Abstract
In clinical practice, the beam orientation selection process is either tediously done by the planner or based on specific protocols, typically yielding suboptimal and inefficient solutions. Column generation (CG) has been shown to produce superior plans compared to those of human selected beams, especially in highly non-coplanar plans such as 4π Radiotherapy. In this work, we applied AI to explore the decision space of beam orientation selection. At first, a supervised deep learning neural network (SL) is trained to mimic a CG generated policy. By iteratively using SL to predict the next beam, a set of beam orientations would be selected. However, iteratively using SL to select the next beam does not guarantee the plan’s quality. Although the teacher policy, CG, is an efficient method, it is a greedy algorithm and still finds suboptimal solutions that are subject to improvement. To address this, a reinforcement learning application of guided Monte Carlo tree search (GTS) was implemented, coupled with SL to guide the traversal through the tree, and update the fitness values of its nodes. To test the feasibility of GTS, 13 test prostate cancer patients were evaluated. Our results show that we maintained a similar planning target volume (PTV) coverage within 2% error margin, reduce the organ at risk (OAR) mean dose, and in general improve the objective function value, while decreasing the computation time.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
\( x \) and \( y \) are complemented, if \( x \vee y = 1, x \wedge y = 0 \)
References
Dong, P., et al.: 4π noncoplanar stereotactic body radiation therapy for centrally located or larger lung tumors. Int. J. Radiat. Oncol.* Biol.* Phys. 86, 407–413 (2013)
Cabrera-Guerrero, G., Lagos, C., Cabrera, E., Johnson, F., Rubio, J.M., Paredes, F.: Comparing local search algorithms for the beam angles selection in radiotherapy. IEEE Access 6, 23701–23710 (2018)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40, 120–145 (2011)
Kuhn, H., Tucker, A.: Proceedings of 2nd Berkeley Symposium. University of California Press, Berkeley (1951)
Karush, W.: Minima of functions of several variables with inequalities as side conditions. In: Giorgi, G., Kjeldsen, T.H. (eds.) Traces and Emergence of Nonlinear Programming, pp. 217–245. Springer, Basel (2014). https://doi.org/10.1007/978-3-0348-0439-4_10
Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Advances in Neural Information Processing Systems, pp. 971–980 (2017)
Browne, C.B., et al.: A survey of monte carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4, 1–43 (2012)
Nguyen, D., et al.: Dose prediction with U-net: a feasibility study for predicting dose distributions from contours using deep learning on prostate IMRT patients. arXiv preprint arXiv:1709.09233 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sadeghnejad Barkousaraie, A., Ogunmolu, O., Jiang, S., Nguyen, D. (2019). Using Supervised Learning and Guided Monte Carlo Tree Search for Beam Orientation Optimization in Radiation Therapy. In: Nguyen, D., Xing, L., Jiang, S. (eds) Artificial Intelligence in Radiation Therapy. AIRT 2019. Lecture Notes in Computer Science(), vol 11850. Springer, Cham. https://doi.org/10.1007/978-3-030-32486-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-32486-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32485-8
Online ISBN: 978-3-030-32486-5
eBook Packages: Computer ScienceComputer Science (R0)
