Advertisement

Artificial Life and Robotics

, Volume 23, Issue 2, pp 161–172 | Cite as

Deep feedback GMDH-type neural network and its application to medical image analysis of MRI brain images

  • Shoichiro Takao
  • Sayaka Kondo
  • Junji Ueno
  • Tadashi Kondo
Original Article

Abstract

The deep feedback group method of data handling (GMDH)-type neural network is applied to the medical image analysis of MRI brain images. In this algorithm, the complexity of the neural network is increased gradually using the feedback loop calculations. The deep neural network architecture is automatically organized so as to fit the complexity of the medical images using the prediction error criterion defined as Akaike’s information criterion (AIC) or prediction sum of squares (PSS). The recognition results show that the deep feedback GMDH-type neural network algorithm is useful for the medical image analysis of MRI brain images, because the optimum neural network architectures fitting the complexity of the medical images are automatically organized so as to minimize the prediction error criterion defined as AIC or PSS.

Keywords

Deep neural network GMDH Medical image recognition Evolutionary computation Machine learning 

Notes

Acknowledgements

This work was supported by (JSPS) KAKENHI 26420421.

References

  1. 1.
    Kondo T, Ueno J, Takao S (2015) Medical image diagnosis of liver cancer by hybrid feedback GMDH-type neural network using principal component-regression analysis. Artif Life Robot 20:145–151CrossRefGoogle Scholar
  2. 2.
    Kondo T, Ueno J, Takao S (2015) Deep multi-layered GMDH-type neural network using principal component-regression analysis and its application to medical image recognition of brain and blood vessels. In: Proceedings of the 20th international symposium on artificial life and robotics 2015, pp 339–342Google Scholar
  3. 3.
    Kondo T (1998) GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem. In: Proceedings of the 37th SICE annual conference, pp 1143–1148Google Scholar
  4. 4.
    Farlow SJ (ed) (1984) Self-organizing methods in modeling, GMDH-type algorithm. Marcel Dekker, Inc., New YorkzbMATHGoogle Scholar
  5. 5.
    Ivakhnenko AG (1970) Heuristic self-organization in problems of engineering cybernetics. Automatica 6(2):207–219CrossRefGoogle Scholar
  6. 6.
    Anderson VM, Schott JM, Bartlett JW, Leung KK, Miller DH, Fox NC (2012) Gray matter atrophy rate as a marker of disease progression in AD. Neurobiol Aging 33(7):1194–1202CrossRefGoogle Scholar
  7. 7.
    Mouton PR, Martin LJ, Calhoun ME, Dal Fomo G, Price DL (1998) Cognitive decline strongly correlates with cortical atrophy in Alzheimer’s dementia. Neurobiol Aging 19(5):371–377CrossRefGoogle Scholar
  8. 8.
    Serra L, Cercignani M, Lenzi D, Perri R, Fadda L, Caltagirone C, Macaluso E, Bozzali M (2010) Gray and white matter changes at different stages of Alzheimer’s disease. J Alzheimer’s Dis 19(1):147–159CrossRefGoogle Scholar
  9. 9.
    Anderson VM, Femando KT, Davies GR, Rashid W, Frost C, Fox NC, Miller DH (2007) Cerebral atrophy measurement in clinically isolated syndromes and relapsing remitting multiple sclerosis: a comparison of registration-based methods. J Neuroimaging 17(1):61–68CrossRefGoogle Scholar
  10. 10.
    Akaike H (1974) A new look at the statistical model identification. IEEE Trans Automatic Control AC-19(6):716–723MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Tamura H, Kondo T (1980) Heuristics free group method of data handling algorithm of generating optimum partial polynomials with application to air pollution prediction. Int J Syst Sci 11(9):1095–1111CrossRefGoogle Scholar
  12. 12.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagation errors. Nature 323(9):533–536CrossRefzbMATHGoogle Scholar
  13. 13.
    Zurada JM (1992) Introduction to artificial neural systems. PWS Publishing Company, BostonGoogle Scholar
  14. 14.
    Pham DT, Xing L (1995) Neural networks for identification, prediction and control. Springer, LondonCrossRefGoogle Scholar
  15. 15.
    Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Hinton GE, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313:504–507MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Draper NR, Smith H (1981) Applied regression analysis. Wiley, New YorkzbMATHGoogle Scholar

Copyright information

© ISAROB 2017

Authors and Affiliations

  • Shoichiro Takao
    • 1
  • Sayaka Kondo
    • 2
  • Junji Ueno
    • 1
  • Tadashi Kondo
    • 1
  1. 1.Graduate School of Health SciencesTokushima UniversityTokushimaJapan
  2. 2.Tokushima Medical Informatics LaboratoryTokushimaJapan

Personalised recommendations