Improvement based on regularization for building hybrid criteria model of radiotherapy planning

doi:10.3778/j.issn.1002-8331.1605-0377

Computer Engineering and Applications ›› 2017, Vol. 53 ›› Issue (1): 23-28.DOI: 10.3778/j.issn.1002-8331.1605-0377

Previous Articles Next Articles

Improvement based on regularization for building hybrid criteria model of radiotherapy planning

GUO Caiping1，2，3, SHU Huazhong4, GUI Zhiguo1, 2, ZHANG Pengcheng1，2

1.National Key Laboratory for Electronic Measurement Technology, North University of China, Taiyuan 030051, China
2.Key Laboratory of Instrument Science & Dynamic Measurement Technology，North University of China, Taiyuan 030051, China
3.Department of Electronic Engineering, Taiyuan Institute of Technology, Taiyuan 030008, China
4.Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China

Online:2017-01-01 Published:2017-01-10

基于正则化的混合准则放疗规划模型的改进

郭彩萍1，2，3，舒华忠4，桂志国1，2，张鹏程1，2

1.中北大学电子测试技术国家重点实验室，太原 030051
2.中北大学仪器科学与动态测试教育部重点实验室，太原 030051
3.太原工业学院电子工程系，太原 030008
4.东南大学影像科学与技术实验室，南京 210096

Abstract

Abstract: To solve the problem existing in the physical-biological hybrid criteria model based on the generalized equivalent uniform dose linear objective function in conformal intensity-modulated radiation therapy, this paper presents a smooth and convex regularization of max function using regularization theory, and improves the hybrid criteria model based on the generalized equivalent uniform dose. When this improved model is applied in inverse planning optimization process, problems（searching ability of optimization algorithm is restricted and it is hard time predicting how large a step can be made when using a gradient-based optimization algorithm） existing in original model are circumvented. Compared to the original model, experiments show that the method using newly proposed model can get better protection to organs at risk while ensuring similar dose coverage for target and the quality of radiotherapy planning is improved.

Key words: intensity-modulated radiation therapy, generalized equivalent uniform dose, hybrid criteria, regularization

摘要： 针对调强放射治疗中基于等效均匀剂量线性目标函数的物理生物混合准则模型的不足，利用正则化理论构造了最大函数的平滑和凸正则化函数，改进了基于等效均匀剂量线性目标函数的混合准则放疗规划模型，解决了原模型限制优化算法寻优能力和难以确定梯度算法步长的问题。实验证明，该方法可以在保证相似靶区剂量覆盖特性的前提下，更好地保护危及器官，提高了放疗计划质量。

关键词: 调强放疗, 等效均匀剂量, 混合准则, 正则化

GUO Caiping1，2，3, SHU Huazhong4, GUI Zhiguo1, 2, ZHANG Pengcheng1，2. Improvement based on regularization for building hybrid criteria model of radiotherapy planning[J]. Computer Engineering and Applications, 2017, 53(1): 23-28.

郭彩萍1，2，3，舒华忠4，桂志国1，2，张鹏程1，2. 基于正则化的混合准则放疗规划模型的改进[J]. 计算机工程与应用, 2017, 53(1): 23-28.

[1]	ZHAO Tong, HUANG Zheng, WANG Xiuchao, LI Miao, ZHANG Yun, ZHENG Xiujuan, LIU Kai. Recognition Research on Concealing Behavior in Psychological Test [J]. Computer Engineering and Applications, 2020, 56(20): 158-164.
[2]	LIU Chunling, ZHANG Li. Recommendation Algorithm for Improving Asymmetric Similarity and Associated Regularization [J]. Computer Engineering and Applications, 2020, 56(16): 45-49.
[3]	HAN Ming1，2, WANG Jingtao1, MENG Junying1, LIU Jiaomin2. Energy Functional of Local Entropy Combined with Non-Convex Regularization for Image Segmentation [J]. Computer Engineering and Applications, 2019, 55(6): 160-167.
[4]	YANG-ZHAO Qilin, PENG Dingtao, TANG Qi, LUO Xiaomin. Smoothing Quasi-Newton Algorithm for [lp] Regularization of Sparse Optimization [J]. Computer Engineering and Applications, 2019, 55(22): 163-171.
[5]	ZHANG Xiaoting, HE Lang, HUANG Zhangcan, TAN Qing. High Order Ordinary Differential Equation Prediction Model Based on MFR-GEP [J]. Computer Engineering and Applications, 2019, 55(21): 247-253.
[6]	XU Shuang1, YU Li2. Regularized Matrix Factorization Algorithm for Multi-View Data Clustering [J]. Computer Engineering and Applications, 2019, 55(14): 142-147.
[7]	LIU Heng, HOU Yue. Application of Bayesian Neural Network in Prediction of Stock Time Series [J]. Computer Engineering and Applications, 2019, 55(12): 225-229.
[8]	SUN Jiamei, WU Chengmao. Regularized Picture Fuzzy Clustering and Its Robust Segmentation Algorithm [J]. Computer Engineering and Applications, 2019, 55(11): 179-186.
[9]	ZHANG Wei, XU Aiqiang. Application of MKL model incorporated within-class scatter in analog circuit diagnosis [J]. Computer Engineering and Applications, 2018, 54(9): 5-12.
[10]	CAO Zaihui1，2, WU Qingtao1，2, SHI Jinfa2，3. Attribute selection algorithm based on low rank and Tula Laplace [J]. Computer Engineering and Applications, 2018, 54(17): 110-115.
[11]	HUANG Jiqing, WANG Lihui, QIN Jin, CHENG Xinyu, ZHANG Jian, LI Zhi. Improved image super resolution reconstruction method based on multiple regularizations [J]. Computer Engineering and Applications, 2018, 54(15): 22-28.
[12]	CHEN Siyong, AN Congpei. l1-regularization approximation model and its application [J]. Computer Engineering and Applications, 2018, 54(12): 35-40.
[13]	WENG Qian1，2，3, MAO Zhengyuan2, LIN Jiawen3, JIAN Cairen4. Dimension reduction method based on spectral regression and graph regularization least square regression [J]. Computer Engineering and Applications, 2017, 53(5): 81-84.
[14]	ZHANG Hang, YE Dongyi. Recommender algorithm based on matrix factorization with multiple regularization parameters [J]. Computer Engineering and Applications, 2017, 53(3): 74-79.
[15]	KONG Guojie, WANG Kai, SHEN Mingtang, ZHANG Fang, WU Ke. Adaptive total variation method with wavelet threshold filtering [J]. Computer Engineering and Applications, 2016, 52(8): 240-242.

Improvement based on regularization for building hybrid criteria model of radiotherapy planning

基于正则化的混合准则放疗规划模型的改进

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics