Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks

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.

arXiv comment15 pages. Accepted for publication in PMLR. Presented at Machine Learning for Health Care

Cited by in corpus (10)

• Generative Adversarial Network in Medical Imaging: A Review
• OpenKBP: The open-access knowledge-based planning grand challenge
• 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
• Long short-term memory networks for proton dose calculation in highly heterogeneous tissues
• Improving Efficiency of Training a Virtual Treatment Planner Network via Knowledge-guided Deep Reinforcement Learning for Intelligent Automatic Treatment Planning of Radiotherapy
• Using Deep Learning to Predict Beam-Tunable Pareto Optimal Dose Distribution for Intensity Modulated Radiation Therapy
• Knowledge-based Radiation Treatment Planning: A Data-driven Method Survey
• An Artificial Intelligence-Driven Agent for Real-Time Head-and-Neck IMRT Plan Generation using Conditional Generative Adversarial Network (cGAN)
• Generating Pareto optimal dose distributions for radiation therapy treatment planning
• Site-Agnostic 3D Dose Distribution Prediction with Deep Learning Neural Networks