An optimization method for importance factors and beam weights based on genetic algorithms for radiotherapy treatment planning

We propose a new method for selecting importance factors (for regions of in terest like organs at risk) used to plan conformal radiotherapy. Importance factors, also known as weighting factors or penalty factors, are essential in determining the relative importance of multiple objectives or the penal ty ratios of constraints incorporated into cost functions, especially in de aling with dose optimization in radiotherapy treatment planning. Researcher s usually choose importance factors on the basis of a trial-and-error proce ss to reach a balance between all the objectives. In this study, we used a genetic algorithm and adopted a real-number encoding method to represent bo th beam weights and importance factors in each chromosome. The algorithm st arts by optimizing the beam weights for a fixed number of iterations then m odifying the importance factors for another fixed number of iterations. Dur ing the first phase, the genetic operators, such as crossover and mutation, are carried out only on beam weights, and importance factors for each chro mosome are not changed or 'frozen'. In the second phase, the situation is r eversed: the beam weights are 'frozen' and the importance factors are chang ed after crossover and mutation. Through alternation of these two phases, b oth beam weights and importance factors are adjusted according to a fitness function that describes the conformity of dose distribution in planning ta rget volume and dose-tolerance constraints in organs at risk. Those chromos omes with better fitness are passed into the next generation, showing that they have a better combination of beam weights and importance factors. Alth ough the ranges of the importance factors should be set in advance by using this algorithm, it is much more convenient than selecting specific numbers for importance factors. Three clinical examples are presented and compared with manual plans to verify this method. Three-dimensional standard displa ys and dose-volume histograms are shown to demonstrate that this method is feasible, automatic and convenient.