| Peer-Reviewed

Medical Images Classification and Diagnostics Using Fuzzy Neural Networks

Received: 23 July 2019     Accepted: 19 August 2019     Published: 9 September 2019
Views:       Downloads:
Abstract

The problem of medical images of cervix epithelium classification for express diagnostics is considered…The following states of cervix epithelium are to be recognized and classified: normal state - columnar epithelium; squamous epithelium (normal state); metaplasia-benign changes of cervix uterus epithelium; CIN1-displasia of light degree, CIN 2-displasia of middle degree, CIN 3-displasia of high degree- intra-epithelium cancer: For its solution the application of fuzzy neural network (FNN NEFClass M) is suggested. The application of FNN is grounded by its following properties: it may work with fuzzy and qualitative information; it has accelerated convergence as compared with crisp classification methods; it enables to attain better classification accuracy than conventional classifiers. The structure of FNN NEFClass and its model description are presented. Training algorithm stochastic gradient descent for membership functions of fuzzy sets is considered and implemented. Data set of medical images of cervix epithelium which was obtained by special device colposcope is described and some images are presented. The experimental investigations of FNN NEFClass application for medical images recognition on real data are carried out, the results are presented. The comparison with NN Back Propagation, RBF NN and cascade RBF NN was made and estimation of efficiency of the suggested approach was performed. The problem of reduction of features number in classification tasks using principal component method (PCM) method is considered and implemented.

Published in American Journal of Neural Networks and Applications (Volume 5, Issue 2)
DOI 10.11648/j.ajnna.20190502.11
Page(s) 45-50
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Medical Images Classification, Medical Diagnostics, FNN NEFClass, Training, Cascade RBFNN, Features Selection, PCM

References
[1] Doyle, S. Agner, A. Madabhushi, M. Feldman, and J. Tomaszewski, “Automated grading of breast cancer histopathology using spectral clustering with textural and architectural image features,” in Proceedings of the 5th IEEE International Symposium on Biomedical Imaging (ISBI): From Nano to Macro, vol. 61. IEEE, May 2008, pp. 496-499.
[2] Y. Le Cun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436-444, 2015.
[3] Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in NeuralInformation Processing Systems 25, 2012, pp. 1097-1105.
[4] Jianpeng Zhang, Yong Xia, Qi Wu, Yutong Xie. Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning, Xiv:1706.09092v1 [cs. CV] 28 Jun 2017.
[5] Nilanjan Dey. Classification Technologies Techniques for Medical ImageAnalysis and Computer-aided Diagnosis, Volume 14, 1st Edition.-Academic Press, 201.-218 p.
[6] Yin, Xiao-Xia, Hadjiloucas, Sillas, Zhang, Yanchun. Pattern Classification of Medical Images: Computer Aided Diagnosis Springer International. Springer International Publishing. 2017.-218 p. DOI. 10.1007/978-3-319-57027-3.Hardcover ISBN.978-3-319-57026-6.
[7] K. Malyshevska. The analysis of neural networks’ performance for medical image classification/K. Malyshevska//International Journal "Information Content and Processing", Volume 1, Number 2, 2014.-С. 194-199.
[8] K. Malyshevska. Analysis of neural networks application for diagnostics of uterus cancer using multispectral images. System research and information technologies.-2010-№2-pp. 64-71. (rus)
[9] Detlef Nauck and Rudolf Kruse. Generating classification rules with the neuro-fuzzy system NEFCLASS. In Proc. Biennial Conf. of the Norght American Fuzzy Information Processing Society (NAFIPS’96), Berkeley, 1996.
[10] Detlef Nauck and Rudolf Kruse. New learning strategies for NEFCLASS. In Proc. Seventh International Fuzzy Systems Association World Congress IFSA’97, Vol. IV, pp. 50-55, Academia Prague, 1997.
[11] Zaychenko Yu. P., Sevaee Fatma, Matsak A. V. Fuzzy neural networks for economic data classification//Vestnik of National Technical University of Ukraine “KPI”, section “Informatic, control and c omputer engineering. Vol. 42.-2004.-pp. 121-133. (rus).
[12] Zaychenko Yu. P., Petrosyuk I. M., Jaroshenko M. S. The investigations of fuzzy neural networks in the problems of electro-optical images recognition//System research and information technologies.-2009.-№4.-pp. 61-76. (rus).
[13] M. Zgurovsky, Yu. Zaychenko. The Fundamentals of Computational Intelligence: System Approach. Springer International Publishing AG, Switzerland.-2016-308p.
[14] N. Jindal. Enhanced Face Recognition Algorithm using PCA with Artificial Neural Networks./N Jindal, V Kumar//International Journal of Advanced Research in Computer Science and Software Engineering-2013-vol 3 pp. 864-872.
Cite This Article
  • APA Style

    Yuriy Zaychenko, Aghaei Agh Ghamish Ovi Nafas. (2019). Medical Images Classification and Diagnostics Using Fuzzy Neural Networks. American Journal of Neural Networks and Applications, 5(2), 45-50. https://doi.org/10.11648/j.ajnna.20190502.11

    Copy | Download

    ACS Style

    Yuriy Zaychenko; Aghaei Agh Ghamish Ovi Nafas. Medical Images Classification and Diagnostics Using Fuzzy Neural Networks. Am. J. Neural Netw. Appl. 2019, 5(2), 45-50. doi: 10.11648/j.ajnna.20190502.11

    Copy | Download

    AMA Style

    Yuriy Zaychenko, Aghaei Agh Ghamish Ovi Nafas. Medical Images Classification and Diagnostics Using Fuzzy Neural Networks. Am J Neural Netw Appl. 2019;5(2):45-50. doi: 10.11648/j.ajnna.20190502.11

    Copy | Download

  • @article{10.11648/j.ajnna.20190502.11,
      author = {Yuriy Zaychenko and Aghaei Agh Ghamish Ovi Nafas},
      title = {Medical Images Classification and Diagnostics Using Fuzzy Neural Networks},
      journal = {American Journal of Neural Networks and Applications},
      volume = {5},
      number = {2},
      pages = {45-50},
      doi = {10.11648/j.ajnna.20190502.11},
      url = {https://doi.org/10.11648/j.ajnna.20190502.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20190502.11},
      abstract = {The problem of medical images of cervix epithelium classification for express diagnostics is considered…The following states of cervix epithelium are to be recognized and classified: normal state - columnar epithelium; squamous epithelium (normal state); metaplasia-benign changes of cervix uterus epithelium; CIN1-displasia of light degree, CIN 2-displasia of middle degree, CIN 3-displasia of high degree- intra-epithelium cancer: For its solution the application of fuzzy neural network (FNN NEFClass M) is suggested. The application of FNN is grounded by its following properties: it may work with fuzzy and qualitative information; it has accelerated convergence as compared with crisp classification methods; it enables to attain better classification accuracy than conventional classifiers. The structure of FNN NEFClass and its model description are presented. Training algorithm stochastic gradient descent for membership functions of fuzzy sets is considered and implemented. Data set of medical images of cervix epithelium which was obtained by special device colposcope is described and some images are presented. The experimental investigations of FNN NEFClass application for medical images recognition on real data are carried out, the results are presented. The comparison with NN Back Propagation, RBF NN and cascade RBF NN was made and estimation of efficiency of the suggested approach was performed. The problem of reduction of features number in classification tasks using principal component method (PCM) method is considered and implemented.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Medical Images Classification and Diagnostics Using Fuzzy Neural Networks
    AU  - Yuriy Zaychenko
    AU  - Aghaei Agh Ghamish Ovi Nafas
    Y1  - 2019/09/09
    PY  - 2019
    N1  - https://doi.org/10.11648/j.ajnna.20190502.11
    DO  - 10.11648/j.ajnna.20190502.11
    T2  - American Journal of Neural Networks and Applications
    JF  - American Journal of Neural Networks and Applications
    JO  - American Journal of Neural Networks and Applications
    SP  - 45
    EP  - 50
    PB  - Science Publishing Group
    SN  - 2469-7419
    UR  - https://doi.org/10.11648/j.ajnna.20190502.11
    AB  - The problem of medical images of cervix epithelium classification for express diagnostics is considered…The following states of cervix epithelium are to be recognized and classified: normal state - columnar epithelium; squamous epithelium (normal state); metaplasia-benign changes of cervix uterus epithelium; CIN1-displasia of light degree, CIN 2-displasia of middle degree, CIN 3-displasia of high degree- intra-epithelium cancer: For its solution the application of fuzzy neural network (FNN NEFClass M) is suggested. The application of FNN is grounded by its following properties: it may work with fuzzy and qualitative information; it has accelerated convergence as compared with crisp classification methods; it enables to attain better classification accuracy than conventional classifiers. The structure of FNN NEFClass and its model description are presented. Training algorithm stochastic gradient descent for membership functions of fuzzy sets is considered and implemented. Data set of medical images of cervix epithelium which was obtained by special device colposcope is described and some images are presented. The experimental investigations of FNN NEFClass application for medical images recognition on real data are carried out, the results are presented. The comparison with NN Back Propagation, RBF NN and cascade RBF NN was made and estimation of efficiency of the suggested approach was performed. The problem of reduction of features number in classification tasks using principal component method (PCM) method is considered and implemented.
    VL  - 5
    IS  - 2
    ER  - 

    Copy | Download

Author Information
  • Institute for Applied System Analysis, Igor Sikorsky Kiev Polytechnic Institute, Kiev, Ukraine

  • Department of Applied Mathematics, Igor Sikorsky Kiev Polytechnic Institute, Kiev, Ukraine

  • Sections