Skip to main content

Generalized Multiscale RBF Networks and the DCT for Breast Cancer Detection

Abstract

The use of the multiscale generalized radial basis function (MSRBF) neural networks for image feature extraction and medical image analysis and classification is proposed for the first time in this work. The MSRBF networks hold a simple and flexible architecture that has been successfully used in forecasting and model structure detection of input-output nonlinear systems. In this work instead, MSRBF networks are part of an integrated computer-aided diagnosis (CAD) framework for breast cancer detection, which holds three stages: an input-output model is obtained from the image, followed by a high-level image feature extraction from the model and a classification module aimed at predicting breast cancer. In the first stage, the image data is rendered into a multiple-input-single-output (MISO) system. In order to improve the characterisation, the nonlinear autoregressive with exogenous inputs (NARX) model is introduced to rearrange the available input-output data in a nonlinear way. The forward regression orthogonal least squares (FROLS) algorithm is then used to take advantage of the previous arrangement by solving the system as a model structure detection problem and finding the output layer weights of the NARX-MSRBF network. In the second stage, once the network model is available, the feature extraction takes place by stimulating the input to produce output signals to be compressed by the discrete cosine transform (DCT). In the third stage, we leverage the extracted features by using a clustering algorithm for classification to integrate a CAD system for breast cancer detection. To test the method performance, three different and well-known public image repositories were used: the mini-MIAS and the MMSD for mammography, and the BreaKHis for histopathology images. A comparison exercise was also made between different database partitions to understand the mammogram breast density effect in the performance since there are few remarks in the literature on this factor. Classification results show that the new CAD method reached an accuracy of 93.5% in mini-Mammo graphic image analysis society (mini-MIAS), 93.99% in digital database for screening mammography (DDSM) and 86.7% in the BreaKHis. We found that the MSRBF networks are able to build tailored and precise image models and, combined with the DCT, to extract high-quality features from both black and white and coloured images.

This is a preview of subscription content, access via your institution.

References

  1. [1]

    A. C. Bovik. The Essential Guide to Image Processing, London, UK: Academic Press, 2009. DOI: https://doi.org/10.1016/B978-0-12-374457-9.X0001-7.

    Google Scholar 

  2. [2]

    S. A. Billings. Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-temporal Domains, Chichester, UK: John Wiley & Sons, Ltd., 2013. DOI: https://doi.org/10.1002/9781118535561.

    MATH  Book  Google Scholar 

  3. [3]

    V. K. Ha, J. C. Ren, X. Y. Xu, S. Zhao, G. Xie, V. M. Vargas. Deep learning based single image super-resolution: A survey. In Proceedings of the 9th International Conference on Brain Inspired Cognitive Systems, Springer, Xi’an, China, pp. 106–119, 2018. DOI: https://doi.org/10.1007/978-3-030-00563-4_11.

    Google Scholar 

  4. [4]

    V. A. Le, H. X. Le, L. Nguyen, M. X. Phan. An efficient adaptive hierarchical sliding mode control strategy using neural networks for 3D overhead cranes. International Journal of Automation and Computing, vol. 16, no. 5, pp. 614–627, 2019. DOI: https://doi.org/10.1007/s11633-019-1174-y.

    Article  Google Scholar 

  5. [5]

    K. Doi. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Computerized Medical Imaging and Graphics, vol. 31, no. 4–5, pp. 198–211, 2007. DOI: https://doi.org/10.1016/j.compmedimag.2007.02.002.

    Article  Google Scholar 

  6. [6]

    S. K. Vipparthi, S. K. Nagar. Local extreme complete trio pattern for multimedia image retrieval system. International Journal of Automation and Computing, vol. 13, no. 5, pp. 457–467, 2016. DOI: https://doi.org/10.1007/s11633-016-0978-2.

    Article  Google Scholar 

  7. [7]

    G. Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, vol. 2, no. 4, pp. 303–314, 1989. DOI: https://doi.org/10.1007/BF02551274.

    MathSciNet  MATH  Article  Google Scholar 

  8. [8]

    A. X. Li, Z. W. Lu, L. W. Wang, T. Xiang, X. Q. Li, J. R. Wen. Zero-shot fine-grained classification by deep feature learning with semantics. https://arXiv.org/abs/1707.00785, 2017.

  9. [9]

    M. Sonka, V. Hlavac, R. Boyle. Image Processing, Analysis and Machine Vision, Boston, USA: Springer, 1993. DOI: https://doi.org/10.1007/978-1-4899-3216-7.

    Book  Google Scholar 

  10. [10]

    C. Kotropoulos, I. Pitas. Nonlinear Model-based Image/Video Processing and Analysis, New York, USA: John Wiley & Sons, Inc., 2001.

    MATH  Google Scholar 

  11. [11]

    L. F. C. Pessoa, P. Maragos. MRL-filters: A general class of nonlinear systems and their optimal design for image processing. IEEE Transactions on Image Processing, vol. 7, no. 7, pp. 966–978, 1998. DOI: https://doi.org/10.1109/83.701150.

    Article  Google Scholar 

  12. [12]

    S. A. Billings, H. L. Wei, M. A. Balikhin. Generalized multiscale radial basis function networks. Neural Networks, vol. 20, no. 10, pp. 1081–1094, 2007. DOI: https://doi.org/10.1016/j.neunet.2007.09.017.

    MATH  Article  Google Scholar 

  13. [13]

    A. Rubio-Solis, U. Martinez-Hernandez, G. Panoutsos. Evolutionary extreme learning machine for the interval type-2 radial basis function neural network: A fuzzy modelling approach. In Proceedings of IEEE International Conference on Fuzzy Systems, IEEE, Rio de Janeiro, Brazil, 2018. DOI: https://doi.org/10.1109/FUZZ-IEEE.2018.8491583.

    Google Scholar 

  14. [14]

    A. Rubio-Solis, G. Panoutsos. Interval type-2 radial basis function neural network: A modeling framework. IEEE Transactions on Fuzzy Systems, vol. 23, no. 2, pp. 457–473, 2015. DOI: https://doi.org/10.1109/TFUZZ.2014.2315656.

    Article  Google Scholar 

  15. [15]

    A. Rubio-Solis, P. Melin, U. Martinez-Hernandez, G. Panoutsos. General type-2 radial basis function neural network: A data-driven fuzzy model. IEEE Transactions on Fuzzy Systems, vol. 27, no. 2, pp. 333–347, 2019. DOI: https://doi.org/10.1109/TFUZZ.2018.2858740.

    Article  Google Scholar 

  16. [16]

    H. L. Wei, S. A. Billings, M. Balikhin. Prediction of the Dst index using multiresolution wavelet models. Journal of Geophysical Research: Space Physics, vol. 109, no. A7, Article number A07212, 2004. DOI: https://doi.org/10.1029/2003JA010332.

    Google Scholar 

  17. [17]

    M. J. Er, W. Chen, S. Q. Wu. High-speed face recognition based on discrete cosine transform and RBF neural networks. IEEE Transactions on Neural Networks, vol. 16, no. 3, pp. 679–691, 2005. DOI: https://doi.org/10.1109/TNN.2005.844909.

    Article  Google Scholar 

  18. [18]

    M. J. Er, S. Q. Wu, J. W. Lu, H. L. Toh. Face recognition with radial basis function (RBF) neural networks. IEEE Transactions on Neural Networks, vol. 13, no. 3, pp. 697–710, 2002. DOI: https://doi.org/10.1109/TNN.2002.1000134.

    Article  Google Scholar 

  19. [19]

    S. Chen, S. A. Billings. Neural networks for nonlinear dynamic system modelling and identification. International Journal of Control, vol. 56, no. 2, pp. 319–346, 1992. DOI: https://doi.org/10.1080/00207179208934317.

    MathSciNet  MATH  Article  Google Scholar 

  20. [20]

    T. Poggio, S. Edelman. A network that learns to recognize three-dimensional objects. Nature, vol. 343, no. 6255, pp. 263–266, 1990. DOI: https://doi.org/10.1038/343263a0.

    Article  Google Scholar 

  21. [21]

    R. Yang, P. V. Er, Z. D. Wang, K. K. Tan. An RBF neural network approach towards precision motion system with selective sensor fusion. Neurocomputing, vol. 199, pp. 21–39, 2016. DOI: https://doi.org/10.1016/j.neucom.2016.01.093.

    Google Scholar 

  22. [22]

    Z. H. Lu, S. Y. Lu, G. Liu, Y. D. Zhang, J. F. Yang, P. Phillips. A pathological brain detection system based on radial basis function neural network. Journal of Medical Imaging and Health Informatics, vol. 6, no. 5, pp. 1218–1222, 2016. DOI: https://doi.org/10.1166/jmihi.2016.1901.

    Article  Google Scholar 

  23. [23]

    G. Vani, R. Savitha, N. Sundararajan. Classification of abnormalities in digitized mammograms using extreme learning machine. In Proceedings of the 11th International Conference on Control Automation Robotics & Vision, IEEE, Singapore, pp. 2114–2117, 2010. DOI: https://doi.org/10.1109/ICARCV.2010.5707794.

    Google Scholar 

  24. [24]

    M. Pratiwi, Alexander, J. Harefa, S. Nanda. Mammograms classification using gray-level co-occurrence matrix and radial basis function neural network. Procedia Computer Science, vol. 59, pp. 83–91, 2015. DOI: https://doi.org/10.1016/j.procs.2015.07.340.

    Article  Google Scholar 

  25. [25]

    I. Christoyianni, A. Koutras, E. Dermatas, G. Kokkinakis. Computer aided diagnosis of breast cancer in digitized mammograms. Computerized Medical Imaging and Graphics, vol. 26, no. 5, pp. 309–319, 2002. DOI: https://doi.org/10.1016/s0895-6111(02)00031-9.

    Article  Google Scholar 

  26. [26]

    K. Iftikhar, S. Anwar, I. U. Haq, M. T. Khan, S. R. Akbar. An optimal neural network based classification technique for breast cancer detection. Journal of Engineering and Applied Sciences, vol. 35, no. 1, pp. 51–58, 2016.

    Google Scholar 

  27. [27]

    S. P. Singh, S. Urooj. An improved CAD system for breast cancer diagnosis based on generalized pseudo-Zernike moment and Ada-DEWNN classifier. Journal of Medical Systems, vol. 40, no. 9, Article number 105, 2016. DOI: https://doi.org/10.1007/s10916-016-0454-0.

    Google Scholar 

  28. [28]

    Z. J. Yao, J. Bi, Y. X. Chen. Applying deep learning to individual and community health monitoring data: A survey. International Journal of Automation and Computing, vol. 15, no. 6, pp. 643–655, 2018. DOI: https://doi.org/10.1007/s11633-018-1136-9.

    Article  Google Scholar 

  29. [29]

    T. Poggio, F. Girosi. A Theory of Networks for Approximation and Learning, No. AI-M-1140, Massachusetts Institute of Technology, Cambridge, USA, 1989.

    MATH  Google Scholar 

  30. [30]

    N. Ahmed, T. Natarajan, K. R. Rao. Discrete cosine transform. IEEE Transactions on Computers, vol. C-23, no. 1, pp. 90–93, 1974. DOI: https://doi.org/10.1109/T-C.1974.223784.

    MathSciNet  MATH  Article  Google Scholar 

  31. [31]

    C. B. Perez, H. L. Wei. Digital image classification and detection using a 2D-NARX model. In Proceedings of the 23rd International Conference on Automation and Computing, IEEE, Huddersfield, UK, 2017. DOI: https://doi.org/10.23919/IConAC.2017.8081989.

    Google Scholar 

  32. [32]

    F. Schwenker, H. A. Kestler, G. Palm. Three learning phases for radial-basis-function networks. Neural Networks, vol. 14, no. 4–5, pp. 439–458, 2001. DOI: https://doi.org/10.1016/s0893-6080(01)00027-2.

    MATH  Article  Google Scholar 

  33. [33]

    W. J. Krzanowski, Y. T. Lai. A criterion for determining the number of groups in a data set using sum-of-squares clustering. Biometrics, vol. 44, no. 1, pp. 23–34, 1988. DOI: https://doi.org/10.2307/2531893.

    MathSciNet  MATH  Article  Google Scholar 

  34. [34]

    D. Arthur, S. Vassilvitskii. k-means++: The advantages of careful seeding. In Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms, Society for Industrial and Applied Mathematics, Louisiana, USA, pp. 1027–1035, 2007. https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf

    MATH  Google Scholar 

  35. [35]

    S. A. Billings, M. J. Korenberg, S. Chen. Identification of non-linear output-affine systems using an orthogonal least-squares algorithm. International Journal of Systems Science, vol. 19, no. 8, pp. 1559–1568, 1988. DOI: https://doi.org/10.1080/00207728808964057.

    MathSciNet  MATH  Article  Google Scholar 

  36. [36]

    M. Korenberg, S. A. Billings, Y. P. Liu, P. J. McILROY. Orthogonal parameter estimation algorithm for non-linear stochastic systems. International Journal of Control, vol. 48, no. 1, pp. 193–210, 1988. DOI: https://doi.org/10.1080/00207178808906169.

    MathSciNet  MATH  Article  Google Scholar 

  37. [37]

    J. P. Suckling. The mammographic image analysis society digital mammogram database. Digital Mammo, pp. 375–386, 1994.

  38. [38]

    J. Whitehill, P. Ruvolo, T. F. Wu, J. Bergsma, J. Movellan. Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. In Proceedings of the 22nd International Conference on Neural Information Processing Systems, Curran Associates Inc., Vancouver, Canada, pp. 2035–2043, 2009.

    Google Scholar 

  39. [39]

    M. Heath, K. Bowyer, D. Kopans, R. Moore, W P. Kegelmeyer. The digital database for screening mammography. In Proceedings of the 5th International Workshop on Digital Mammography, Medical Physics Publishing, Madison, USA, pp. 212–218, 2001.

    Google Scholar 

  40. [40]

    R. S. Lee, F. Gimenez, A. Hoogi, K. K. Miyake, M. Gorovoy, D. L. Rubin. A curated mammography data set for use in computer-aided detection and diagnosis research. Scientific Data, vol. 4, Article number 170177, 2017. DOI: https://doi.org/10.1038/sdata.2017.177.

  41. [41]

    A. Sharma. DDSM utility. GitHub, GitHub repository, [Online], Available: https://github.com/trane293/DDS-MUtility, 2015.

  42. [42]

    F. A. Spanhol, L. S. Oliveira, C. Petitjean, L. Heutte. Breast cancer histopathological image classification using convolutional neural networks. In Proceedings of 2016 International Joint Conference on Neural Networks, IEEE, Vancouver, BC, Canada, pp. 2560–2567, 2016. DOI: https://doi.org/10.1109/IJCNN.2016.7727519.

    Google Scholar 

  43. [43]

    L. G. Hafemann, L. S. Oliveira, P. Cavalin. Forest species recognition using deep convolutional neural networks. In Proceedings of the 2014 22nd International Conference on Pattern Recognition, IEEE, Stockholm, Sweden, pp. 1103–1107, 2014. DOI: https://doi.org/10.1109/ICPR.2014.199.

    Google Scholar 

  44. [44]

    A. Krizhevsky, I. Sutskever, G. Hinton. Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Curran Associates Inc., Lake Tahoe, USA, pp. 1097–1105, 2012. DOI: https://doi.org/10.1145/3065386.

    Google Scholar 

  45. [45]

    F. A. Spanhol, L. S. Oliveira, P. R. Cavalin, C. Petitjean, L. Heutte. Deep features for breast cancer histopathological image classification. In Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, IEEE, Banff, AB, Canada, pp. 1868–1873, 2017. DOI: https://doi.org/10.1109/SMC.2017.8122889.

    Google Scholar 

  46. [46]

    Z. Y. Han, B. Z. Wei, Y. J. Zheng, Y. L. Yin, K. J. Li, S. Li. Breast cancer multi-classification from histopathological images with structured deep learning model. Scientific Reports, vol. 7, no. 1, Article number 4172, 2017. DOI: https://doi.org/10.1038/s41598-017-04075-z.

    Google Scholar 

Download references

Acknowledgements

The authors acknowledge the financial support to Carlos Beltran-Perez from the Mexican National Council of Science and Technology (CONACYT). The authors gratefully acknowledge that part of the work was supported by the Engineering and Physical Sciences Research Council (EPSRC) under grant EP/I011056/1 and platform grant EP/H00453X/1.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Carlos Beltran-Perez.

Additional information

Carlos Beltran-Perez received the B. Eng. degree in systems engineering from the Autonomous Metropolitan University, Mexico, and received M. Sc. degree in systems engineering from the Autonomous University of Nuevo Leon, Mexico. He received the Ph. D. degree in automatic control and systems engineering from University of Sheffield, UK in 2019. He is currently a lecturer at Departments of Industrial Engineering and Computer Engineering, Monterrey Institute of Technology and Higer Education, Campus Toluca, Mexico, and a graduate researcher at University of Sheffield, UK.

His research interests include identification and modelling for complex systems, medical image processing, NARMAX methodologies, multilayer neural networks, forecasting and time series analysis.

Hua-Liang Wei received the Ph. D. degree in signal processing and complex system from Department of Automatic Control and Systems Engineering, University of Sheffield, UK in 2004. He is currently a senior lecturer in Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, UK.

His research interests include system identification and data analytics for complex systems, data driven modeling and data mining, NARMAX methodology and its applications, statistical digital signal processing, machine learning and neural networks, spatio-temporal system modeling, neuro-wavelet models for learning, nonstationary (time varying) process modeling, forecasting of complex dynamic processes, generalized regression analysis, linear and nonlinear optimization, and multidisciplinary applications in medicine and bio-medicine, medical informatics, space weather and environmental sciences.

Adrian Rubio-Solis received the B. Eng. degree in robotics and the M. Sc degree in electrical engineering from the the National Polytechnic Institute of Mexico, Mexico in 2003 and 2005 respectively. He received the Ph. D. degree in automatic control and systems engineering from the University of Sheffield, UK in 2014. He is currently working as research fellow at the Submarine Robotics Laboratory, CIDESI Queretaro, Mexico.

His research interests include data-driven modelling, image processing, fuzzy control theory and machine learning applied to submarine robotics.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Beltran-Perez, C., Wei, HL. & Rubio-Solis, A. Generalized Multiscale RBF Networks and the DCT for Breast Cancer Detection. Int. J. Autom. Comput. 17, 55–70 (2020). https://doi.org/10.1007/s11633-019-1210-y

Download citation

Keywords

  • Nonlinear system identification
  • image processing
  • discrete cosine transform
  • radial basis functions
  • computer-aided diagnosis
  • neural networks