北京生物醫(yī)學(xué)工程

基于小波分解和神經(jīng)網(wǎng)絡(luò)的呼吸運(yùn)動(dòng)預(yù)測算法

Respiratory motion prediction based on wavelet and neural network

作者：黃姍姍杜宏偉

單位：中國科學(xué)技術(shù)大學(xué) (合肥2300271)

關(guān)鍵詞：呼吸運(yùn)動(dòng)；預(yù)測算法；小波神經(jīng)網(wǎng)絡(luò)

分類號：R318.04

出版年·卷·期（頁碼）：2016·35·4（381-388）

摘要：

目的放射治療是胸腹部腫瘤治療的常用手段，但呼吸等運(yùn)動(dòng)大大影響了放射治療的準(zhǔn)確性，因此精確的呼吸運(yùn)動(dòng)定位和預(yù)測對腫瘤治療很有必要。相關(guān)預(yù)測方法缺乏對系統(tǒng)長延遲預(yù)測的研究，本文提出一種用小波分解結(jié)合Elman神經(jīng)網(wǎng)絡(luò)的算法（wavelet Elman network,WEN）預(yù)測呼吸運(yùn)動(dòng)。方法采用光學(xué)定位系統(tǒng)采集數(shù)據(jù)，對數(shù)據(jù)進(jìn)行簡單的預(yù)處理，再利用小波分解壓縮數(shù)據(jù)，訓(xùn)練Elman神經(jīng)網(wǎng)絡(luò)，最后進(jìn)行神經(jīng)網(wǎng)絡(luò)的預(yù)測。預(yù)測結(jié)果和真實(shí)值對比，繪制誤差曲線，計(jì)算均方根誤差，并與其他主流算法對比，驗(yàn)證算法的可行性。結(jié)果 WEN算法在短延遲預(yù)測中表現(xiàn)一般，但當(dāng)延遲達(dá)1000ms時(shí)，WEN算法的均方根誤差平均為1.6164mm，比臨床中使用的線性預(yù)測低32.9%。結(jié)論通過實(shí)驗(yàn)驗(yàn)證了基于小波分解和Elman神經(jīng)網(wǎng)絡(luò)的呼吸運(yùn)動(dòng)預(yù)測算法，在長延遲時(shí)表現(xiàn)較好，證明了本算法的正確性及可行性。

Objective One of the common treatments for cancer of the chest and abdomen is radiation therapy,yet respiratory movement reduces the quality of radiation therapy.Therefore,the precise positioning and prediction of respiratory movement are essential in radiation therapy.An algorithm for predicting respiratory movement is proposed based on wavelet and Elman network since there is a lack of research on long delays in prediction.Methods First,we collected data by optical positioning system,pre-processed the data,then compressed data by wavelet,trained Elman network,and predicted the neural network.With the comparison of predictions and actual values,we drew error curve,calculated the root mean square error,and compared with the other major algorithms to validate the feasibility.Results The performance of WEN in short delays was not very well,when the delay came to 1000ms,the average of WEN’s RMSE (root mean square error) was 1.6164mm,32.9% less than linear prediction used in clinical.Conclusions The experiments demonstrated that the respiratory motion prediction based on wavelet and Elman network performed well in the long delays,and all the results demonstrated the validity and feasibility of the algorithm.

參考文獻(xiàn)：

［1］Vedam SS, Keall PJ, Docef A, et al. Predicting respiratory motion for four-dimensional radiotherapy［J］. Med Phys, 2004，31(8):2274-2283.

［2］Murphy MJ, Dieterich S. Comparative performance of linear and nonlinear neural networks to predict irregular breathing［J］. Phys Med Biol, 2006，51(22):5903-5914.

［3］Sharp GC, Jiang SB, Shimizu S, et al. Prediction of respiratory tumour motion for real-time image-guided radiotherapy［J］. Phys Med Biol, 2004, 49(3):425-440.

［4］Kakar M, Nystrm H, Aarup LR, et al. Respiratory motion prediction by using the adaptive neuro fuzzy inference system (ANFIS) ［J］. Phys Med Biol, 2005, 50(19):4721-4728.

［5］Ramrath L, Schlaefer A, Ernst F, et al. Prediction of respiratory motion with a multi-frequency based Extended Kalman Filter［J］. IJCARS, 2007, 2:56-58.

［6］Isaksson M, Jalden J, Murphy MJ. On using an adaptive neural network to predict lung tumor motion during respiration for radiotherapy applications［J］. Med Phys, 2005, 32(12):3801-3809.

［7］Goodband JH, Haas OCL, Mills JA. A comparison of neural network approaches for on-line prediction in IGRT［J］. Med Phys, 2008, 35(3):1113-1122.

［8］Riaz N, Shanker P, Wiersma R, et al. Predicting respiratory tumor motion with multi-dimensional adaptive filters and support vector regression［J］. Phys Med Biol, 2009, 54(19):5735-5748.

［9］Ingrid Daubechies. 李建平, 楊萬年, 譯. 小波十講［M］. 北京: 國防工業(yè)出版社, 2004.

［10］史峰，王小川，郁磊，等. MATLAB神經(jīng)網(wǎng)絡(luò)30個(gè)案例分析［M］. 北京:北京航空航天大學(xué)出版社，2010.

［11］虞和濟(jì)，陳長征，張省. 基于神經(jīng)網(wǎng)絡(luò)的智能診斷［M］. 北京：冶金工業(yè)出版社，2000.

［12］Verma, Poonam S. Survey: real-time tumor motion prediction for image-guided radiation treatment［J］. Computing in Science and Engineering, 2011, 13(5): 24-35.

［13］Riaz N, Shanker P, Wiersma R, et al. Preidicting respiratory tumor motion with multi-dimensinal adaptive filters and support vector regression［J］. Phys Med Biol, 2009, 54(19):5735-5748.

［14］Suk Jin Lee, Yuichi Motai. Prediction and Classification of Respiratory Motion. Studies in Computational Intelligence［M］. Berlin:Springe, 2014.

［15］Ruan D, Keall P. Online prediction of respiratory motion: multidimensional processing with low-dimensional feature learning［J］. Phys Med Biol, 2010, 55(11), 3011-3025 .

［16］歐陽斌, 盧文婷, 竇建洪, 等. 基于非參數(shù)回歸的呼吸運(yùn)動(dòng)預(yù)測方法在實(shí)時(shí)跟蹤放療中的應(yīng)用［J］. 南方醫(yī)科大學(xué)學(xué)報(bào), 2011, 31(10): 1682-1686.

Ouyang Bin, Lu Wenting, Dou Jianhong, et al. Prediction of respiratory motion based on nonparametric regression for real-time tumor-tracking radiotherapy［J］. J South Med Univ, 2011, 31(10): 1682-1686.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频