It has been believed that the better optimization can be achieved by tile P＋＋ optimization strategy since the P＋ curve shows a rather shallow maximum. In this paper, the P＋＋ optimization strategy has been verifie...It has been believed that the better optimization can be achieved by tile P＋＋ optimization strategy since the P＋ curve shows a rather shallow maximum. In this paper, the P＋＋ optimization strategy has been verified by evaluating （intensity-modulated radiation therapy, IMRT） plans for a T4 stage NPC patient in the situation where diffieuh compromise has to be made between probabilities for tumor control and normal tissue injuh＇y. The results showed that including the biological objective gEUD into the plan optimization couht decrease the mean dose of OAR. Theoretically, P＋＋ optimization strategy could be helpfnl to find the refined optimization solution for radiation therapy planning. However, in clinical radiotherapy practice, disease situations will form restrictions to use the biological evaluation only. More factors including both physical and biological models should be considered in a planning evaluation process to aehieve a best clinical solution.展开更多
An integrated optimization strategy based on Kriging model and multi-objective particle swarm optimization(PSO) algorithm was constructed.As a new surrogate model technology,Kriging model has better fitting precision ...An integrated optimization strategy based on Kriging model and multi-objective particle swarm optimization(PSO) algorithm was constructed.As a new surrogate model technology,Kriging model has better fitting precision for nonlinear problem.The Kriging model was adopted to replace computer aided engineering(CAE) simulation as fitness function of multi-objective PSO algorithm,and the computation cost can be reduced greatly.By introducing multi-objective handling mechanism of crowding distance and mutation operator to multiobjective PSO algorithm,the entire Pareto front can be approximated better.It is shown that the multi-objective optimization strategy can get higher solving accuracy and computation efficiency under small sample.展开更多
文摘It has been believed that the better optimization can be achieved by tile P＋＋ optimization strategy since the P＋ curve shows a rather shallow maximum. In this paper, the P＋＋ optimization strategy has been verified by evaluating （intensity-modulated radiation therapy, IMRT） plans for a T4 stage NPC patient in the situation where diffieuh compromise has to be made between probabilities for tumor control and normal tissue injuh＇y. The results showed that including the biological objective gEUD into the plan optimization couht decrease the mean dose of OAR. Theoretically, P＋＋ optimization strategy could be helpfnl to find the refined optimization solution for radiation therapy planning. However, in clinical radiotherapy practice, disease situations will form restrictions to use the biological evaluation only. More factors including both physical and biological models should be considered in a planning evaluation process to aehieve a best clinical solution.
基金the National Natural Science Foundation of China (No. 50873060)
文摘An integrated optimization strategy based on Kriging model and multi-objective particle swarm optimization(PSO) algorithm was constructed.As a new surrogate model technology,Kriging model has better fitting precision for nonlinear problem.The Kriging model was adopted to replace computer aided engineering(CAE) simulation as fitness function of multi-objective PSO algorithm,and the computation cost can be reduced greatly.By introducing multi-objective handling mechanism of crowding distance and mutation operator to multiobjective PSO algorithm,the entire Pareto front can be approximated better.It is shown that the multi-objective optimization strategy can get higher solving accuracy and computation efficiency under small sample.
