© The Institution of Engineering and Technology
Tissue classification using computer aided diagnosis can help automated decision making to aid clinical diagnosis. Classification of breast tissue based on spectral features of impedance loci has frequently been done to classify malignant tissue with further requirement of more complex classification methodologies needed to improve the characterisation. In current study, tissue classification is done using in vivo electrical impedance data of 18 human subjects, from four quadrants of breast, palm, nail, arm, bicep and classified using algorithms involving machine learning methodologies, specifically support vector machines (SVMs) that are supervised learning models. They consist of learning algorithms based on the principal of structural risk minimisation. Two methodologies of SVM have been used in this study: with data binning and data pruning and without data binning and data pruning. Data binning and data pruning have improved the sensitivity of the SVM from 76.76 to 89.23%, but the specificity has decreased from 76.23 to 74.15%. This is a pilot study towards testing the reliability of the developed electrical impedance measuring system and developing a data mining-based decision making system into an electrical impedance spectroscopy system, to help users (physicians) with tissue classification leading to reliable objective decision making.
References
-
-
1)
-
16. Cole, K.S.: ‘Membranes, ions and impulses: a chapter of classical biophysics’ (University of California Press, Berkley, CA, 1968), pp. 6–102.
-
2)
-
3)
-
5. Foster, K.R., Schwan, H.: ‘Dielectric properties of tissues and biological materials: a critical review’, Crit. Rev. Biomed. Eng., 1989, 17, (I), pp. 25–104.
-
4)
-
14. Liu, N., Saulnier, G.J., Newell, J.C., Isaacson, D., Kao, J.: ‘ACT4: a high precision, multi frequency electrical impedance tomography’. Proc. Sixth Conf. Biomedical Applications, University College London, London, UK, 22–24 June 2005.
-
5)
-
13. Latge, C.K., Souza, M.N.: ‘Study of the electrical impedance scanning’. Proc. 23rd EMBS Int. Conf., 2001, pp. 3262–3264.
-
6)
-
7)
-
F. Melgani ,
L. Bruzzone
.
Classification of hyperspectral remote sensing images with support vector machines.
IEEE Trans. Geosci. Remote Sens.
,
8 ,
1778 -
1790
-
8)
-
6. Jossinet, J.: ‘Variability of impedivity in normal and pathological breast tissue’, Med. Biol. Eng. Comput., 1996, 34, pp. 346–350 (doi: 10.1007/BF02520002).
-
9)
-
28. Chang, C.-C., Lin, C.-J.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 1–27 (doi: 10.1145/1961189.1961199).
-
10)
-
40. Clarkson, P., Moreno, P.J.: ‘On the use of support vector machines for phonetic classification’. Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, 1999, vol. 2, pp. 585–588.
-
11)
-
23. Shini, M.A., Laufer, S., Rubinsky, B.: ‘SVM for prostate cancer using electrical impedance measurements’, Physiol. Meas., 2011, 32, (9), p. 1373 (doi: 10.1088/0967-3334/32/9/002).
-
12)
-
21. McGivney, D., Calvetti, D., Somersalo, E.: ‘Quantitative imaging with electrical impedance spectroscopy’, Phys. Med. Biol., 2012, 57, (22), pp. 7289–7302 (doi: 10.1088/0031-9155/57/22/7289).
-
13)
-
29. Schwan, H.P.: ‘Electrical properties of tissue and cell suspensions’, Adv. Biol. Med. Phys., 1957, 5, pp. 147–207 (doi: 10.1016/B978-1-4832-3111-2.50008-0).
-
14)
-
18. Kim, S.: ‘Assessment of breast tumor size in electrical impedance scanning’, Inverse Probl., 2012, 28, (2), pp. 025004 (doi: 10.1088/0266-5611/28/2/025004).
-
15)
-
3. Jossinet, J.: ‘The impedivity of freshly excised human breast tissue’, Physiol. Meas., 1998, 19, pp. 61–75 (doi: 10.1088/0967-3334/19/1/006).
-
16)
-
38. Hsu, C., Chang, C., Lin, C.: ‘A practical guide to support vector classification’, National Taiwan University, 2010.
-
17)
-
1. Fricke, H., Morse, S.: ‘The electric capacity of tumors in the breast’, J Cancer Res., 1926, 16, pp. 340–376.
-
18)
-
2. Surowiec, A., Stuchly, S., Barr, R., Swarup, A.: ‘Dielectric properties of breast carcinoma and the surrounding tissues’, IEEE Trans. Biomed. Eng., 1988, 35, pp. 257–263 (doi: 10.1109/10.1374).
-
19)
-
R. Halter ,
P. Meaney ,
A. Hartov ,
R.R. Barth ,
K.M. Rosenkranz ,
W.A. Wells ,
C.A. Kogel ,
E. Rizzo ,
K.D. Paulsen
.
The correlation of in vivo and ex vivo tissue dielectric properties to validate electromagnetic breast imaging: initial clinical experience.
Physiol. Meas
,
6 ,
S121 -
S136
-
20)
-
21)
-
22. Vapnik, V.N.: ‘The nature of statistical learning theory’ (Springer, Berlin, 2000).
-
22)
-
8. Assenheimer, M., Laver-Moskovitz, O., Malonek, D., et al: ‘The T-SCANTM technology: electrical impedance as a diagnostic tool for breast cancer detection’, Physiol. Meas., 2000, 22, pp. 1–8.
-
23)
-
9. ‘Transcan T-Scan 2000 Gets Panel Nod As Mammography Adjunct’, 1998, , 24, pp. 5–6.
-
24)
-
15. Tyna, A.H., Sian, E.: ‘Technology review: the use of electrical impedance scanning in the detection of breast cancer’, Breast Cancer Res., 2004, 6, (2), pp. 69–74.
-
25)
-
10. Glichman, Y.A., Filo, O., Nachaliel, U., Lnington, S., Amin-Spector, S., Ginor, R.: ‘Novel EIS postprocessing algorithm for breast cancer diagnosis’, IEEE Trans. Med. Imaging, 2002, 21, pp. 710–712 (doi: 10.1109/TMI.2002.800605).
-
26)
-
4. Mitsuyama, N., Morimoto, T., Kinouchi, Y., et al: ‘In vivo measurements of electrical bio-impedance of breast tumors’, Nippon Geka Gakkai Zasshi, 1988, 89, pp. 251–255.
-
27)
-
11. Seo, J.K., Kwon, O., Ammari, H., Woo, E.J.: ‘A mathematical model for breast cancer lesion estimation: electrical impedance technique using TS2000 commercial system’, IEEE Trans. Biomed. Eng., 2004, 51, pp. 1898–1906 (doi: 10.1109/TBME.2004.834261).
-
28)
-
K. Cole ,
R. Cole
.
Dispersion and absorption in dielectrics.
J. Chem. Phys.
,
341 -
351
-
29)
-
36. Dheeba, J., Tamil, S. S.: ‘Classification of malignant and benign microcalcification using SVM classifier’. Proc. ICETECT, 2011, pp. 686–690.
-
30)
-
25. Gur, D., Zheng, B., Lederman, D., Dhurjaty, S., Sumkin, J., Zuley, M.: ‘A support vector machine designed to identify breasts at high risk using multi-probe generated REIS signals: a preliminary assessment’. Proc. SPIE, 2010, 7627, pp. 76271B–76271B–10.
-
31)
-
20. Kim, B.S., Isaacson, D., Xia, H., Kao, T.J., Newell, J.C., Saulnier, G.J.: ‘A method for analyzing electrical impedance spectroscopy data from breast cancer patients’, Physiol. Meas., 2007, 28, pp. S237–S246 (doi: 10.1088/0967-3334/28/7/S17).
-
32)
-
33. Robinson, M.P., Richardson, M.J., Green, J.L., Preece, A.W.: ‘New materials for dielectric simulation of tissues’, Phys. Med. Biol., 1991, 36, (12), pp. 1565–1571 (doi: 10.1088/0031-9155/36/12/002).
-
33)
-
17. Estrela da Silva, J., Marques de Sa, J.P., Jossinet, J.: ‘Classification of breast tissue by electrical impedance spectroscopy’, Med. Biol. Eng. Comput., 2000, 38, pp. 26–30 (doi: 10.1007/BF02344684).
-
34)
-
7. Scholz, B., Anderson, R.: ‘On electrical impedance scanning – principles and simulations’, Electromedia, 2000, 68, pp. 35–44.
-
35)
-
19. Liu, R., Dong, X., Fu, F., et al: ‘Multifrequency parameter mapping of electrical impedance scanning using two kinds of circuit model’, Physiol. Meas., 2007, 28, pp. S85–S100 (doi: 10.1088/0967-3334/28/7/S07).
-
36)
-
37)
-
28. Polk, C., Postow, E(Eds.): ‘CRC handbook of biological effects of electromagnetic fields’ (CRC Press, Boca Raton, FL, 1986), pp. 27–96.
-
38)
-
24. Laufer, S., Rubinsky, B.: ‘Tissue characterization with an electrical spectroscopy SVM classifier’, IEEE Trans. Biomed. Eng., 2009, 56, (2), pp. 525–528 (doi: 10.1109/TBME.2008.2003105).
-
39)
-
12. Diebold, T., Jacobi, V., Scholz, B., et al: ‘Value of electrical impedance scanning (EIS) in the evaluation of BI-RADSTM III/IV/V-lesions’, Technol. Cancer Res. Treat., 2005, 4, pp. 93–97.
-
40)
-
26. Daliri, M.R.: ‘Combining extreme learning machines using support vector machines for breast tissue classification’, Comput. Meth. Biomech. Biomed. Eng., 2013. .
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-smt.2013.0087
Related content
content/journals/10.1049/iet-smt.2013.0087
pub_keyword,iet_inspecKeyword,pub_concept
6
6