Frequency Domain Breast Lesion Classification Using Ultra-Wideband Lesion Response - Ultra-Wideband and 60 GHz Communications for Biomedical Applications - page 247

using these vectors. The performance of the neural network classifiers is evaluated
and compared. Results show that cascade Kolmogrov architecture has the best per-
formance among the network architectures compared. To improve the accuracy of
the classifier, PCA is used to reduce the vector dimension. The resulting classi-
fier achieves lesion classification accuracy of 75.19 % which is higher than similar
existing methods [ 21 , 32 ].
References
1. Center for Disease Control and Prevention (CDC). Statistics (2013), http://www.cdc.gov/
cancer/breast/statistics
2. E.J. Bond, X. Li, S.C. Hagness, B.D. Van Veen, Microwave imaging via space-time beam-
forming for early detection of breast cancer. IEEE Trans. Antennas Propag. 51 (8), 1690-1705
(2003)
3. D. Byrne, M. O'Halloran, M. Glavin, E. Jones, Data independent radar beamforming
algorithms for 2 cancer detection. PIER. 107 , 331-348 (2010)
4. Y. Chen, I.J. Craddock, P. Kosmas, M. Ghavami, P. Rapajic, Multiple-input multiple-output
radar for lesion classification in ultra-wideband breast imaging. IEEE J. Selected Topics Signal
Processing. 4 (1), 187-201 (2010)
5. Y. Chen, I.J. Craddock, P. Kosmas, Feasibility study of lesion classification via contrast-agent-
aided UWB breast imaging. IEEE Trans. Biomed. Eng. 57 (5), 1003-1007 (2010)
6. Y. Chen, E. Gunawan, K.S. Low, S.-C. Wang, C.B. Soh, T.C. Putti, Effect of lesion morphology
on microwave signature in 2-d ultra-wideband breast imaging. IEEE Trans. Biomed. Eng. 55 (8),
2011-2021 (2008)
7. Y. Chen, E. Gunawan, K.S. Low, S.-C. Wang, C.B. Soh, L.L. Thi, Time of arrival data fusion
method for two-dimensional ultra-wideband breast cancer detection. IEEE Trans. Antennas
Propag. 55 (10), 2852-2865 (2007)
8. R.C. Conceicao, M. O'Halloran, M. Glavin, E. Jones, Support vector machines for the clas-
sification of early-stage breast cancer based on radar target signatures. PIER B. 23 , 311-327
(2010)
9. R.C. Conceicao, M. O'Halloran, E. Jones, M. Glavin, Investigation of classifiers for early-stage
breast cancer based on 2 target signatures. PIER. 105 , 295-311 (2010)
10. S.K. Davis, H. Tandradinata, S.C. Hagness, B.D. Van Veen, Ultra-wideband microwave breast
cancer detection: a detection-theoretic approach using the generalized likelihood ratio test.
IEEE Trans. Biomed. Eng. 52 (7), 1237-1250 (2005)
11. S.C. Hagness, A. Taflove, J.E. Bridges, in Antennas and Propagation Society International
Symposium . FDTD modeling of a coherent-addition antenna array for early-stage detection of
breast cancer, vol. 2 (IEEE, Atlanta, 1998), pp. 1220-1223
12. S.C. Hagness, A. Taflove, J.E. Bridges, Three-dimensional FDTD analysis of a pulsed mi-
crowave confocal system for breast cancer detection: design of an antenna-array element.
IEEE Trans. Antennas Propag. 47 (5), 783-791 (1999)
13. S.C. Hagness, A. Taflove, J.E. Bridges, in Engineering in Medicine and Biology Society . FDTD
analysis of a pulsed microwave confocal system for breast cancer detection. Proceedings of
the 19th Annual International Conference of the IEEE, vol. 6, (IEEE, Chicago, 1997), pp.
2506-2508
14. H. Kanj, M. Popovic, A novel ultra-compact broadband antenna for microwave 2 tumor
detection. PIER. 86 , 169-198 (2008)
15. M. Klemm, I.J. Craddock, J.A. Leendertz, A. Preece, R. Benjamin, Radar-based breast cancer
detection using a hemispherical antenna array—experimental results. IEEE Trans. Antennas
Propag. 57 (6), 1692-1704 (2009)