IMRT逆向计划中的混合多目标梯度算法的研究.pdf

IMRT 逆向计划中的混合多目标梯度算法研究 摘 要 优化算法作为放射治疗计划系统的核心模块之一，一直以来备受关注，寻 求快速高精度的优化算法对于发展调强放疗逆向计划系统具有重要意义。 本论文针对放射治疗逆向计划中靶区、正常组织、危及器官优化过程的多 目标特性，在对多目标优化理论和方法、剂量计算、智能算法等进行研究的基 础上，开展调强放射治疗中逆向计划过程多目标优化算法的研究，为精确放疗 计划系统提供多目标优化的逆向计划模块。 本论文将多目标遗传算法与梯度算法的进化策略有机结合，构造一种混合 多目标梯度算法，该算法对每一种群使用梯度算法求解下一代新群体，采用实 数运算。测试函数地分析验证了算法的有效性，并将其应用于IMRT 逆向计划 过程：通过水模中的测试算例，使用基于平均剂量分布的目标函数，得出强度 分布。与其他优化算法的比较结果表明，该混合多目标梯度算法可节省大量计 算时间，且具有较高的计算精度，能够满足实际应用的要求。 关键词：梯度方法；逆向计划；多目标优化；混合算法 Study on Hybrid Multi-objective Gradient Algorithm for Inverse Planning of IMRT ABSTRACT As one of the core modules on radiation treatment planning system(TPS/RTS), optimization algorithm has been concerned very much. It is very important to develop inverse planning system in intensity modulated radiation therapy (IMRT) for seeking a high-speed and precise optimization algorithm. Aimming at the multi-objective characteristic of target volume, normal tissue and organ at risk on inverse planning of IMRT, based on the research of theory and method of multi-objective optimization, dose calculation, intelligent algorithm, This thesis develop a multi-objective gradient algorithm for the inverse planning module in the IMRT PST . The multi-objective genetic algorithm is combined with gradient algorithm, the hybrid multi-objective gradient algorithm is formed by real number. Test functions are used to analyze the efficiency of the algorithm. Under the simulation case of water phantom, the algorithm is applied to inverse planning process of IMRT. The objective functions of (planning target volume) PTV and (normal tissue) NT are based on the average dose distribution. Comparising