Literature DB >> 31675444

Knowledge-based automated planning with three-dimensional generative adversarial networks.

Aaron Babier1, Rafid Mahmood1, Andrea L McNiven2,3, Adam Diamant4, Timothy C Y Chan1,5.   

Abstract

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.
© 2019 American Association of Physicists in Medicine.

Entities:  

Keywords:  3D-dose prediction; artificial intelligence; automated planning; generative adversarial networks; knowledge-based planning; optimization

Mesh:

Year:  2019        PMID: 31675444     DOI: 10.1002/mp.13896

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  15 in total

1.  Automatic configuration of the reference point method for fully automated multi-objective treatment planning applied to oropharyngeal cancer.

Authors:  Rens van Haveren; Ben J M Heijmen; Sebastiaan Breedveld
Journal:  Med Phys       Date:  2020-03-05       Impact factor: 4.071

2.  Utilizing pre-determined beam orientation information in dose prediction by 3D fully-connected network for intensity modulated radiotherapy.

Authors:  Hui Yan; Shoulin Liu; Jingjing Zhang; Jianfei Liu; Teng Li
Journal:  Quant Imaging Med Surg       Date:  2021-12

3.  Deep learning-based inverse mapping for fluence map prediction.

Authors:  Lin Ma; Mingli Chen; Xuejun Gu; Weiguo Lu
Journal:  Phys Med Biol       Date:  2020-11-27       Impact factor: 3.609

Review 4.  Artificial intelligence and machine learning for medical imaging: A technology review.

Authors:  Ana Barragán-Montero; Umair Javaid; Gilmer Valdés; Dan Nguyen; Paul Desbordes; Benoit Macq; Siri Willems; Liesbeth Vandewinckele; Mats Holmström; Fredrik Löfman; Steven Michiels; Kevin Souris; Edmond Sterpin; John A Lee
Journal:  Phys Med       Date:  2021-05-09       Impact factor: 2.685

5.  A comparison of Monte Carlo dropout and bootstrap aggregation on the performance and uncertainty estimation in radiation therapy dose prediction with deep learning neural networks.

Authors:  Dan Nguyen; Azar Sadeghnejad Barkousaraie; Gyanendra Bohara; Anjali Balagopal; Rafe McBeth; Mu-Han Lin; Steve Jiang
Journal:  Phys Med Biol       Date:  2021-02-24       Impact factor: 3.609

6.  A Novel Machine Learning Model for Dose Prediction in Prostate Volumetric Modulated Arc Therapy Using Output Initialization and Optimization Priorities.

Authors:  P James Jensen; Jiahan Zhang; Bridget F Koontz; Q Jackie Wu
Journal:  Front Artif Intell       Date:  2021-04-23

7.  DVH Prediction for VMAT in NPC with GRU-RNN: An Improved Method by Considering Biological Effects.

Authors:  Yongdong Zhuang; Yaoqin Xie; Luhua Wang; Shaomin Huang; Li-Xin Chen; Yuenan Wang
Journal:  Biomed Res Int       Date:  2021-01-19       Impact factor: 3.411

8.  Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks.

Authors:  Xue Bai; Jie Zhang; Binbing Wang; Shengye Wang; Yida Xiang; Qing Hou
Journal:  Biomed Eng Online       Date:  2021-10-09       Impact factor: 2.819

9.  Assessment of efficacy in automated plan generation for Varian Ethos intelligent optimization engine.

Authors:  Shyam Pokharel; Abilio Pacheco; Suzanne Tanner
Journal:  J Appl Clin Med Phys       Date:  2022-01-27       Impact factor: 2.102

10.  A feasibility study for in vivo treatment verification of IMRT using Monte Carlo dose calculation and deep learning-based modelling of EPID detector response.

Authors:  Jun Zhang; Zhibiao Cheng; Ziting Fan; Qilin Zhang; Xile Zhang; Ruijie Yang; Junhai Wen
Journal:  Radiat Oncol       Date:  2022-02-10       Impact factor: 3.481

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.