A method for adjusting directed texture features in biomedical image analysis problems
A.V. Gaidel

 

Samara State Aerospace University,
Image Processing Systems Institute, Russian Academy of Sciences

 

DOI: 10.18287/0134-2452-2015-39-2-287-293

Full text of article: Russian language.

Abstract:
As part of the general problem of automatic information feature construction, we considered a particular applied problem of the calculation direction adjustment for the directed texture features intended to diagnose various diseases from digital biomedical images. As feature space quality criteria, we considered the classification accuracy, Bhattacharyya distance and the discriminant analysis criteria. We used random search, a genetic algorithm and simulated annealing as the optimization algorithms. The proposed approach enables a two-fold reduction in the error probability estimation when diagnosing bone tissue X-ray images (from 0.20 to 0.10), also enabling a 45-percent error reduction when diagnosing computed tomography (CT) lung images (from 0.11 to 0.06) in comparison with conventional procedures of selecting from a large number of heterogeneous features.

Keywords:
texture analysis, feature construction, discriminant analysis, genetic algorithm, simulated annealing.

References:

  1. Rangayyan, R.M. Biomedical image analysis / R.M. Rangayyan. – CRC press, 2004. – 1272 p.
  2. Ilyasova, N.Yu. Information technologies of the image analysis in the medical diagnosis problems / N.Yu. Ilyasova, A.V. Kupriyanov, A.G. Khramov. – Moscow: “Radio I Svyaz” Publisher, 2012. – 424 p. – (In Russian).
  3. Glumov, N.I. Method of the informative features selection on the digital images / N.I. Glumov, E.V. Myasnikov // Computer Optics. – 2007. – Vol. 31(3). – P. 73-76. – ISSN 0134-2452. – (In Russian).
  4. Gaidel, A.V. Research of the textural features for the bony tissue diseases diagnostics using the roentgenograms / A.V. Gaidel, S.S. Pervushkin // Computer Optics. – 2013. – Vol. 37(1). – P. 113-119.
  5. Gaidel, A.V. Research of the textural features for the nephrological diseases diagnostics using the ultrasound images / A.V. Gaidel, S.N. Larionova, A.G. Khramov // Herald of the Samara State Aerospace University. – 2014. – Vol. 43(1). – P. 229-237. – ISSN 1998-6629. – (In Russian).
  6. Gaidel, A.V. Computed tomography texture analysis possibilities of the chronic obstructive pulmonary disease diagnosis / A.V. Gaidel, P.M. Zelter, A.V. Kapishnikov, A.G. Khramov // Computer Optics. – 2014. – Vol. 38(4). – P. 843-850.
  7. Feature construction and dimension reduction using genetic programming / K. Neshatian, M. Zhang, M. Johnston // Lecture Notes in Computer Science. – 2007. – Vol. 4830. – P. 160-170.
  8. A feature construction method for general object recognition / K. Lillywhite, D.-J. Lee, B. Tippetts, J. Archibald // Pattern Recognition. – 2013. – Vol. 46, Issue 12. – P. 3300-3314.
  9. Myasnikov, V.V. Analysis of methods for construction of efficient linear local features for digital signals and images description / V.V. Myasnikov, A.Y. Bavrina, O.A. Titova // Computer Optics. – 2010. – Vol. 34(3). – P. 374-381. – (In Russian).
  10. Schneider, J.J. Stochastic Optimization / J.J. Schneider, S. Kirkpatrick. – Berlin: Springer, 2006. – 568 p.
  11. Gill, Ph. Practical optimization / Ph. Gill, W. Murray, M. Wright. – Academic Press, 1982. – 418 p.
  12. Emelyanov, V.V. Theory and practice of the evolutionary computation / V.V. Emelyanov, V.V. Kureychik, V.M. Kureychik. – Moscow: “Fismatlit” Publisher, 2003. – 432 p. – (in Russian).
  13. Optimization by simulated annealing / S. Kirkpatrick, C.D. Gelatt-Jr, M.P. Vecchi // Science. – 1983. – Vol. 220(4598). – P. 671-680.
  14. Fukunaga, K. Introduction to Statistical Pattern Recognition / K. Fukunaga. – Academic Press, 1990. – 592 p.
  15. Yang, M. Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis / M. Yang, H. Zheng, H. Wang, S. McClean // 3rd International Conference on Pervasive Computing Technologies for Healthcare – Pervasive Health 2009. – London, United Kingdom, 1-3 April, 2009. – 7 p.
  16. Automated Texture-based Quantification of Centrilobular Nodularity and Centrilobular Emphysema in Chest CT Images / S.B. Ginsburg, D.A. Lynch, R.P. Bowler, J.D. Schroeder // Academic Radiology. – 2012. – Vol. 19(10). – P. 1241-1251.
  17. Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions / A. Agresti, B.A. Coull // American Statistician / American Statistical Association. – 1998. – Vol. 52(2). – P. 119-126.
  18. Keeney, R.L. Decisions with Multiple Objectives: Preferences and Value Trade-Offs / R.L. Keeney, H. Raiffa. – Cambridge: Cambridge University Press, 1993. – 569 p..

© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; e-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20