Comparison of initial learning algorithms for long short-term memory method on real-time respiratory signal prediction

作者全名："Sun, Wenzheng; Dang, Jun; Zhang, Lei; Wei, Qichun"

作者地址："[Sun, Wenzheng; Wei, Qichun] Zhejiang Univ, Affiliated Hosp 2, Sch Med, Dept Radiat Oncol, Hangzhou, Zhejiang, Peoples R China; [Dang, Jun] Chinese Acad Med Sci & Peking Union Med Coll, Canc Hosp, Natl Canc Ctr, Natl Clin Res Ctr Canc,Dept Rad Oncol, Shenzhen, Guangdong, Peoples R China; [Dang, Jun] Chinese Acad Med Sci & Peking Union Med Coll, Shenzhen Hosp, Shenzhen, Guangdong, Peoples R China; [Dang, Jun] Chongqing Med Univ, Affiliated Hosp 1, Dept Oncol, Chongqing, Peoples R China; [Zhang, Lei] Duke Kunshan Univ, Grad Program Med Phys, Kunshan, Jiangsu, Peoples R China"

通信作者："Wei, QC (通讯作者)，Zhejiang Univ, Affiliated Hosp 2, Sch Med, Dept Radiat Oncol, Hangzhou, Zhejiang, Peoples R China."

来源：FRONTIERS IN ONCOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000922580800001

JCR分区：Q2

影响因子：3.5

年份：2023

卷号：13

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：respiratory signals prediction; initializer; long short-term memory; radiation therapy; He initializer; Glorot initializer; orthogonal initializer; narrow-normal initializer

摘要："AimThis study aimed to examine the effect of the weight initializers on the respiratory signal prediction performance using the long short-term memory (LSTM) model. MethodsRespiratory signals collected with the CyberKnife Synchrony device during 304 breathing motion traces were used in this study. The effectiveness of four weight initializers (Glorot, He, Orthogonal, and Narrow-normal) on the prediction performance of the LSTM model was investigated. The prediction performance was evaluated by the normalized root mean square error (NRMSE) between the ground truth and predicted respiratory signal. ResultsAmong the four initializers, the He initializer showed the best performance. The mean NRMSE with 385-ms ahead time using the He initializer was superior by 7.5%, 8.3%, and 11.3% as compared to that using the Glorot, Orthogonal, and Narrow-normal initializer, respectively. The confidence interval of NRMSE using Glorot, He, Orthogonal, and Narrow-normal initializer were [0.099, 0.175], [0.097, 0.147], [0.101, 0.176], and [0.107, 0.178], respectively. ConclusionsThe experiment results in this study indicated that He could be a valuable initializer in the LSTM model for the respiratory signal prediction."

基金机构：National Natural Science Foundation of China [62103366]; General Project of Chongqing Natural Science Foundation [cstc2020jcyj-msxm2928]; Duke Kunshan University Education Development Foundation [22KDKUF032]

基金资助正文："Funding This work was partially supported by the National Natural Science Foundation of China (62103366), the General Project of Chongqing Natural Science Foundation (grant cstc2020jcyj-msxm2928), and Duke Kunshan University Education Development Foundation (22KDKUF032)."