Comparison of Combinatorial and Continuous Frameworks for the Beam Angle Optimization Problem in IMRT

Rocha, Humberto; Dias, Joana; Ventura, Tiago; Ferreira, B.; Lopes, Maria do Carmo

doi:10.1007/978-3-319-95165-2_42

Cited by 3 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two main aspects of the proposed multistart approach, after the definition of the initial starting points, are the local procedure considered to explore each of the cubes of the reduced search space, and the definition of each cube as a region of attraction to avoid overlapping of different local search procedures. For the local search procedure, pattern search methods (PSM) as described in Rocha et al [29] are used for their ability to avoid local entrapment. Algorithms 1 and 2 display the PSM algorithm and the multistart algorithm, respectively.…”

Section: Noncoplanar Beam Angle Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

An Optimization Approach for Noncoplanar Intensity-Modulated Arc Therapy Trajectories

Rocha

Dias

Ventura

et al. 2019

Computational Science and Its Applications – ICCSA 2019

Self Cite

View full text Add to dashboard Cite

The latest generation of linear accelerators allows the simultaneous motion of gantry and couch leading to highly noncoplanar arc trajectories. The use of noncoplanar trajectories in arc radiotherapy was recently proposed to combine the benefits of arc treatment plans, such as short treatment times, with the benefits of step-and-shoot noncoplanar intensity-modulated radiation therapy (IMRT) treatment plans, such as improved organ sparing. In this paper, a two-step approach for the optimization of highly noncoplanar arc trajectories is presented and tested using a complex nasopharyngeal tumor case already treated at the Portuguese Institute of Oncology of Coimbra. In the first step, a set of noncoplanar beam directions is calculated resorting to one of the beam angle optimization (BAO) algorithms proposed in our previous works for step-and-shoot IMRT. In the second step, anchored in the points (beam directions) calculated in the first step, the proposed optimization strategy determines iteratively more anchor points that will define the noncoplanar arc trajectory, considering the dosimetric criteria used for the noncoplanar BAO search rather than geometric or time criteria commonly used. For the patient tested, the resulting noncoplanar arc therapy plan has undoubtedly greater overall quality compared to both the coplanar arc therapy plan and the typically used coplanar equispaced step-and-shoot IMRT plan.

show abstract

Section: Noncoplanar Beam Angle Optimizationmentioning

confidence: 99%

“…Algorithms 1 and 2 display the PSM algorithm and the multistart algorithm, respectively. For further details on the parallel implementation of the multistart approach see Rocha et al [29]. Iteration:…”

Section: Noncoplanar Beam Angle Optimizationmentioning

confidence: 99%

An Optimization Approach for Noncoplanar Intensity-Modulated Arc Therapy Trajectories

Rocha

Dias

Ventura

et al. 2019

Computational Science and Its Applications – ICCSA 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…[16][17][18][19][20][21][22][23][24][25][26][27][28] But computing the dose influence matrices and the FMO are both very complex and time intensive operations, 29 taking hours to compute dose influence matrices and minutes to solve the FMO, which ultimately hampers the implementation of BOO in clinical routines. 13,20,24,[30][31][32] Breedveld et al 13 used a "wish list" to prioritize constraints and objective functions related to OARs and the tumor and to iteratively add new beam orientations to the set of currently selected beams. Yarmand et al 31 scored beamlets of candidate beams based on their contributions to irradiating tumors and weighted the average of the total dose received by OARs.…”

Section: Introductionmentioning

confidence: 99%

“…The final objective function in these works is usually a function of the differences between the actual and prescribed dosage received by heathy tissues, organs at risk (OARs), and the PTV. [16][17][18][19][20][21][22][23][24][25][26][27][28] But computing the dose influence matrices and the FMO are both very complex and time intensive operations, 29 taking hours to compute dose influence matrices and minutes to solve the FMO, which ultimately hampers the implementation of BOO in clinical routines. 13,20,24,[30][31][32] Breedveld et al 13 used a "wish list" to prioritize constraints and objective functions related to OARs and the tumor and to iteratively add new beam orientations to the set of currently selected beams.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

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 ...

show abstract

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

Barkousaraie¹,

Bohara²,

Jiang³

et al. 2021

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

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.

show abstract

Comparison of Combinatorial and Continuous Frameworks for the Beam Angle Optimization Problem in IMRT

Cited by 3 publications

References 20 publications

An Optimization Approach for Noncoplanar Intensity-Modulated Arc Therapy Trajectories

An Optimization Approach for Noncoplanar Intensity-Modulated Arc Therapy Trajectories

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

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

Contact Info

Product

Resources

About