Optimization of X-ray Treatment Planning by Computer Judgement

Hope, C S; Laurie, Jean; Orr, J. S.; Halnan, K.E.

doi:10.1088/0031-9155/12/4/310

Cited by 57 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During each phase of the evolution of computer technology, treatment plans could be generated faster and more accurately, with improved image and graphic display capabilities. While automated optimization of treatment techniques has been under investigation since the 1960's [55,56], it is only in recent years that inverse treatment planning capabilities are actually being used in clinical practice with faster computers (see chapters 12 and 15).…”

Section: Historical Perspectivementioning

confidence: 99%

The Modern Technology of Radiation Oncology: A Compendium for Medical Physicists and Radiation Oncologists

2000

View full text Add to dashboard Cite

A sincere thank you: To Tomas Kron for seeding the concept of this book. To Jerry Battista for providing unending support, for being an excellent "sounding board," and for reviewing a number of my chapters. To the authors and co-authors of the chapters of this book. Their contributions have given this book the quality that it is. To Ervin Podgorsak and Glenn Glasgow who graciously took on the additional challenge of providing more than one chapter. To Christina Woodward for sleuthing and resolving incomplete references. To members of the Medical Physics group at the London Regional Cancer Centre who have been consistent in their help and support. To Betsey Phelps and the staff at Medical Physics Publishing for making this book a reality. To Barb Barons for clerical support.

show abstract

Section: Historical Perspectivementioning

confidence: 99%

The Modern Technology of Radiation Oncology: A Compendium for Medical Physicists and Radiation Oncologists

2000

View full text Add to dashboard Cite

show abstract

“…Through the medium of score functions Hope et al (1967) introduced the concept of a calculated judgement which allowed a more quantitative comparison of isodose distributions to be made. A function of the form (KC)n, where K is a normalizing constant, C is the value of the relevant feature of the dose distribution and n the emphasis placed on a particular criterion, is assigned to each of the six criteria of judgement previously mentioned.…”

Section: Score Functionsmentioning

confidence: 99%

“…This results in the evaluation of a very large number of plans for any treatment, and in order to reduce overall calculation time simplifications to the dose calculation had to be introduced. A vector representation of the dose distribution was developed (Hope and Orr 1965) but this was used a t only one point within the tumour in the evaluation of tumour dependent score functions. Although the optimum solution may be determined for this point, sufficient consideration is not taken of factors which will affect the dose to other regions such as variations in non-normal incidence and the presence of heterogeneities.…”

Section: Score Functionsmentioning

confidence: 99%

A new technique for radiotherapy planning using quadratic programming

Redpath

Vickery

Wright

1976

pmb

View full text Add to dashboard Cite

Previous attempts at optimization of radiotherapy planning are described and criticized, and consideration of these attempts has resulted in the development of a new technique using quadratic programming. Uniformity of tumour dose is selected as the most important feature of any plan, and this is achieved by minimizing the variance of the dose to preselected points within the tumour. The dose to vulnerable regions can be constrained not to exceed a given percentage of the mean tumour dose. Optimization of field weight and field type is possible. The operation of the system is described and some typical results are given.

show abstract

“…The configuration of beam directions has a major effect on the quality of the treatment plan and can be considered as a large scale combinatorial optimization problem, 10 usually called a beam orientation optimization (BOO) problem. BOO has been studied since 1967 11 ; however, in the current treatment planning workflow, the beam direction is selected manually by the planner, following a time-consuming trial-and-error process that typically yields suboptimal solutions. 12,13 To accurately measure the impact of the BOO solution in the dosimetric space, a fluence map optimization (FMO) 14 problem must be solved.…”

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

Optimization of X-ray Treatment Planning by Computer Judgement

Cited by 57 publications

References 1 publication

The Modern Technology of Radiation Oncology: A Compendium for Medical Physicists and Radiation Oncologists

The Modern Technology of Radiation Oncology: A Compendium for Medical Physicists and Radiation Oncologists

A new technique for radiotherapy planning using quadratic programming

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

Contact Info

Product

Resources

About