北京生物醫(yī)學(xué)工程

基于深度學(xué)習(xí)方法的放療患者擺位誤差預(yù)測(cè)

Prediction of setup errors for patients treated with radiotherapy based on deep learning method

作者：高翔宋雙張偉陳妙然夏宇曹征

單位：合肥市第一人民醫(yī)院血液腫瘤科(合肥 230001)<p>通信作者:曹征,高級(jí)工程師 E-mail:caozheng81@ 126.com</p>

關(guān)鍵詞：深度學(xué)習(xí); 放療; 擺位誤差; 錐形束 CT; 預(yù)測(cè)

分類號(hào)：R318.6; R815.6

出版年·卷·期（頁(yè)碼）：2020·39·2（380-388）

摘要：

目的為了實(shí)現(xiàn)對(duì)放療患者日常擺位誤差的準(zhǔn)確預(yù)測(cè),優(yōu)化錐形束計(jì)算機(jī)斷層掃描( cone beam computed tomography,CBCT)使用頻率,確保患者擺位誤差處在允許范圍內(nèi)的同時(shí)盡可能減少其承受的額外輻射劑量,本研究基于深度學(xué)習(xí)方法能夠?qū)?fù)雜體系進(jìn)行預(yù)測(cè)的能力,構(gòu)建了一種深度全連接神經(jīng)網(wǎng)絡(luò)? 方法選取 20 名頭頸部腫瘤患者累積共 76 次 CBCT 掃描結(jié)果作為研究對(duì)象? 首先,根據(jù)文獻(xiàn)調(diào)研及臨床實(shí)踐經(jīng)驗(yàn),確定患者日常治療時(shí)的擺位誤差受到不同技術(shù)人員的工作經(jīng)驗(yàn)?患者體型?固定膜的松緊程度?靶區(qū)位置?靶區(qū)大小及形狀等因素的影響,且與患者前三次治療時(shí)的擺位誤差相關(guān)性較強(qiáng),因此針對(duì)患者每次 CBCT 掃描得到的擺位誤差,從患者的治療記錄及患者 CT 圖像中獲得相關(guān)信息,得到 467 個(gè)特征值作為深度學(xué)習(xí)的輸入值,以三個(gè)方向上最大擺位誤差的分類作為深度學(xué)習(xí)的輸出值,將每次擺位誤差的最大值以 3 mm 為標(biāo)準(zhǔn)分為兩類,作為深度學(xué)習(xí)的目標(biāo)值? 然后,將研究數(shù)據(jù)按7 ∶ 3 的比例隨機(jī)劃分為訓(xùn)練集和驗(yàn)證集,通過(guò)訓(xùn)練集訓(xùn)練深度神經(jīng)網(wǎng)絡(luò),再使用驗(yàn)證集對(duì)神經(jīng)網(wǎng)絡(luò)進(jìn)行初步評(píng)估? 在完成深度神經(jīng)網(wǎng)絡(luò)的訓(xùn)練后,將正在治療中的新患者的數(shù)據(jù)作為測(cè)試集,使用訓(xùn)練好的神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)新患者的擺位誤差大小,并與實(shí)際結(jié)果對(duì)比,評(píng)估其準(zhǔn)確率? 最后,進(jìn)行重復(fù)實(shí)驗(yàn),判斷神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)結(jié)果是否具有可重復(fù)性? 結(jié)果本研究構(gòu)建的深度神經(jīng)網(wǎng)絡(luò)對(duì)患者擺位誤差的預(yù)測(cè)準(zhǔn)確率可以達(dá)到 86%,能準(zhǔn)確預(yù)測(cè)患者擺位誤差大于 3 mm 的情況,且預(yù)測(cè)結(jié)果的可重復(fù)性好? 結(jié)論基于深度學(xué)習(xí)方法可以較準(zhǔn)確地預(yù)測(cè)放療患者日常擺位誤差的最大絕對(duì)值是否大于 3 mm,為優(yōu)化 CBCT 掃描頻率提供了可靠依據(jù),有助于提高放療療效,減輕放療副反應(yīng),具有良好的臨床應(yīng)用價(jià)值?

Objective By accurately predicting the daily setup errors of each radiotherapy patient, the use of cone beam computed tomography (CBCT) could be optimized to reduce the risks of additional radiation exposure for the patients. For this purpose, a deep fully connected neural network was proposed in this paper. Methods A total of 76 CBCT results from different patients with head and neck tumors were selected for this study and. First, based on literature research and clinical practice experience, it was determined that the setup errors of patients during daily treatment were affected by the work experience of different technicians, the patients’ body shape, the tightness of the fixed membranes, the locations, the sizes and shapes of the tumors. And it had a strong correlation with the setup errors during the first three treatments of the patients. Therefore, for each CBCT verification result of the patients, relevant information was obtained from the patients’ treatment records and the patients’ CT images, and 467 characteristic values were obtained. A set of 467 feature values was used as the input values of deep learning, and the maximum values of the setup errors in three directions were used as the output values. The maximum value of each setup error was divided into two categories with the standard of 3 mm as the label for deep learning. Then, the research data was randomly divided into a training set and a validation set according to the ratio of 7:3. The deep neural network was trained by the training set, and evaluated by the validation set. After completing the training of the neural network, the data of new patients were used as the test set. The trained neural network and test set were used to predict the daily setup errors of new patients, and the results were compared with the actual results to evaluate its prediction accuracy. Finally, repeated experiments were performed to determine whether the training and prediction results of the neural network were repeatable. Results The prediction accuracy of the patient’s setup errors in this study could reach 86%. The situation that the patients’ setup errors would be greater than 3 mm could be accurately predicted. The test results were reproducible. Conclusions Based on deep learning method, whether the maximum absolute value of the daily setup errors of radiotherapy patients would be greater than 3mm could be accurately predicted, and the accuracy could reach 86%.This study could help departments optimize the frequency of the using of CBCT, improve the efficacy, reduce the side effects of radiotherapy and have good clinical application value.

參考文獻(xiàn)：

[ 1 ] 戴建榮, 胡逸民. 圖像引導(dǎo)放療的實(shí)現(xiàn)方式[J]. 中華放射腫瘤學(xué)雜志, 2006, 15(2):132-135.

Dai JR, Hu YM. Image guided radiotherapy implementation[ J]. Chinese Journal of Radiation Oncology, 2006, 15(2):132-135.

[ 2 ] Kim J, Fessler JA, Lam KL, et al. A feasibility study of mutual information based setup error estimation for radiotherapy [ J ]. Medical Physics, 2001, 28(12):2507-2517.

[ 3 ] Sykes JR, Lindsay R, Iball G, et al. Dosimetry of CBCT: methods, doses and clinical consequences [ J ]. Journal of Physics:Conference Series, 2013, 444:012017.

[ 4 ] Altunbas C, Zheng D, Weiss E, et al. SU - FF - T - 490: the effect of daily cone beam CT imaging dose on the secondary cancer risk for patients receiving prostate IMRT treatments[ J]. Medical Physics, 2009, 36(6Part16):2636.

[ 5 ] Spezi E, Downes P, Jarvis R, et al. Patient-specific three-dimensional concomitant dose from cone beam computed tomography exposure in image-guided radiotherapy [ J ]. International Journal of Radiation Oncology? Biology? Physics, 2012, 83(1):419-426.

[ 6 ] 吳潤(rùn)葉, 高黎, 李明輝, 等. 應(yīng)用非每日錐形束 CT 校位減少擺位誤差對(duì)鼻咽癌調(diào)強(qiáng)放療劑量影響[ J]. 中華放射腫瘤學(xué)雜志, 2011, 20(5):379-383.

Wu RY, Gao L, Li MH, et al. Using non-daily cone-beam computed tomography reduce dosimetric effect of set-up errors in intensity-modulated radiotherapy for nasopharyngeal cancer [ J]. Chinese Journal of Radiation Oncology, 2011, 20(5):379-383.

[ 7 ] 孔玲玲, 程健, 李寶生, 等. 保留乳房術(shù)后放療錐形束 CT 引導(dǎo)系統(tǒng)擺位誤差預(yù)測(cè)的可行性研究[J]. 中華腫瘤防治雜志,2013, 20(12):949-952.

Kong LL, Cheng J, Li BS, et al. Feasibility study of systematic setup error prediction for breast irradiation after breast-conserving therapy based on cone-beam CT setup verification[ J]. Chinese Journal of Cancer Prevention and Treatment, 2013, 20 ( 12): 949-952.

[ 8 ] 王瑋, 李建彬, 徐敏, 等. 錐形束 CT 引導(dǎo)全乳調(diào)強(qiáng)放療擺位誤差自適應(yīng)的預(yù)測(cè)與校正[ J]. 中華腫瘤雜志, 2016, 38 (3):197-201.

Wang W, Li JB, Xu M, et al. Cone beam CT-derived adaptive radiotherapy for setup error assessment and correction in whole breast intensity modulated radiotherapy [ J]. Chinese Journal of Oncology, 2016, 38(3):197-201.

[ 9 ] 李慶, 尹龍斌, 謝慧輕, 等. 鼻咽癌調(diào)強(qiáng)放療中擺位誤差的變化趨勢(shì):基于千伏級(jí)錐形束 CT 的前瞻性研究[ J]. 放射學(xué)實(shí)踐, 2017, 32(8):870-875.

Li Q, Yin LB, Xie HQ, et al. Trends of inter-fractional setup errors in intensity-modulated radiotherapy for nasopharyngeal carcinoma: a prospective study based on kilovoltage cone-beam computed tomography[ J]. Radiologic Practice, 2017, 32( 8): 870-875.

[10] 丘敏敏, 鐘嘉健, 歐陽(yáng)斌, 等. 基于高斯混合模型 Varian NovalisTX 直線加速器盆腔腫瘤放療擺位誤差分布預(yù)測(cè)模型的構(gòu)建[ J]. 中山大學(xué)學(xué)報(bào)(醫(yī)學(xué)科學(xué)版), 2019, 40 ( 2):284-290.

Qiu MM, Zhong JJ, Ouyang B, et al. Set-up errors distribution prediction model for pelvic tumors radiotherapy of Varian NovalisTX medical linear accelerator based on gaussian mixtures [ J]. Journal of Sun Yat-sen University ( Medical Sciences), 2019, 40(2):284-290.

[11] Bengio Y. Learning deep architectures for AI [ J]. Foundations and Trends ? in Machine Learning, 2009, 2(1):1-127.

[12] 張方圓, 郁蕓, 趙宇, 等. 人工神經(jīng)網(wǎng)絡(luò)在臨床醫(yī)學(xué)中的應(yīng)用[J]. 北京生物醫(yī)學(xué)工程, 2016, 35(4):422-428.

Zhang FY, Yu Y, Zhao Y, et al. Application of artificial neural network in clinical medicine [ J ]. Beijing Biomedical Engineering, 2016, 35(4):422-428.

[13] Spencer M, Eickholt J, Cheng J. A deep learning network approach to ab initio protein secondary structure prediction[ J]. IEEE / ACM Transactions on Computational Biology & Bioinformatics, 2015, 12(1):103-112.

[14] 李偉, 楊金才, 黃牛. 深度學(xué)習(xí)在藥物設(shè)計(jì)與發(fā)現(xiàn)中的應(yīng)用[J]. 藥學(xué)學(xué)報(bào), 2019, 54(5):761-767.

Li W, Yang JC, Huang N. Deep learning in drug design and discovery [ J ]. Acta Pharmaceutica Sinica, 2019, 54 ( 5 ):761-767.

[15] Ayachi R, Afif M, Said Y, et al. Traffic signs detection for real-world application of an advanced driving assisting system using deep learning [ J]. Neural Processing Letters, 2020, 51 ( 1): 837-851.

[16] Sezer OB, Ozbayoglu AM. Algorithmic financial trading with deep convolutional neural networks: time series to image conversion approach [ J]. Applied Soft Computing, 2018, 70: 525-538.

[17] 鄧金城, 彭應(yīng)林, 劉常春, 等. 深度卷積神經(jīng)網(wǎng)絡(luò)在放射治療計(jì)劃圖像分割中的應(yīng)用[ J]. 中國(guó)醫(yī)學(xué)物理學(xué)雜志, 2018,35(6):621-627.

Deng JC, Peng YL, Liu CC, et al. Application of deep convolution neural network in radiotherapy planning image segmentation[J].Chinese Journal of Medical Physics, 2018, 35 (6):621-627.

[18] 王燃. 基于深度學(xué)習(xí)的胸腹部腫瘤呼吸運(yùn)動(dòng)的實(shí)時(shí)跟蹤方法研究[D]. 深圳:中國(guó)科學(xué)院深圳先進(jìn)技術(shù)研究院, 2019.

Wang R. Deep learning in real-time tracking method for respiratory motion of thoracic and abdominal tumors [ D ]. Shenzhen:Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 2019.

[19] Dinkla AM, Wolterink JM, Maspero M, et al. MR-only brain radiation therapy:dosimetric evaluation of synthetic CTs generated by a dilated convolutional neural network [ J ]. International Journal of Radiation Oncology*Biology*Physics, 2018, 102 (4):801-812.

[20] Ibragimov B, Toesca DAS, Yuan Y, et al. Neural networks for deep radiotherapy dose analysis and prediction of liver SBRT outcomes [ J ]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(5):1821-1833.

[21] Keras. The Python deep learning library [EB / OL]. (2019-11-6)[2019-11-15] https: / / keras.io / .

[22] 覃光華, 丁晶, 陳彬兵. 預(yù)防過(guò)擬合現(xiàn)象的人工神經(jīng)網(wǎng)絡(luò)訓(xùn)練策略及其應(yīng)用[J]. 長(zhǎng)江科學(xué)院院報(bào), 2002, 19(3):59-61.

Qin GH, Ding J, Chen BB. Learning strategies of artificial neural networks for preventing over-training and their application [ J]. Journal of Yangtze River Scientific Research Institute, 2002, 19 (3):59-61.

[23] Lin S, Pan J, Han L, et al. Nasopharyngeal carcinoma treated with reduced-volume intensity-modulated radiation therapy:report on the 3-year outcome of a prospective series[ J]. International Journal of Radiation Oncology*Biology*Physics, 2009, 75 (4):1071-1078.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)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