Skip to main content
Journal cover image

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

Publication ,  Journal Article
Sun, WZ; Jiang, MY; Ren, L; Dang, J; You, T; Yin, F-F
Published in: Phys Med Biol
August 3, 2017

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 500 ms 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 500 ms 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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Phys Med Biol

DOI

EISSN

1361-6560

Publication Date

August 3, 2017

Volume

62

Issue

17

Start / End Page

6822 / 6835

Location

England

Related Subject Headings

  • Retrospective Studies
  • Respiration
  • Radiotherapy Planning, Computer-Assisted
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Neoplasms
  • Movement
  • Humans
  • Algorithms
  • 5105 Medical and biological physics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Sun, W. Z., Jiang, M. Y., Ren, L., Dang, J., You, T., & Yin, F.-F. (2017). Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network. Phys Med Biol, 62(17), 6822–6835. https://doi.org/10.1088/1361-6560/aa7cd4
Sun, W. Z., M. Y. Jiang, L. Ren, J. Dang, T. You, and F. -. F. Yin. “Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network.Phys Med Biol 62, no. 17 (August 3, 2017): 6822–35. https://doi.org/10.1088/1361-6560/aa7cd4.
Sun WZ, Jiang MY, Ren L, Dang J, You T, Yin F-F. Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network. Phys Med Biol. 2017 Aug 3;62(17):6822–35.
Sun, W. Z., et al. “Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network.Phys Med Biol, vol. 62, no. 17, Aug. 2017, pp. 6822–35. Pubmed, doi:10.1088/1361-6560/aa7cd4.
Sun WZ, Jiang MY, Ren L, Dang J, You T, Yin F-F. Respiratory signal prediction based on adaptive boosting and multi-layer perceptron neural network. Phys Med Biol. 2017 Aug 3;62(17):6822–6835.
Journal cover image

Published In

Phys Med Biol

DOI

EISSN

1361-6560

Publication Date

August 3, 2017

Volume

62

Issue

17

Start / End Page

6822 / 6835

Location

England

Related Subject Headings

  • Retrospective Studies
  • Respiration
  • Radiotherapy Planning, Computer-Assisted
  • Nuclear Medicine & Medical Imaging
  • Neural Networks, Computer
  • Neoplasms
  • Movement
  • Humans
  • Algorithms
  • 5105 Medical and biological physics