Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (11): 265-270.

Previous Articles    

Method based on heuristic information for solving non-convex model of radiotherapy planning

ZHANG Dongbing1, LAN Yihua2, WAN Jinxin3   

  1. 1.School of Computer Science and Technology, Huaibei Normal University, Huaibei, Anhui 235000, China
    2.School of Computer and Information Technology, Nanyang Normal University, Nanyang, Henan 473061, China
    3.Medical Imaging Department, Lianyungang Second People’s Hospital, Lianyungang, Jiangsu 222005, China
  • Online:2013-06-01 Published:2013-06-14

基于启发式信息的非凸放疗规划模型的求解方法

张栋冰1,兰义华2,万金鑫3   

  1. 1.淮北师范大学 计算机科学与技术学院,安徽 淮北 235000
    2.南阳师范学院 计算机与信息技术学院,河南 南阳 473061
    3.连云港市第二人民医院 医学影像科,江苏 连云港 222005

Abstract: For the inverse planning process of intensity-modulated radiotherapy—the non-convex mathematical programming for the fluence map optimization with dose volume constraints, this paper presents a novel and scientific heuristic information—distance priority value in normalized space. Compared to the traditional dose ordering heuristic information, this new method leads to better solutions. A phantom example and four test cases show the effectiveness of the proposed method.

Key words: non-convex fractional programming, heuristic algorithm, intensity-modulated radiation therapy technology, linear constrained quadratic programming

摘要: 针对调强放疗逆向优化过程中的关键环节——各照射野的强度照射分布图在带有剂量体积曲线限制条件下的非凸数学规划问题,提出了一种新颖的更加科学的启发式信息——正规化空间内的空间距离排序值。与传统的剂量排序启发式信息相比较,新方法可以得到更好的解。一个简单示例和四个测试病例表明了该方法的有效性。

关键词: 非凸数学规划, 启发式求解, 调强放疗, 线性约束二次规划