基于粒子群算法与反向传播神经网络的呼吸运动预测研究

doi:10.3969/j.issn.0258-8021.2018.06.010

Abstract
Figure/Table
References
Related Citation (8)

Download: PDF (1090 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Objective, Respiratory motion may cause the change of some organs and tissues, such as lung and liver tumors in radiation therapy, which may influence the treatment effect and increase the damage to normal tissues and organs. Hence, it is an essential work to estimate the real-time movement of target in radiation therapy. Method, BP-NN has been widely used in respiratory motion prediction due to its superior non-linear fitting capability. However, BP-NN is easy to fall into local minimum. Results, In this study a novel method using PSO to optimize the BP-NN was proposed to avoid its drawbacks and improve prediction accuracy. Firstly, the PSO method was used to select optimal initial weights and thresholds of neural network. Then, the optimal initial weights and thresholds was utilized to establish artificial neural network (ANN). Finally, the established PSO-NN was used to predict respiratory signals.The preliminary results of 11 patients demonstrate that the mean absolute error reduced from 0.24 to 0.18(25%) and the coefficient correlation increased from 0.82 to 0.86. Conclusion, The proposed method (PSO-NN)could reduce the risk of BP-NN falling into local optimum and has the ability of improving the prediction accuracy of BP-NN method.

Key words： respiration prediction particle swarm optimization(PSO) back propagation neural networks(BP-NN) radiotherapy

Received: 17 January 2017

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chang Panchun
	Yang Jimin
	Yang Juan
	You Tao

Cite this article:

Chang Panchun,Yang Jimin,Yang Juan, et al. Respiratory Signals Prediction based on Particle Swarm Optimization and Back Propagation Neural Networks[J]. Chinese Journal of Biomedical Engineering, 2018, 37(6): 714-719.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2018.06.010 OR http://cjbme.csbme.org/EN/Y2018/V37/I6/714

[1] 黄志业,陈武凡,周凌宏,等.基于GA-BP神经网络进行呼吸运动预测的研究[J].中国生物医学工程学报,2010,29(6):812-817.
[2] Partridgeb M, Treea A, Brocka J, et al. Improvement in tumor control probability with active breathing control and doseescalation: A modeling study[J]. Radiotherapy and Oncology, 2009, 91(3): 325-329.
[3] Liu Jicheng, Yan Suli, Qi Jianxun. A hybrid particle swarm optimization approach with neural network and set pair analysis for transmission network planning[J]. Cent South Univ Technol, 2008,15(S2):321-326.
[4] Wang Ping, Huang Zhenyi, Zhang Mingya, et al. Mechanical property prediction of strip model based on PSO-BP neural network[J]. International Journal of Iron and Steel Research,2008,15(3):87-91.
[5] 倪庆剑,邢汉承,张志政,等.粒子群优化算法研究进展[J].模式识别与人工智能, 2007,20(3):349-357.
[6] Santoro JP, Yorke E, Goodman KA, et al. From phase-based to displacement-based gating: a software tool to facilitate respiration-gated radiation treatment[J]. Journal of Applied Clinical Medical Physics,2009,10(4):132-141.
[12] Zhao Haijuan, Wang Jialong, Zong Weiguo. Prediction of the smoothed monthly mean sunspot numbers by means of radial basis function neural networks[J]. Chinese Journal of Geophysics-chinese Edition, 2002,51(1):31-35.
[13] Taha Z, Widiyati K. Artificial neural network for bearing defect detection based on acoustic emission[J]. International Journal of Advanced Manufacturing Technology, 2010,50(1-4):289-296.
[14] Ma Deyin, Liang Yanchun, Zhao Xiaoshe. Multi-BP expert system for fault diagnosis of power system[J].Advances in Materials Science and Engineering,2015,26(3):937-944.
[15] Kameyama K. Particle swarm optimization:A survey[J].IEICE Transactions on Information and Systems, 2009,E92D(7):1354-1361.
[16] 申哲,葛广英, 田存伟.浅析BP神经网络设计中的关键问题[J].科技信息,2011,6: 238-238.
[17] 张蕾,陈月辉,杨波.基于并行PSO的神经网络优化算法研究.计算机科学,2005,32(8):308-311.