[1]朱健,白曈,李宝生舒华忠,等.肿瘤放疗并发症概率预测模型参数拟合方法[J].东南大学学报(自然科学版),2015,45(2):256-259.[doi:10.3969/j.issn.1001-0505.2015.02.011]
　Zhu Jian,Bai Tong,Li BaoshengShu Huazhong,et al.Parameter fitting method of NTCP predictive model in radiation oncology[J].Journal of Southeast University (Natural Science Edition),2015,45(2):256-259.[doi:10.3969/j.issn.1001-0505.2015.02.011]
点击复制

肿瘤放疗并发症概率预测模型参数拟合方法()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
45
期数:
2015年第2期
页码:
256-259
栏目:
计算机科学与工程
出版日期:
2015-03-20

文章信息/Info

Title:
Parameter fitting method of NTCP predictive model in radiation oncology
作者:
朱健1; 2; 白曈2; 李宝生1; 2舒华忠1; Antoine Simon3; Renaud de Crevoisier3
1东南大学影像科学与技术实验室, 南京 210096; 2山东省肿瘤防治研究院, 济南 250117; 3雷恩第一大学信号与图像实验室, 法国雷恩 35510
Author(s):
Zhu Jian1; 2;  Bai Tong2;  Li Baosheng1; 2Shu Huazhong1;  Antoine Simon3;  Renaud de Crevoisier3
1Laboratory of Image Science and Technique, Southeast University, Nanjing 210096, China
2Shandong Cancer Hospital and Institute, Jinan 250117, China
3Laboratoire Traitement du Signal et de l’Image, Université de Rennes 1, Rennes 35510, France
关键词:
肿瘤;  放射治疗;  并发症;  NTCP模型
Keywords:
tumor;  radiotherapy;  complication;  NTCP(normal tissue complication probability)model
分类号:
TP391.9
DOI:
10.3969/j.issn.1001-0505.2015.02.011
摘要:
为了建立具有群体特异性的肿瘤放疗NTCP预测模型,提出了一种模型参数拟合方法.首先,基于NTCP模型的特点构建最大似然函数;然后,分别采用确定性优化方法和随机性优化方法对最大似然函数进行优化,分析优化过程的时间成本及优化结果,探讨用于拟合NTCP模型参数的最优方法.实验结果表明,用于拟合NTCP模型参数的最大似然函数是非凸的,存在局部最优解;遗传算法是一种最稳定的最大似然函数优化方法,其运行时间比模拟退火算法短,而且可以在每次优化结束后给出全局最优解,以作为NTCP模型参数.所提方法可以帮助肿瘤放疗工作者在临床随访数据的基础上建立具有群体特异性的放疗并发症预测模型.
Abstract:
To establish the population specific NTCP(normal tissue complication probability)prediction model in radiation oncology, a parameter fitting method is proposed. First, the maximum likelihood function is constructed based on the characteristic of the NTCP model. Then, the deterministic optimization method and the stochastic optimization method are used to optimize the maximum likelihood function, respectively. The time cost and the optimization results are analyzed to find the better method for fitting the parameters of the NTCP model. The experimental results show that the maximum likelihood function for fitting the parameters of the NTCP model is non-convex, indicating that there exist the local optimal solutions. The genetic algorithm is the most stable optimization algorithm for fitting the NTCP model, and the running time is less than that of the simulated annealing algorithm. In this algorithm, the global optimal solutions, which are regarded as the parameters of the NTCP model, can be obtained after each optimization. The proposed method can help the researchers in radiation oncology establish the population specific NTCP predictive models based on clinical follow-ups.

参考文献/References:

[1] Tucker S L, Li M, Xu T, et al. Incorporating single-nucleotide polymorphisms into the Lyman model to improve prediction of radiation pneumonitis[J]. Int J Radiat Oncol Biol Phys, 2013, 85(1): 251-257.
[2] Strigari L, Pedicini P, D’Andrea M, et al. A new model for predicting acute mucosal toxicity in head-and-neck cancer patients undergoing radiotherapy with altered schedules[J]. Int J Radiat Oncol Biol Phys, 2012, 83(5): e697-e702.
[3] Gulliford S L, Partridge M, Sydes M R, et al. Parameters for the Lyman Kutcher Burman(LKB)model of normal tissue complication probability(NTCP)for specific rectal complications observed in clinical practise[J]. Radiotherapy and Oncology, 2012, 102(3): 347-351.
[4] Fellin F, Azzeroni R, Maggio A, et al. Helical tomotherapy and intensity modulated proton therapy in the treatment of dominant intraprostatic lesion: a treament planning comparison[J]. Radiotherapy and Oncology, 2013, 107(2): 207-212.
[5] Amin N P, Miften M, Thornton D, et al. Effect of induction chemotherapy on estimated risk of radiation pneumonitis in bulky non-small cell lung cancer[J]. Medical Dosimetry, 2013, 38(3): 320-326.
[6] de Sanctis V, Bolzan C, D’Arienzo M, et al. Intensity modulated radiotherapy in early stage Hodgkin lymphoma patients: is it better than three dimensional conformal radiotherapy?[J]. Radiation Oncology, 2012, 7: 129-1-129-9.
[7] Zhu J, Zhang Z C, Li B S, et al. Analysis of acute radiation-induced esophagitis in non-small-cell lung cancer patients using the Lyman NTCP model[J]. Radiotherapy and Oncology, 2010, 97(3): 449-454.
[8] 朱健,李宝生,舒华忠,等.正常组织并发症概率模型综述[J].中国生物医学工程学报,2014,33(2):233-240.
　　Zhu Jian, Li Baosheng, Shu Huazhong, et al. Review of normal tissues complication probability models[J]. Chinese Journal of Biomedical Engineering, 2014, 33(2): 233-240.(in Chinese)
[9] 袁亚湘,孙文瑜.最优化理论与方法[M].北京:科学出版社,2001:50-51.
[10] Zhu J, Simon A, Ospina J D, et al. Predictive models of bladder toxicity in prostate cancer radiotherapy[J]. Eur J Cancer, 2011, 47(S1): S486.

备注/Memo

备注/Memo:
收稿日期: 2014-10-01.
作者简介: 朱健(1980—),男,博士,助理研究员;李宝生(联系人),男,博士,研究员,博士生导师,baoshli@yahoo.com.
基金项目: 国家自然科学基金资助项目(61271312,81272501,81301298)、国家重点基础研究发展计划(973计划)资助项目(2011CB707904).
引用本文: 朱健,白曈,李宝生,等.肿瘤放疗并发症概率预测模型参数拟合方法[J].东南大学学报:自然科学版,2015,45(2):256-259. [doi:10.3969/j.issn.1001-0505.2015.02.011]
更新日期/Last Update: 2015-03-20