Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network

被引:31
|
作者
Sun, W. Z. [1 ,2 ]
Jiang, M. Y. [1 ]
Ren, L. [2 ]
Dang, J. [3 ]
You, T. [3 ]
Yin, F-F [2 ]
机构
[1] Shandong Univ, Inst Informat Sci & Engn, Jinan, Shandong, Peoples R China
[2] Duke Univ, Dept Radiat Oncol, Ctr Canc, Durham, NC 27708 USA
[3] Jiangsu Univ, Dept Radiat Oncol, Affiliated Hosp, Zhenjiang, Jiangsu, Peoples R China
来源
PHYSICS IN MEDICINE AND BIOLOGY | 2017年 / 62卷 / 17期
基金
美国国家卫生研究院;
关键词
radiation therapy; dynamic tracking; artificial neural network; respiratory motion prediction; multi-layer perceptron neural network; BREATH-HOLD; TUMOR TRACKING; MOTION; MODEL; LUNG; AVERAGE; FILTER;
D O I
10.1088/1361-6560/aa7cd4
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
To improve the prediction accuracy of respiratory signals using adaptive boosting and multi-layer perceptron neural network (ADMLP-NN) for gated treatment of moving target in radiation therapy. The respiratory signals acquired using a real-time position management (RPM) device from 138 previous 4DCT scans were retrospectively used in this study. The ADMLP-NN was composed of several artificial neural networks (ANNs) which were used as weaker predictors to compose a stronger predictor. The respiratory signal was initially smoothed using a Savitzky-Golay finite impulse response smoothing filter (S-G filter). Then, several similar multi-layer perceptron neural networks (MLP-NNs) were configured to estimate future respiratory signal position from its previous positions. Finally, an adaptive boosting (Adaboost) decision algorithm was used to set weights for each MLP-NN based on the sample prediction error of each MLP-NN. Two prediction methods, MLP-NN and ADMLP-NN (MLP-NN plus adaptive boosting), were evaluated by calculating correlation coefficient and root-mean-square-error between true and predicted signals. For predicting 500ms ahead of prediction, average correlation coefficients were improved from 0.83 (MLP-NN method) to 0.89 (ADMLP-NN method). The average of root-mean-square-error (relative unit) for 500ms ahead of prediction using ADMLP-NN were reduced by 27.9%, compared to those using MLP-NN. The preliminary results demonstrate that the ADMLP-NN respiratory prediction method is more accurate than the MLP-NN method and can improve the respiration prediction accuracy.
引用
收藏
页码:6822 / 6835
页数:14
相关论文
共 50 条
  • [1] Respiratory Signal Prediction Based on Adaptive Boosting and Multilayer Perceptron Neural Network
    Sun, W.
    Yin, F. F.
    Jiang, M.
    Dang, J.
    You, T.
    INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2016, 96 (02): : E702 - E702
  • [2] Adaptive respiratory signal prediction using dual multi-layer perceptron neural networks
    Sun, Wenzheng
    Wei, Qichun
    Ren, Lei
    Dang, Jun
    Yin, Fang-Fang
    PHYSICS IN MEDICINE AND BIOLOGY, 2020, 65 (18):
  • [3] Respiratory Signal Prediction Based On Multi-Layer Perceptron Neural Network Using Adjustable Training Samples
    Sun, W.
    Jiang, M.
    Yin, F.
    MEDICAL PHYSICS, 2016, 43 (06) : 3354 - 3355
  • [4] Hybrid neural network model based on multi-layer perceptron and adaptive resonance theory
    Gavrilov, Andrey
    Lee, Young-Koo
    Lee, Stlngyoung
    ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 707 - 713
  • [5] Hybrid neural network based on models of multi-layer perceptron and adaptive resonance theory
    Gavrilov, AV
    Korus 2005, Proceedings, 2005, : 604 - 606
  • [6] Multi-Layer Perceptron Based Spectrum Prediction in Cognitive Radio Network
    Amit Kumar Singh
    Rakesh Ranjan
    Wireless Personal Communications, 2022, 123 : 3539 - 3553
  • [7] Multi-Layer Perceptron Based Spectrum Prediction in Cognitive Radio Network
    Singh, Amit Kumar
    Ranjan, Rakesh
    WIRELESS PERSONAL COMMUNICATIONS, 2022, 123 (04) : 3539 - 3553
  • [8] A Study on Single and Multi-layer Perceptron Neural Network
    Singh, Jaswinder
    Banerjee, Rajdeep
    PROCEEDINGS OF THE 2019 3RD INTERNATIONAL CONFERENCE ON COMPUTING METHODOLOGIES AND COMMUNICATION (ICCMC 2019), 2019, : 35 - 40
  • [9] Thermal Conductivity Prediction of Pure Liquids Using Multi-Layer Perceptron Neural Network
    Najafi, Alireza
    Hamzehie, Mohammad Ehsan
    Najibi, Hesam
    Soleimani, Mohammad
    Van Gerven, Tom
    Van der Bruggen, Bart
    Mazinani, Saeed
    JOURNAL OF THERMOPHYSICS AND HEAT TRANSFER, 2015, 29 (01) : 197 - 202
  • [10] Emotional temporal difference learning based multi-layer perceptron neural network application to a prediction of solar activity
    Rashidi, F
    Rashidi, M
    ROUGH SETS AND CURRENT TRENDS IN COMPUTING, 2004, 3066 : 685 - 690