints and objectives with ascribed priorities. Priorities are ordinal parameters used for relative importance ranking of the objectives. The higher an objective priority is, the higher the probability that the corresponding objective will be met. Beam directions are selected from an input set of candidate directions. Input sets can be restricted, e.g., to allow only generation of coplanar plans, or to avoid collisions between patient/couch and the gantry in a noncoplanar setup. Obtaining clinically feasible calculation times was an important design criterium for development of iCycle. This could be realized by sequentially adding beams to the treatment plan in an iterative procedure. Each iteration loop starts with selection of the optimal direction to be added. Then, a Pareto-optimal IMRT plan is generated for the (fixed) beam setup that includes all so far selected directions, using a previously published algorithm for multicriterial optimization of fluence profiles for a fixed beam arrangement Breedveld et al. [Phys. Med. Biol. 54, 7199-7209 (2009)]. To select the next direction, each not yet selected candidate direction is temporarily added to the plan and an optimization problem, derived from the Lagrangian obtained from the just performed optimization for establishing the Pareto-optimal plan, is solved. For each patient, a single one-beam, two-beam, three-beam, etc. Pareto-optimal plan is generated until addition of beams does no longer result in significant plan quality improvement. Plan generation with iCycle is fully automated.

RESULTS

Performance and characteristics of iCycle are demonstrated by generating plans for a maxillary sinus case, a cervical cancer patient, and a liver patient treated with SBRT. Plans generated with beam angle optimization did better meet the clinical goals than equiangular or manually selected configurations. For the maxillary sinus and liver cases, significant improvements for noncoplanar setups were seen. The cervix case showed that also in IMRT with coplanar setups, beam angle optimization with iCycle may improve plan quality. Computation times for coplanar plans were around 1-2 h and for noncoplanar plans 4-7 h, depending on the number of beams and the complexity of the site.

CONCLUSIONS

Integrated beam angle and profile optimization with iCycle may result in significant improvements in treatment plan quality. Due to automation, the plan generation workload is minimal. Clinical application has started.

PARETO: A novel evolutionary optimization approach to multiobjective IMRT planning

PURPOSE

In radiation therapy treatment planning, the clinical objectives of uniform high dose to the planning target volume (PTV) and low dose to the organs-at-risk (OARs) are invariably in conflict, often requiring compromises to be made between them when selecting the best treatment plan for a particular patient. In this work, the authors introduce Pareto-Aware Radiotherapy Evolutionary Treatment Optimization (pareto), a multiobjective optimization tool to solve for beam angles and fluence patterns in intensity-modulated radiation therapy (IMRT) treatment planning.

METHODS

pareto is built around a powerful multiobjective genetic algorithm (GA), which allows us to treat the problem of IMRT treatment plan optimization as a combined monolithic problem, where all beam fluence and angle parameters are treated equally during the optimization. We have employed a simple parameterized beam fluence representation with a realistic dose calculation approach, incorporating patient scatter effects, to demonstrate feasibility of the proposed approach on two phantoms. The first phantom is a simple cylindrical phantom containing a target surrounded by three OARs, while the second phantom is more complex and represents a paraspinal patient.

RESULTS

pareto results in a large database of Pareto nondominated solutions that represent the necessary trade-offs between objectives. The solution quality was examined for several PTV and OAR fitness functions. The combination of a conformity-based PTV fitness function and a dose-volume histogram (DVH) or equivalent uniform dose (EUD) -based fitness function for the OAR produced relatively uniform and conformal PTV doses, with well-spaced beams. A penalty function added to the fitness functions eliminates hotspots. Comparison of resulting DVHs to those from treatment plans developed with a single-objective fluence optimizer (from a commercial treatment planning system) showed good correlation. Results also indicated that pareto shows promise in optimizing the number of beams.

CONCLUSIONS

This initial evaluation of the evolutionary optimization software tool pareto for IMRT treatment planning demonstrates feasibility and provides motivation for continued development. Advantages of this approach over current commercial methods for treatment planning are many, including: (1) fully automated optimization that avoids human controlled iterative optimization and potentially improves overall process efficiency, (2) formulation of the problem as a true multiobjective one, which provides an optimized set of Pareto nondominated solutions refined over hundreds of generations and compiled from thousands of parameter sets explored during the run, and (3) rapid exploration of the final nondominated set accomplished by a graphical interface used to select the best treatment option for the patient.

Feasibility of identification of gamma knife planning strategies by identification of pareto optimal gamma knife plans

The use of conformity indices to optimize Gamma Knife planning is common, but does not address important tradeoffs between dose to tumor and normal tissue. Pareto analysis has been used for this purpose in other applications, but not for Gamma Knife (GK) planning. The goal of this work is to use computer models to show that Pareto analysis may be feasible for GK planning to identify dosimetric tradeoffs. We define a GK plan A to be Pareto dominant to B if the prescription isodose volume of A covers more tumor but not more normal tissue than B, or if A covers less normal tissue but not less tumor than B. A plan is Pareto optimal if it is not dominated by any other plan. Two different Pareto optimal plans represent different tradeoffs between dose to tumor and normal tissue, because neither plan dominates the other. ‘GK simulator’ software calculated dose distributions for GK plans, and was called repetitively by a genetic algorithm to calculate Pareto dominant plans. Three irregular tumor shapes were tested in 17 trials using various combinations of shots. The mean number of Pareto dominant plans/trial was 59 ± 17 (sd). Different planning strategies were identified by large differences in shot positions, and 70 of the 153 coordinate plots (46%) showed differences of 5mm or more. The Pareto dominant plans dominated other nearby plans. Pareto dominant plans represent different dosimetric tradeoffs and can be systematically calculated using genetic algorithms. Automatic identification of non-intuitive planning strategies may be feasible with these methods.

Improved planning time and plan quality through multicriteria optimization for intensity-modulated radiotherapy

PURPOSE

To test whether multicriteria optimization (MCO) can reduce treatment planning time and improve plan quality in intensity-modulated radiotherapy (IMRT).

METHODS AND MATERIALS

Ten IMRT patients (5 with glioblastoma and 5 with locally advanced pancreatic cancers) were logged during the standard treatment planning procedure currently in use at Massachusetts General Hospital (MGH). Planning durations and other relevant planning information were recorded. In parallel, the patients were planned using an MCO planning system, and similar planning time data were collected. The patients were treated with the standard plan, but each MCO plan was also approved by the physicians. Plans were then blindly reviewed 3 weeks after planning by the treating physician.

RESULTS

In all cases, the treatment planning time was vastly shorter for the MCO planning (average MCO treatment planning time was 12 min; average standard planning time was 135 min). The physician involvement time in the planning process increased from an average of 4.8 min for the standard process to 8.6 min for the MCO process. In all cases, the MCO plan was blindly identified as the superior plan.

CONCLUSIONS

This provides the first concrete evidence that MCO-based planning is superior in terms of both planning efficiency and dose distribution quality compared with the current trial and error-based IMRT planning approach.