Contextual Atlas Regression Forests: Multiple-Atlas-Based Automated Dose Prediction in Radiation Therapy

McIntosh, Chris; Purdie, Thomas G.

doi:10.1109/tmi.2015.2505188

Cited by 69 publications

(67 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[8][9][10][11][12][13][14][15][16] While the majority of these methods use hand-tailored or low dimensional features for prediction, recent advances in machine learning have spurred the development of KBP methods that predict full dose distributions using automatically generated high-dimensional features. 8,17,18 The most recent work in this space has focused on neural network-based KBP methods, which are trained on libraries of historical plans to predict dose for each axial slice separately [i.e., two-dimensional (2D) KBP methods] 8,18,19 or all slices concurrently [i.e., three-dimensional (3D) KBP methods]. 20,21 Among the 2D methods, generative adversarial networks (GANs) have been shown to perform the best 18 while among the 3D methods, DoseNet is considered state-of-the-art.…”

Section: Introductionmentioning

confidence: 99%

Knowledge‐based automated planning with three‐dimensional generative adversarial networks

et al. 2019

View full text Add to dashboard Cite

Purpose To develop a knowledge‐based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three‐dimensional (3D) dose. Methods Our knowledge‐based automated planning (KBAP) pipeline consisted of a knowledge‐based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence‐based plans, respectively. We developed a novel generative adversarial network (GAN)‐based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state‐of‐the‐art deep learning–based KBP methods from the literature. We also developed an additional benchmark, a two‐dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted dose distributions achieved all target clinical criteria. Each KBP model was trained on 130 previously delivered oropharyngeal treatment plans. Performance was tested on 87 out‐of‐sample previously delivered treatment plans. All KBAP plans were evaluated using clinical planning criteria and compared to their corresponding clinical plans. KBP prediction quality was assessed using dose‐volume histogram (DVH) differences from the corresponding clinical plans. Results The best performing KBAP plans were generated using predictions from the 3D GAN model that were multiplicatively scaled. These plans satisfied 77% of all clinical criteria, compared to the clinical plans, which satisfied 67% of all criteria. In general, multiplicatively scaling predictions prior to optimization increased the fraction of clinical criteria satisfaction by 11% relative to the plans generated with nonscaled predictions. Additionally, these KBAP plans satisfied the same criteria as the clinical plans 84% and 8% more frequently as compared to the two benchmark methods, respectively. Conclusions We developed the first knowledge‐based automated planning framework using a 3D generative adversarial network for prediction. Our results, based on 217 oropharyngeal cancer treatment plans, demonstrated superior performance in satisfying clinical criteria and generated more realistic plans as compared to the previous state‐of‐the‐art approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Knowledge‐based automated planning with three‐dimensional generative adversarial networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Our model demonstrated that mean absolute errors of 3D dose for Body are 1.9 ± 1.8%. Using the atlas regression forests for three clinical treatment plan sites, McIntosh and Purdie reported that the overall dose prediction accuracies are 78.68%, 64.76%, 86.83% for whole breast, breast cavity, and prostate cases under the Gamma metric (passing rate standard is 5 mm/5%). Our study showed that the overall 3D passing rate for NPC cases ranged from 81.5% to 93.4% (averaged 88.4%) under the standard of 3 mm/3% (see Appendix ).…”

Section: Discussionmentioning

confidence: 99%

A deep learning method for prediction of three‐dimensional dose distribution of helical tomotherapy

Liu

Fan

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Purpose To develop a deep learning method for prediction of three‐dimensional (3D) voxel‐by‐voxel dose distributions of helical tomotherapy (HT). Methods Using previously treated HT plans as training data, a deep learning model named U‐ResNet‐D was trained to predict a 3D dose distribution. First, the contoured structures and dose volumes were converted from plan database to 3D matrix with a program based on a developed visualization toolkit (VTK), then transferred to U‐ResNet‐D for correlating anatomical features and dose distributions at voxel‐level. One hundred and ninety nasopharyngeal cancer (NPC) patients treated by HT with multiple planning target volumes (PTVs) in different prescription patterns were studied. The model was typically trained from scratch with weights randomly initialized rather than using transfer‐learning method, and used to predict new patient's 3D dose distributions. The predictive accuracy was evaluated with three methods: (a) The dose difference at the position r, δ(r, r) = Dc(r) − Dp(r), was calculated for each voxel. The mean (μδ(r,r)) and standard deviation (σδ(r,r)) of δ(r, r) were calculated to assess the prediction bias and precision; (b) The mean absolute differences of dosimetric indexes (DIs) including maximum and mean dose, homogeneity index, conformity index, and dose spillage for PTVs and organ at risks (OARs) were calculated and statistically analyzed with the paired‐samples t test; (c) Dice similarity coefficients (DSC) between predicted and clinical isodose volumes were calculated. Results The U‐ResNet‐D model predicted 3D dose distribution accurately. For twenty tested patients, the prediction bias ranged from −2.0% to 2.3% and prediction error varied from 1.5% to 4.5% (relative to prescription) for 3D dose differences. The mean absolute dose differences for PTVs and OARs are within 2.0% and 4.2%, and nearly all the DIs for PTVs and OARs had no significant differences. The averaged DSC ranged from 0.95 to 1 for different isodose volumes. Conclusions The study developed a new deep learning method for 3D voxel‐by‐voxel dose prediction, and shown to be able to produce accurately dose predictions for nasopharyngeal patients treated by HT. The predicted 3D dose map can be useful for improving radiotherapy planning design, ensuring plan quality and consistency, making clinical technique comparison, and guiding automatic treatment planning.

show abstract

“…Improving specific components of an RT plan via knowledge-based techniques has been shown to substantially increase plan quality. 10,11,12 However, the implementation of such techniques with the goal of optimizing the RT plan as a whole would entail a paradigm shift in the manner in which cancer centers gather and store data. We conclude that a binary classification of erroneous plans remains the best feasible A natural extension of this work is to evaluate these methods across data from multiple institutions, although there are two key challenges.…”

Section: Discussionmentioning

confidence: 99%

Guided undersampling classification for automated radiation therapy quality assurance of prostate cancer treatment

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

Contextual Atlas Regression Forests: Multiple-Atlas-Based Automated Dose Prediction in Radiation Therapy

Cited by 69 publications

References 48 publications

Knowledge‐based automated planning with three‐dimensional generative adversarial networks

Knowledge‐based automated planning with three‐dimensional generative adversarial networks

A deep learning method for prediction of three‐dimensional dose distribution of helical tomotherapy

Guided undersampling classification for automated radiation therapy quality assurance of prostate cancer treatment

Contact Info

Product

Resources

About