A reinforcement learning application of a guided Monte Carlo Tree Search algorithm for beam orientation selection in radiation therapy

  title={A reinforcement learning application of a guided Monte Carlo Tree Search algorithm for beam orientation selection in radiation therapy},
  author={Azar Sadeghnejad-Barkousaraie and Gyanendra Bohara and Steve B. Jiang and Dan Nguyen},
  journal={Machine Learning: Science and Technology},
Current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature because of the size of the combinatorial problem, which leads to suboptimal solutions. We propose a reinforcement learning strategy using a Monte Carlo Tree Search (MCTS) that can find a better beam orientation set in less time than CG. We utilize a reinforcement learning structure involving a supervised learning network to guide the MCTS and to explore… 

Comparing Multi-Objective Local Search Algorithms for the Beam Angle Selection Problem

Three different strategies are proposed and compared to accelerate a previously proposed Pareto local search (PLS) algorithm to solve the beam angle selection problem in IMRT, showing that algorithms proposed reach a similar performance than PLS and require fewer function evaluations.

A Review on Application of Deep Learning Algorithms in External Beam Radiotherapy Automated Treatment Planning

The historical advancement, strengths, and weaknesses of various DL-based automated RT treatment planning techniques are reviewed and artificial intelligence, including machine learning (ML) and deep learning (DL), has gained enormous attention in the RT community.

Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions

Though reinforcement learning has gradually gained momentum in recent years, many researchers in the medical analysis field find it hard to understand and deploy in clinics, so this paper may help the readers to learn how to formulate and solve their medical image analysis research as reinforcement learning problems.

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

  • A. Barragán-MonteroU. Javaid J. Lee
  • Medicine, Computer Science
    Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics
  • 2021



A Fast Deep Learning Approach for Beam Orientation Optimization for Prostate Cancer Treated with Intensity Modulated Radiation Therapy.

A fast beam orientation selection method based on a DNN that selects beam orientations in seconds is developed and is therefore suitable for clinical routines and may save hours of computation.

Neighborhood search approaches to beam orientation optimization in intensity modulated radiation therapy treatment planning

It is shown empirically that the BOO problem can be combined with a new neighborhood structure that allows for faster convergence using the simulated annealing and local search algorithms, thus reducing the amount of time required to obtain a good solution.

Comparing Local Search Algorithms for the Beam Angles Selection in Radiotherapy

A prostate case which considers two organs at risk, namely the rectum and the bladder is considered, and three matheuristic methods based on local search algorithms, namely, steepest descent, next descent, and tabu search are compared to approximately solve the beam angle optimisation problem (BAO).

Automating proton treatment planning with beam angle selection using Bayesian optimization.

A fully automated and efficient treatment planning process for proton therapy, including beam angle optimization was developed using a novel Bayesian optimization approach and previously-developed constrained hierarchical fluence optimization method.

A particle swarm optimization algorithm for beam angle selection in intensity-modulated radiotherapy planning

It is suggested that the introduced PSO algorithm could act as a new promising solution to the beam angle optimization problem and potentially other optimization problems in IMRT, though further studies need to be investigated.

Beam angle optimization for intensity-modulated radiation therapy using a guided pattern search method

The goal of this paper is to introduce a novel approach that uses beam’s-eye-view dose ray tracing metrics within a pattern search method framework in the optimization of the highly non-convex BAO problem.

Automatic beam angle selection in IMRT planning using genetic algorithm.

In this paper an efficient method is presented to investigate how to improve the dose distributions by selecting suitable coplanar beam angles and the results show that ABAS is valid and efficient and can improve the doses distributions within a clinically acceptable computation time.

Effective heuristics for beam angle optimization in radiation therapy

Three novel heuristic approaches to reduce the computation time and find high-quality treatment plans for beam angle optimization (BAO) are proposed and evaluated by applying them to a mixed integer programming (MIP) formulation of BAO for a phantom liver case and a clinical liver case.

Automatic learning-based beam angle selection for thoracic IMRT.

The results demonstrated the feasibility of utilizing a learning-based approach for automatic selection of beam angles in thoracic IMRT planning and may assist in reducing the manual planning workload, while sustaining plan quality.

Optimization of Beam Orientation in Intensity Modulated Radiation Therapy Planning

For the last decade, optimization of beam orientations in intensity-modulated radiation therapy (IMRT) has been shown to be successful in improving the treatment plan. Unfortunately, the quality of a