Can a MM-wave ultra-wideband ANN-based radar data processing approach be used for breast cancer detection?

The paper compares the waveform of a millimeter (MM)-wave differentiated Gaussian pulse (DGP) centered at 30 GHz with others DGPs centered at different microwave frequencies. The performance are assessed using an artificial neural network (ANN)-based radar data processing technique for breast cancer detection. The radar signals are measured using a set of realistic two-dimensional (2D) breast geometries derived from the realistic three-dimensional (3D) breast phantoms provided by the numerical breast phantom repository of the University of Wisconsin cross-disciplinary electromagnetic laboratory (UWCEM). The results show that, using the DGP of central frequency 30 GHz, tumors are detected with sensitivity of 88%, a specificity of 90%, and an overall accuracy of 89%.

[1]  Gaussian vs differentiated gaussian as the input pulse for ground penetrating radar applications , 2007, 2007 International Conference on Industrial and Information Systems.

[2]  S. Caorsi,et al.  A Breast Cancer Detection Approach Based on Radar Data Processing using Artificial Neural Network , 2016 .

[3]  Antonios Giannopoulos,et al.  Modelling ground penetrating radar by GprMax , 2005 .

[4]  M. Lindstrom,et al.  A large-scale study of the ultrawideband microwave dielectric properties of normal, benign and malignant breast tissues obtained from cancer surgeries , 2007, Physics in medicine and biology.

[5]  Francois P. S. Chin,et al.  Entropy-Based Time Window for Artifact Removal in UWB Imaging of Breast Cancer Detection , 2006, IEEE Signal Processing Letters.

[6]  Constantino Carlos Reyes-Aldasoro,et al.  A Robust and Artifact Resistant Algorithm of Ultrawideband Imaging System for Breast Cancer Detection , 2015, IEEE Transactions on Biomedical Engineering.

[7]  M. Okoniewski,et al.  Highly Accurate Debye Models for Normal and Malignant Breast Tissue Dielectric Properties at Microwave Frequencies , 2007, IEEE Microwave and Wireless Components Letters.

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  X. Li,et al.  Confocal microwave imaging for breast cancer detection: localization of tumors in three dimensions , 2002, IEEE Transactions on Biomedical Engineering.

[10]  Xu Li,et al.  Microwave imaging via space-time beamforming for early detection of breast cancer , 2003 .

[11]  Barry D. Van Veen,et al.  A TSVD Analysis of Microwave Inverse Scattering for Breast Imaging , 2012, IEEE Transactions on Biomedical Engineering.

[12]  Q. Fang,et al.  Viable Three-Dimensional Medical Microwave Tomography: Theory and Numerical Experiments , 2010, IEEE Transactions on Antennas and Propagation.

[13]  Cheong Boon Soh,et al.  FREQUENCY DOMAIN SKIN ARTIFACT REMOVAL METHOD FOR ULTRA-WIDEBAND BREAST CANCER DETECTION , 2009 .

[14]  S.C. Hagness,et al.  A confocal microwave imaging algorithm for breast cancer detection , 2001, IEEE Microwave and Wireless Components Letters.

[15]  Magda El-Shenawee,et al.  Review of Electromagnetic Techniques for Breast Cancer Detection , 2011, IEEE Reviews in Biomedical Engineering.

[16]  S. Caorsi,et al.  Skin artifact removal technique for breast cancer radar detection , 2016 .

[17]  Elise C. Fear,et al.  Reduction of skin reflections in radar-based microwave breast imaging , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Ian J Craddock,et al.  Improved Delay-and-Sum Beamforming Algorithm for Breast Cancer Detection , 2008 .