Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks

Rafid Mahmood, Aaron Babier, Andrea McNiven, Adam Diamant, Timothy C. Y. Chan
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:484-499, 2018.

Abstract

Knowledge-based planning (KBP) is an automated approach to radiation therapy treatment planning that involves predicting desirable treatment plans before they are then corrected to deliverable ones. We propose a generative adversarial network (GAN) approach for predicting desirable 3D dose distributions that eschews the previous paradigms of site-specific feature engineering and predicting low-dimensional representations of the plan. Experiments on a dataset of oropharyngeal cancer patients show that our approach significantly outperforms previous methods on several clinical satisfaction criteria and similarity metrics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v85-mahmood18a, title = {Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks}, author = {Mahmood, Rafid and Babier, Aaron and McNiven, Andrea and Diamant, Adam and Chan, Timothy C. Y.}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {484--499}, year = {2018}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {85}, series = {Proceedings of Machine Learning Research}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/mahmood18a/mahmood18a.pdf}, url = {https://proceedings.mlr.press/v85/mahmood18a.html}, abstract = {Knowledge-based planning (KBP) is an automated approach to radiation therapy treatment planning that involves predicting desirable treatment plans before they are then corrected to deliverable ones. We propose a generative adversarial network (GAN) approach for predicting desirable 3D dose distributions that eschews the previous paradigms of site-specific feature engineering and predicting low-dimensional representations of the plan. Experiments on a dataset of oropharyngeal cancer patients show that our approach significantly outperforms previous methods on several clinical satisfaction criteria and similarity metrics.} }
Endnote
%0 Conference Paper %T Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks %A Rafid Mahmood %A Aaron Babier %A Andrea McNiven %A Adam Diamant %A Timothy C. Y. Chan %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-mahmood18a %I PMLR %P 484--499 %U https://proceedings.mlr.press/v85/mahmood18a.html %V 85 %X Knowledge-based planning (KBP) is an automated approach to radiation therapy treatment planning that involves predicting desirable treatment plans before they are then corrected to deliverable ones. We propose a generative adversarial network (GAN) approach for predicting desirable 3D dose distributions that eschews the previous paradigms of site-specific feature engineering and predicting low-dimensional representations of the plan. Experiments on a dataset of oropharyngeal cancer patients show that our approach significantly outperforms previous methods on several clinical satisfaction criteria and similarity metrics.
APA
Mahmood, R., Babier, A., McNiven, A., Diamant, A. & Chan, T.C.Y.. (2018). Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks. Proceedings of the 3rd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 85:484-499 Available from https://proceedings.mlr.press/v85/mahmood18a.html.

Related Material