本文關(guān)鍵詞： 腫瘤 放射治療 并發(fā)癥 NTCP模型　出處：《東南大學(xué)學(xué)報(bào)(自然科學(xué)版)》2015年02期 　論文類型：期刊論文

【摘要】：為了建立具有群體特異性的腫瘤放療NTCP預(yù)測(cè)模型,提出了一種模型參數(shù)擬合方法.首先,基于NTCP模型的特點(diǎn)構(gòu)建最大似然函數(shù);然后,分別采用確定性優(yōu)化方法和隨機(jī)性優(yōu)化方法對(duì)最大似然函數(shù)進(jìn)行優(yōu)化,分析優(yōu)化過(guò)程的時(shí)間成本及優(yōu)化結(jié)果,探討用于擬合NTCP模型參數(shù)的最優(yōu)方法.實(shí)驗(yàn)結(jié)果表明,用于擬合NTCP模型參數(shù)的最大似然函數(shù)是非凸的,存在局部最優(yōu)解;遺傳算法是一種最穩(wěn)定的最大似然函數(shù)優(yōu)化方法,其運(yùn)行時(shí)間比模擬退火算法短,而且可以在每次優(yōu)化結(jié)束后給出全局最優(yōu)解,以作為NTCP模型參數(shù).所提方法可以幫助腫瘤放療工作者在臨床隨訪數(shù)據(jù)的基礎(chǔ)上建立具有群體特異性的放療并發(fā)癥預(yù)測(cè)模型.
[Abstract]:In order to establish a population-specific NTCP prediction model for tumor radiotherapy, a model parameter fitting method is proposed. Firstly, the maximum likelihood function is constructed based on the characteristics of NTCP model, and then the maximum likelihood function is constructed. The deterministic optimization method and stochastic optimization method are used to optimize the maximum likelihood function respectively. The time cost and optimization results of the optimization process are analyzed, and the optimal method for fitting the parameters of the NTCP model is discussed. The experimental results show that, The maximum likelihood function used to fit the parameters of NTCP model is nonconvex and has a local optimal solution. Genetic algorithm is the most stable maximum likelihood function optimization method, and its running time is shorter than that of simulated annealing algorithm. After each optimization, the global optimal solution can be given as a parameter of NTCP model. The proposed method can help tumor radiotherapy workers to establish a group specific prediction model of radiotherapy complications on the basis of clinical follow-up data.
【作者單位】： 東南大學(xué)影像科學(xué)與技術(shù)實(shí)驗(yàn)室;山東省腫瘤防治研究院;雷恩第一大學(xué)信號(hào)與圖像實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61271312,81272501,81301298) 國(guó)家重點(diǎn)基礎(chǔ)研究發(fā)展計(jì)劃(973計(jì)劃)資助項(xiàng)目(2011CB707904)
【分類號(hào)】：R730.55

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 朱健;李寶生;舒華忠;白f，

本文編號(hào)：1512117