Optimization of beam angles for intensity modulated radiation therapy treatment planning using genetic algorithm on a distributed computing platform

A data-driven approach to optimal beam/arc angle selection for liver stereotactic body radiation therapy treatment planning

BACKGROUND

Stereotactic body radiation therapy (SBRT) for liver cancer has shown promising therapeutic effects. Effective treatment relies not only on the precise delivery provided by image-guided radiation therapy (IGRT) but also high dose gradient formed around the treatment volume to spare functional liver tissue, which is highly dependent on the beam/arc angle selection. In this study, we aim to develop a decision support model to learn human planner's beam navigation approach for beam angle/arc angle selection for liver SBRT.

METHODS

A total of 27 liver SBRT/HIGRT patients (10 IMRT, 17 VMAT/DCA) were included in this study. A dosimetric budget index was defined for each beam angle/control point considering dose penetration through the patient body and liver tissue. Optimal beam angle setting (beam angles for IMRT and start/terminal angle for VMAT/DCA) was determined by minimizing the loss function defined as the sum of total dosimetric budget index and beam span penalty function. Leave-one-out validation was exercised on all 27 cases while weighting coefficients in the loss function was tuned in nested cross validation. To compare the efficacy of the model, a model plan was generated using automatically generated beam setting while retaining the original optimization constraints in the clinical plan. Model plan was normalized to the same planning target volume (PTV) V100% as the clinical plans. Dosimetric endpoints including PTV D98%, D2%, liver V20Gy and total MU were compared between two plan groups. Wilcoxon Signed-Rank test was performed with the null hypothesis being that no difference exists between two plan groups.

RESULTS

Beam setting prediction was instantaneous. Mean PTV D98% was 91.3% and 91.3% (P=0.566), while mean PTV D2% was 107.9% and 108.1% (P=0.164) for clinical plan and model plan respectively. Liver V20Gy showed no significant difference (P=0.590) with 23.3% for clinical plan and 23.4% for the model plan. Total MU is comparable (P=0.256) between the clinical plan (avg. 2,389.6) and model plan (avg. 2,319.6).

CONCLUSIONS

The evidence driven beam setting model yielded similar plan quality as hand-crafted clinical plan. It is capable of capturing human's knowledge in beam selection decision making. This model could facilitate decision making for beam angle selection while eliminating lengthy trial-and-error process of adjusting beam setting during liver SBRT treatment planning.

The Applications of Genetic Algorithms in Medicine

A great wealth of information is hidden amid medical research data that in some cases cannot be easily analyzed, if at all, using classical statistical methods. Inspired by nature, metaheuristic algorithms have been developed to offer optimal or near-optimal solutions to complex data analysis and decision-making tasks in a reasonable time. Due to their powerful features, metaheuristic algorithms have frequently been used in other fields of sciences. In medicine, however, the use of these algorithms are not known by physicians who may well benefit by applying them to solve complex medical problems. Therefore, in this paper, we introduce the genetic algorithm and its applications in medicine. The use of the genetic algorithm has promising implications in various medical specialties including radiology, radiotherapy, oncology, pediatrics, cardiology, endocrinology, surgery, obstetrics and gynecology, pulmonology, infectious diseases, orthopedics, rehabilitation medicine, neurology, pharmacotherapy, and health care management. This review introduces the applications of the genetic algorithm in disease screening, diagnosis, treatment planning, pharmacovigilance, prognosis, and health care management, and enables physicians to envision possible applications of this metaheuristic method in their medical career.].

Automatic learning-based beam angle selection for thoracic IMRT

PURPOSE

The treatment of thoracic cancer using external beam radiation requires an optimal selection of the radiation beam directions to ensure effective coverage of the target volume and to avoid unnecessary treatment of normal healthy tissues. Intensity modulated radiation therapy (IMRT) planning is a lengthy process, which requires the planner to iterate between choosing beam angles, specifying dose-volume objectives and executing IMRT optimization. In thorax treatment planning, where there are no class solutions for beam placement, beam angle selection is performed manually, based on the planner's clinical experience. The purpose of this work is to propose and study a computationally efficient framework that utilizes machine learning to automatically select treatment beam angles. Such a framework may be helpful for reducing the overall planning workload.

METHODS

The authors introduce an automated beam selection method, based on learning the relationships between beam angles and anatomical features. Using a large set of clinically approved IMRT plans, a random forest regression algorithm is trained to map a multitude of anatomical features into an individual beam score. An optimization scheme is then built to select and adjust the beam angles, considering the learned interbeam dependencies. The validity and quality of the automatically selected beams evaluated using the manually selected beams from the corresponding clinical plans as the ground truth.

RESULTS

The analysis included 149 clinically approved thoracic IMRT plans. For a randomly selected test subset of 27 plans, IMRT plans were generated using automatically selected beams and compared to the clinical plans. The comparison of the predicted and the clinical beam angles demonstrated a good average correspondence between the two (angular distance 16.8° ± 10°, correlation 0.75 ± 0.2). The dose distributions of the semiautomatic and clinical plans were equivalent in terms of primary target volume coverage and organ at risk sparing and were superior over plans produced with fixed sets of common beam angles. The great majority of the automatic plans (93%) were approved as clinically acceptable by three radiation therapy specialists.

CONCLUSIONS

The results demonstrated the feasibility of utilizing a learning-based approach for automatic selection of beam angles in thoracic IMRT planning. The proposed method may assist in reducing the manual planning workload, while sustaining plan quality.

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.

Uncertainty incorporated beam angle optimization for IMPT treatment planning

PURPOSE

Beam angle optimization (BAO) by far remains an important and challenging problem in external beam radiation therapy treatment planning. Conventional BAO algorithms discussed in previous studies all focused on photon-based therapies. Impact of BAO on proton therapy is important while proton therapy increasingly receives great interests. This study focuses on potential benefits of BAO on intensity-modulated proton therapy (IMPT) that recently began available to clinical cancer treatment.

METHODS

The authors have developed a novel uncertainty incorporated BAO algorithm for IMPT treatment planning in that IMPT plan quality is highly sensitive to uncertainties such as proton range and setup errors. A linear programming was used to optimize robust intensity maps to scenario-based uncertainties for an incident beam angle configuration. Unlike conventional intensity-modulated radiation therapy with photons (IMXT), the search space for IMPT treatment beam angles may be relatively small but optimizing an IMPT plan may require higher computational costs due to larger data size. Therefore, a deterministic local neighborhood search algorithm that only needs a very limited number of plan objective evaluations was used to optimize beam angles in IMPT treatment planning.

RESULTS

Three prostate cancer cases and two skull base chordoma cases were studied to demonstrate the dosimetric advantages and robustness of optimized beam angles from the proposed BAO algorithm. Two- to four-beam plans were optimized for prostate cases, and two- and three-beam plans were optimized for skull base cases. By comparing plans with conventional two parallel-opposed angles, all plans with optimized angles consistently improved sparing at organs at risks, i.e., rectum and femoral heads for prostate, brainstem for skull base, in either nominal dose distribution or uncertainty-based dose distributions. The efficiency of the BAO algorithm was demonstrated by comparing it with alternative methods including simulated annealing and genetic algorithm. The numbers of IMPT plan objective evaluations required were reduced by up to a factor of 5 while the same optimal angle plans were converged in selected comparisons.

CONCLUSIONS

Uncertainty incorporated BAO may introduce pronounced improvement of IMPT plan quality including dosimetric benefits and robustness over uncertainties, based on the five clinical studies in this paper. In addition, local search algorithms may be more efficient in finding optimal beam angles than global optimization approaches for IMPT BAO.

Characterizing the combinatorial beam angle selection problem

The beam angle selection (BAS) problem in intensity-modulated radiation therapy is often interpreted as a combinatorial optimization problem, i.e. finding the best combination of η beams in a discrete set of candidate beams. It is well established that the combinatorial BAS problem may be solved efficiently with metaheuristics such as simulated annealing or genetic algorithms. However, the underlying parameters of the optimization process, such as the inclusion of non-coplanar candidate beams, the angular resolution in the space of candidate beams, and the number of evaluated beam ensembles as well as the relative performance of different metaheuristics have not yet been systematically investigated. We study these open questions in a meta-analysis of four strategies for combinatorial optimization in order to provide a reference for future research related to the BAS problem in intensity-modulated radiation therapy treatment planning. We introduce a high-performance inverse planning engine for BAS. It performs a full fluence optimization for ≈3600 treatment plans per hour while handling up to 50 GB of dose influence data (≈1400 candidate beams). For three head and neck patients, we compare the relative performance of a genetic, a cross-entropy, a simulated annealing and a naive iterative algorithm. The selection of ensembles with 5, 7, 9 and 11 beams considering either only coplanar or all feasible candidate beams is studied for an angular resolution of 5°, 10°, 15° and 20° in the space of candidate beams. The impact of different convergence criteria is investigated in comparison to a fixed termination after the evaluation of 10 000 beam ensembles. In total, our simulations comprise a full fluence optimization for about 3000 000 treatment plans. All four combinatorial BAS strategies yield significant improvements of the objective function value and of the corresponding dose distributions compared to standard beam configurations with equi-spaced coplanar beams. The genetic and the cross-entropy algorithms showed faster convergence in the very beginning of the optimization but the simulated annealing algorithm eventually arrived at almost the same objective function values. These three strategies typically yield clinically equivalent treatment plans. The iterative algorithm showed the worst convergence properties. The choice of the termination criterion had a stronger influence on the performance of the simulated annealing algorithm than on the performance of the genetic and the cross-entropy algorithms. We advocate to terminate the optimization process after the evaluation of 1000 beam combinations without objective function decrease. For our simulations, this resulted in an average deviation of the objective function from the reference value after 10 000 evaluated beam ensembles of 0.5% for all metaheuristics. On average, there was only a minor improvement when increasing the angular resolution in the space of candidate beam angles from 20° to 5°. However, we observed significant improvements when considering non-coplanar candidate beams for challenging head and neck cases.

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.

A self-adaptive case-based reasoning system for dose planning in prostate cancer radiotherapy

PURPOSE

Prostate cancer is the most common cancer in the male population. Radiotherapy is often used in the treatment for prostate cancer. In radiotherapy treatment, the oncologist makes a trade-off between the risk and benefit of the radiation, i.e., the task is to deliver a high dose to the prostate cancer cells and minimize side effects of the treatment. The aim of our research is to develop a software system that will assist the oncologist in planning new treatments.

METHODS

A nonlinear case-based reasoning system is developed to capture the expertise and experience of oncologists in treating previous patients. Importance (weights) of different clinical parameters in the dose planning is determined by the oncologist based on their past experience, and is highly subjective. The weights are usually fixed in the system. In this research, the weights are updated automatically each time after generating a treatment plan for a new patient using a group based simulated annealing approach.

RESULTS

The developed approach is analyzed on the real data set collected from the Nottingham University Hospitals NHS Trust, City Hospital Campus, UK. Extensive experiments show that the dose plan suggested by the proposed method is coherent with the dose plan prescribed by an experienced oncologist or even better.

CONCLUSIONS

The developed case-based reasoning system enables the use of knowledge and experience gained by the oncologist in treating new patients. This system may play a vital role to assist the oncologist in making a better decision in less computational time; it utilizes the success rate of the previously treated patients and it can also be used in teaching and training processes.

An algorithm for fast beam angle selection in intensity modulated radiotherapy

PURPOSE

This article aims to introduce a novel algorithm for fast beam angle selection in intensity modulated radiotherapy (IMRT).

METHODS

The algorithm models the optimization problem as a beam angle ranking problem and chooses suitable beam angles according to their rank. A new parameter called "beam intensity profile perturbation score (BIPPS)" is used for ranking the beam angles. The BIPPS-based beam angle ranking implicitly accounts for the dose-volume effects of the involved structures. A simulated phantom case with obvious optimal beam angles is used to verify the validity of the presented technique. In addition, the efficiency of the algorithm was examined in three clinical cases (prostate, pancreas, and head and neck) in terms of DVH and dose distribution. In all cases, the judgment of the algorithm's efficiency was based on the comparison between plans with equidistant beams (equal-angle-plan) and plans with beams obtained using the algorithm (suitable-angle-plan).

RESULTS

It is observed from the study that the beam angle ranking function over BIPPS instantly picks up a suitable set of beam angles for a specific case. It takes only about 15 min for choosing the suitable beam angles even for the most complicated cases. The DVHs and dose distributions confirm that the proposed algorithm can efficiently reduce the mean or maximum dose to OARs, while guaranteeing the target coverage and dose uniformity. On the average, about 17% reduction in the mean dose to critical organs, such as rectum, bladder, kidneys and parotids, is observed. Also, about 12% (averaged) reduction in the maximum dose to critical organs (spinal cord) is observed in the clinical cases presented in this study.

CONCLUSIONS

This study demonstrates that the algorithm can be effectively applied to IMRT scenarios to get fast and case specific beam angle configurations.