(38-4) 39 * << * >> * Russian * English * Content * All Issues

PDF, 419 kB

Full text of article: Russian language.

DOI: 10.18287/0134-2452-2014-38-4-843-850

Pages: 843-850.

Abstract:
The possibility of application of different textural features for the lung disease automatic diagnosis on the basis of the 2D digital computed tomography (CT) images was studied. Histogram features, covariance features, Haralick’s features and run length features were used. A procedure based on the discriminant analysis criterion was used for the selection of the best features group. We experimentally showed that the approach offered is convenient to use for solving the problem of automatic diagnosis on a 160-image set received during examination of patients with a chronic obstructive pulmonary disease. The resulting group of effective features includes two Haralick’s features and three run length features, providing the error rate of 0.11, which is better than similar results obtained without a feature selection procedure.

Key words:
textural analysis, diagnosis, Haralick’s features, run length, feature selection, discriminant analysis.

Citation:
Ilyasova NY, Kupriyanov AV, Paringer RA. Formation features for improving the quality of medical diagnosis based on the discriminant analysis methods. Computer Optics 2014; 38(4): 851-855. DOI: 10.18287/0134-2452-2014-38-4-851-855.

References:

1. Zelter, P.M. Structure and functional phenotyping of COPD / P.M. Zelter, M.S. Ustinov, A.V. Kapishnikov // Physician. – 2014. – Vol. 7(65). – P. 18-23. – ISSN 20726-0277. – (In Russian).
2. Engeler, C.E. Ground-glass opacity of the lung parenchyma: A guide to analysis with high-resolution CT / C.E. Engeler, J.H. Tashjian, S.W. Trenkner, J.W. Walsh // American Journal of Roentgenology. – 1993. – Vol. 160(2). – P. 249-251. – ISSN 0361-803X.
3. Zelter, P.M. Role of CT in early evaluating of COPD signs / P.M. Zelter // Postgraduate Doctor. – 2014. – Vol. 4.2(65). – P. 228-233. – ISSN 1816-5214. – (In Russian).
4. Ginsburg, S.B. 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. – ISSN 1076-6332.
5. 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. – ISSN 0134-2452.
6. 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).
7. Sadykov, S.S. Computer diagnosis of tumors in mammograms / S.S. Sadykov, Yu.A. Bulanova, E.A. Zakharova // Computer Optics. – 2014. – Vol. 38(1). – P. 131-138. – ISSN 0134-2452.
8. Glumov, N.I. Computer processing of lung scintigraphic images / N.I. Glumov, A.V. Kapishnikov // Computer Optics. – 2003. – Vol. 25. – P. 158-164. – ISSN 0134-2452. – (In Russian).
9. Ilyasova, N.Yu. Methods for digital analysis of human vascular system. Literature review / N.Yu. Ilyasova // Computer Optics. – 2013. – Vol. 37(4). – P. 511-535. – ISSN 0134-2452.
10. Ilyasova, N.Yu. Information technologies of image analysis in medical diagnostics / N.Yu. Ilyasova, A.V. Kupriyanov, A.G. Khramov. – Moscow: “Radio I Svyaz” Publisher, 2012. – 424 p. – ISBN 5-89776-014-4. – (In Russian).
11. Ilyasova, N.Yu. Estimating the geometric features of a 3D vascular structure // Computer Optics. – 2014. – Vol. 38(3). – P. 529-538. – ISSN 0134-2452.
12. 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).
13. Tsai, C.-F. Genetic algorithms in feature and instance selection / C.-F. Tsai, W. Eberle, C.-Y. Chu // Knowledge-Based Systems. – 2013. – Vol. 39. – P. 240-247. – ISSN 0950-7051.
14. Khushaba, R.N. Feature subset selection using differential evolution and a statistical repair mechanism / R.N. Khushaba, A. Al-Ani, A. Al-Jumaily // Expert Systems with Applications. – 2011. – Vol. 38(9). – P. 11515-11526. – ISSN 0957-4174.
15. Ilyasova, N.Yu.  Formation features for improving the quality of medical diagnosis based on the discriminant analysis methods / N.Yu. Ilyasova, A.V. Kupriyanov, R.A. Paringer // Computer Optics. – 2014. – Vol. 38(4) – P. 851-856. – ISSN 0134-2452. – (In Russian).
16. Petrou, M. Image Processing: Dealing with Texture / M. Petrou, P. Garcia Sevilla. – Chichester, UK: John Wiley & Sons, Ltd., 2006. – 618 p.
17. Haralick, R.M. Textural features for image classification / R.M. Haralick, K. Shanmugam, I. Dinstein // IEEE Transactions on Systems, Man, and Cybernetics. – 1973. – Vol. SMC-3(6). – P. 610-621. – ISSN 0018-9472.
18. Mollazade, K. Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging / K. Mollazade, M. Omid, F. Akhlaghian Tab, Y.R. Kalaj, S.S. Mohtasebi, M. Zude // Computers and Electronics in Agriculture. – 2013. – Vol. 98. – P. 34-45. – ISSN 0168-1699.
19. Fukunaga, K. Introduction to statistical pattern recognition / K. Fukunaga. – San Diego: Academic Press, 1990. – 592 p.
20. Agresti, A. Approximate is Better than "Exact" for Interval Estimation of Binomial Proportions / A. Agresti, B.A. Coull // American Statistician. – 1998. – Vol. 52(2). – P. 119-126. – ISSN 0003-1305.
21. Brown, L.D. Interval Estimation for a Binomial Proportion / L.D. Brown, T.T. Cai, A. DasGupta // Statistical Science / Institute of Mathematical Statistics. – 2001. – Vol. 16(2). – P. 101-133. – ISSN 0883-4237.

---

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail:journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20