Auxiliary diagnosis of heterogeneous data of Parkinson’s disease based on improved convolution neural network

Abstract

Parkinson’s disease (PD) is a kind of nervous system degenerative disease frequently occurring in the elderly over sixty years old. With the development of imaging technology, medical imaging has played a certain role in the diagnosis of Parkinson’s disease. The aim of the paper is to the diagnosis of Parkinson’s disease through deep learning. This paper selects the T2-MRI(T2-Magnetic Resonance Imaging) image and clinical data to diagnose Parkinson’s disease and integrates the heterogeneous data into the improved convolution neural network. In this paper, convolution neural network is added to the Gabor filter to make the whole convolution neural network have better effect; the activation function is improved and adjusted, which means the traditional sigmoid function and the tanh function are discarded, and the Relu activation function is used to improve the neural network. It is proved by experiments that the heterogeneous data diagnosis of T2-MRI image and clinical data (the accuracy is 77.9%) is better than the simple image data diagnosis (the accuracy is71.2%). For the same data, the improved convolution neural network is superior to the traditional network (the accuracy is 64.5%).

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25

References

  1. 1.

    Alzubi J, Nayyar A, Kumar A (2018) Machine learning from theory to algorithms: an overview [C]//journal of physics: conference series. IOP Publishing 1142(1):012012

    Google Scholar 

  2. 2.

    Cheng Y, Huifang S (2017) Interpretation of 2016 Chinese PD diagnostic criteria [J]. Chinese Journal of Practical Internal Medicine 37(02):124–126

    Google Scholar 

  3. 3.

    Zhao Dan, Mao Chuan-Wan, Huang Jianhe 2010, et al. A magnetic resonance imaging study of the pars Compacta of Substantia Nigra in PD [J]. Chin J Clin Neurosci, 18(2):130–134.

  4. 4.

    Li Dan, Shen Xiajiong, Zhang Haixiang 2016, et al. Improved convolutional neural network based on Lenet-5[J]. Computer Era (08):4–12.

  5. 5.

    Fang Y, Gang Y, Jun X (2014) Meta analysis of risk factors and protective factors for Parkinson disease in Chinese population [J]. Clin Neurol 27(02):111–115

    Google Scholar 

  6. 6.

    Huang Haidong, Deng Jinglan, Huan Yi 2004, et al. The application of measurement of the width of pars Compacta of Substantia Nigra in differential diagnosis on Parkinson’ s disease and vascular parkinsonism on MRI [J]. Clin Neurol, 17(01):11–13.

  7. 7.

    Li Jianchuan, Qin Guojun, Wen Xisen 2002, et al. Over-fitting in neural network learning algorithms and its solving strategies [J]. Journal of Vibration, Measurement & Diagnosis, 22(04):260–264.

  8. 8.

    Feng Jieying, Huang Biao, Zhong Xiaoling 2013, et al. Imaging diagnosis of PD and Parkinson's superposition syndrome [J]. Radio Practice, 28(11):1105–1108.

  9. 9.

    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks [C]//Advances in neural information processing systems, pp 1097–1105

    Google Scholar 

  10. 10.

    Lakshmi C et al (2019) A secure reversible data hiding system for embedding EPR in medical images. Curr. Signal Transduction Ther. 14:1

    Article  Google Scholar 

  11. 11.

    Leshno M, Lin VY, Pinkus A, Schocken S (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function [J]. Neural Netw 6(6):861–867

    Article  Google Scholar 

  12. 12.

    Mehrotra R, Namuduri KR, Ranganathan N (1992) Gabor filter-based edge detection [J]. Pattern Recogn 25(12):1479–1494

    Article  Google Scholar 

  13. 13.

    Polesel A, Ramponi G, Mathews VJ (2000) Image enhancement via adaptive unsharp masking [J]. IEEE Trans Image Process 9(3):505–510

    Article  Google Scholar 

  14. 14.

    Quanhua Z, Gao J, Li Y (2015) Multi-feature texture image segmentation based on tessellation technique [J]. Chin J Sci Instrum 36(11):2519–2530

    Google Scholar 

  15. 15.

    Suh MH, Zangwill LM, Manalastas PIC, Belghith A, Yarmohammadi A, Medeiros FA, Diniz-Filho A, Saunders LJ, Weinreb RN (2016) Deep retinal layer microvasculature dropout detected by the optical coherence tomography angiography in glaucoma [J]. Ophthalmology 123(12):2509–2518

    Article  Google Scholar 

  16. 16.

    Vinoj PG, Jacob S, Menon VG, Rajesh S, Khosravi MR (2019) Brain-controlled adaptive lower limb exoskeleton for rehabilitation of post-stroke paralyzed [J]. IEEE Access 7:132628–132648

    Article  Google Scholar 

  17. 17.

    Wang F (2016) Research and Applications Based The Improved Convolutional Neural Network [D]. Nanjing University of Posts and Telecommunications, Nanjing

    Google Scholar 

  18. 18.

    Zhang Wen-qian, Su Hai-xia, Shang Lei 2017, et al. A comparative study on prediction of Alzheimer's disease progression based on BP and RBF neural network [J]. Progress in Modern Biomedicine, 17(04):738–741.

  19. 19.

    Xu Dongfeng, Lei Yi, Xia Jun 2018, et al. Diagnosis and imaging findings of PD [J]. Hainan Med, 29(03):381–384.

  20. 20.

    Yueqi Z, Wang G (2016) International movement disorders association new standard for clinical diagnosis of PD (2015)[J]. Diagn Concepts Pract 15(02):122–123

    Google Scholar 

Download references

Acknowledgments

The authors acknowledge the Foundation Research Funds for: 1.Youth Program of National Natural Science Foundation of China. “Key Technologies of Early Diagnosis of Alzheimer’s Disease based on Heterogeneous Data Fusion and Brain Network Construction.” (61902058). 2.The Fundamental Research Funds for the Central Universities. “Research on Key Technologies of Early Diagnosis of Encephalitis based on Heterogeneous Data Fusion.” (N2019002). 3.The Fundamental Research Funds for the Central Universities under Grant. (N2024005-2)

Author information

Affiliations

Authors

Corresponding author

Correspondence to Dai Yin.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Yin, D., Zhao, Y., Wang, Y. et al. Auxiliary diagnosis of heterogeneous data of Parkinson’s disease based on improved convolution neural network. Multimed Tools Appl (2020). https://doi.org/10.1007/s11042-020-08984-6

Download citation

Keywords

  • Parkinson’s disease
  • Heterogeneous data
  • Improved convolution neural network
  • Gabor filter