A modified genetic algorithm for the beam angle optimization problem in intensity-modulated radiotherapy planning

  • Authors:

  • Yongjie Li;Dezhong Yao;Jiancheng Zheng;Jonathan Yao

  • Affiliations:

  • School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China;School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China;Topslane Inc, Pleasant Hill, CA;Topslane Inc, Pleasant Hill, CA

  • Venue:
  • EA'05 Proceedings of the 7th international conference on Artificial Evolution
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a modified genetic algorithm (GA) is proposed to improve the efficiency of the beam angle optimization (BAO) problem in intensity-modulated radiotherapy (IMRT). Two modifications are made to GA in this study: (1) a new operation named sorting operation is introduced to sort the gene in each chromosome before the crossover operation, and (2) expert knowledge about tumor treatment is employed to guide the GA evolution. Two types of expert knowledge are employed, i.e., beam orientation constraints and beam configuration templates. The user-defined knowledge is used to reduce the search space and guide the optimization process. The sorting operation is introduced to inherently improve the evolution performance for the specified ABO problem. The beam angles are selected using GA, and the intensity maps of the corresponding beams are optimized using a conjugate gradient (CG) method. The comparisons of the preliminary optimization results on a clinical prostate case show that the proposed optimization algorithm can slightly or heavily improve the computation efficiency.