Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy.
Dan NguyenRafe McBethAzar Sadeghnejad-BarkousaraieGyanendra BoharaChenyang ShenXun JiaSteve B. JiangPublished in: CoRR (2019)
Keyphrases
- radiation therapy
- neural network
- treatment plan
- pareto optimal
- domain knowledge
- ct images
- treatment planning
- image guided
- prostate cancer
- radiation dose
- radiation doses
- multi objective
- organ motion
- normal tissue
- computer aided
- optimization algorithm
- objective function
- computed tomography
- imaging modalities
- gray level
- deformable registration
- particle swarm optimization
- cost function
- optimal solution