Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy

Shiraishi, S.; Moore, Kevin L.

doi:10.1118/1.4938583

Cited by 199 publications

(245 citation statements)

References 19 publications

Supporting

Mentioning

241

Contrasting

Order By: Relevance

“…Should the model performance be highly dependent on the library volume31 and average quality of the training plans,17, 32 incorporating the model‐improved constituent training plans into the model (closed‐loop)25 may potentially evolve the model as a cycle of interactive improvement. There has been attempts to iteratively improve KDE (kernel density estimation)‐based DVH prediction model.…”

Section: Introductionmentioning

confidence: 99%

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

Wang

Huang

et al. 2018

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeTo test if a RapidPlan DVH estimation model and its training plans can be improved interactively through a closed‐loop evolution process.Methods and materialsEighty‐one manual plans (P0) that were used to configure an initial rectal RapidPlan model (M0) were reoptimized using M0 (closed‐loop), yielding 81 P1 plans. The 75 improved P1 (P1+) and the remaining 6 P0 were used to configure model M1. The 81 training plans were reoptimized again using M1, producing 23 P2 plans that were superior to both their P0 and P1 forms (P2+). Hence, the knowledge base of model M2 composed of 6 P0, 52 P1+, and 23 P2+. Models were tested dosimetrically on 30 VMAT validation cases (Pv) that were not used for training, yielding Pv(M0), Pv(M1), and Pv(M2) respectively. The 30 Pv were also optimized by M2_new as trained by the library of M2 and 30 Pv(M0).ResultsBased on comparable target dose coverage, the first closed‐loop reoptimization significantly (P < 0.01) reduced the 81 training plans’ mean dose to femoral head, urinary bladder, and small bowel by 2.65 Gy/15.63%, 2.06 Gy/8.11%, and 1.47 Gy/6.31% respectively, which were further reduced significantly (P < 0.01) in the second closed‐loop reoptimization by 0.04 Gy/0.28%, 0.18 Gy/0.77%, 0.22 Gy/1.01% respectively. However, open‐loop VMAT validations displayed more complex and intertwined plan quality changes: mean dose to urinary bladder and small bowel decreased monotonically using M1 (by 0.34 Gy/1.47%, 0.25 Gy/1.13%) and M2 (by 0.36 Gy/1.56%, 0.30 Gy/1.36%) than using M0. However, mean dose to femoral head increased by 0.81 Gy/6.64% (M1) and 0.91 Gy/7.46% (M2) than using M0. The overfitting problem was relieved by applying model M2_new.ConclusionsThe RapidPlan model and its constituent plans can improve each other interactively through a closed‐loop evolution process. Incorporating new patients into the original training library can improve the RapidPlan model and the upcoming plans interactively.

show abstract

Section: Introductionmentioning

confidence: 99%

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

Wang

Huang

et al. 2018

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…Patient‐specific anatomical parameters were calculated on a voxel‐by‐voxel basis in an approximately spherical volume of 4.5 cm from each discrete target volume in any given multimet plan, i.e., a multimet plan with N total lesions would yield N individual, three‐dimensional dose predictions — one for each lesion. The voxel‐specific parameters included: distance to the nearest PTV voxel, the azimuthal/elevation angles from the PTV centroid, the principal component axis azimuthal/elevation angles (assuming a uniformly distributed PTV mass) and the distances to critical nonbrain OARs . The nonbrain OARs used for this study were the brainstem, optic chiasm, and optic nerves (cochlea were initially included, but none of the 41 available cases contained doses to these structures large enough to bear consideration).…”

Section: Methodsmentioning

confidence: 99%

“…The nonbrain OARs used for this study were the brainstem, optic chiasm, and optic nerves (cochlea were initially included, but none of the 41 available cases contained doses to these structures large enough to bear consideration). These calculated parameters were used as input into a previously published KBP artificial neural network (ANN) trained with 39 single‐target linear accelerator‐based SRS plans to create the three‐dimensional dose distribution for each individual lesion . The treatment plans used for the training were chosen because they possessed superior values of key quality metrics (QMs).…”

Section: Methodsmentioning

confidence: 99%

Heuristic knowledge‐based planning for single‐isocenter stereotactic radiosurgery to multiple brain metastases

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…KBP can be generalized to be the automation of different steps in the creation of a plan based on past practice. These steps can range from the estimation of field direction,1 weights of optimization objectives,2 and even dose distribution 3, 4. The majority of KBP work, however, has focused on estimating dose–volume histograms (DVHs)5, 6, 7, 8, 9 which are commonly used to evaluate plan quality and guide the inverse planning process.…”

Section: Introductionmentioning

confidence: 99%

Creation of knowledge‐based planning models intended for large scale distribution: Minimizing the effect of outlier plans

Aviles

Marcos²,

Sasaki

et al. 2018

J Applied Clin Med Phys

View full text Add to dashboard Cite

Knowledge‐based planning (KBP) can be used to estimate dose–volume histograms (DVHs) of organs at risk (OAR) using models. The task of model creation, however, can result in estimates with differing accuracy; particularly when outlier plans are not properly addressed. This work used RapidPlan™ to create models for the prostate and head and neck intended for large‐scale distribution. Potential outlier plans were identified by means of regression analysis scatter plots, Cook's distance, coefficient of determination, and the chi‐squared test. Outlier plans were identified as falling into three categories: geometric, dosimetric, and over‐fitting outliers. The models were validated by comparing DVHs estimated by the model with those from a separate and independent set of clinical plans. The estimated DVHs were also used as optimization objectives during inverse planning. The analysis tools lead us to identify as many as 7 geometric, 8 dosimetric, and 20 over‐fitting outliers in the raw models. Geometric and over‐fitting outliers were removed while the dosimetric outliers were replaced after re‐planning. Model validation was done by comparing the DVHs at 50%, 85%, and 99% of the maximum dose for each OAR (denoted as V50, V85, and V99) and agreed within −2% to 4% for the three metrics for the final prostate model. In terms of the head and neck model, the estimated DVHs agreed from −2.0% to 5.1% at V50, 0.1% to 7.1% at V85, and 0.1% to 7.6% at V99. The process used to create these models improved the accuracy for the pharyngeal constrictor DVH estimation where one plan was originally over‐estimated by more than twice. In conclusion, our results demonstrate that KBP models should be carefully created since their accuracy could be negatively affected by outlier plans. Outlier plans can be addressed by removing them from the model and re‐planning.

show abstract

Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy

Abstract: The study demonstrates highly accurate knowledge-based 3D dose predictions for radiotherapy plans.

Cited by 199 publications

References 19 publications

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

Heuristic knowledge‐based planning for single‐isocenter stereotactic radiosurgery to multiple brain metastases

Creation of knowledge‐based planning models intended for large scale distribution: Minimizing the effect of outlier plans

Contact Info

Product

Resources

About