EFFECTS OF DIELECTRIC HETEROGENEITY IN THE PERFORMANCE OF BREAST TUMOUR CLASSIFIERS

Breast cancer detection using Ultra Wideband Radar has been thoroughly investigated over the last decade. This breast imaging modality is based on the dielectric properties of normal and cancerous breast tissue at microwave frequencies. However, the dielectric properties of benign and malignant tumours are very similar, so tumour classiflcation based on dielectric properties alone is not feasible. Therefore, classiflcation methods based on the Radar Target Signature of tumours need to be further developed to classify tumours as either benign or malignant. Several studies have addressed the issue of tumour classiflcation based on the size, shape and surface texture of the tumour. In general, these studies examined the performance of classiflcation algorithms in primarily dielectrically homogeneous breast models. These relatively simplistic models do not provide a realistic test platform for the evaluation of tumour classiflcation algorithms. This paper examines the classiflcation of tumours under realistic dielectrically heterogeneous conditions. Four difierent heterogeneous scenarios are considered, with varying levels of heterogeneity and complexity. In this paper, the performance and robustness of tumour classiflcation algorithms under these realistic conditions are examined and discussed.

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

[2]  Soon Yim Tan,et al.  A novel method for microwave breast cancer detection , 2008 .

[3]  Barry D. Van Veen,et al.  Breast Tumor Characterization Based on Ultrawideband Microwave Backscatter , 2008, IEEE Transactions on Biomedical Engineering.

[4]  Larry D. Travis,et al.  Light scattering by nonspherical particles : theory, measurements, and applications , 1998 .

[5]  Edward Jones,et al.  Support Vector Machines for the Classification of Early-Stage Breast Cancer Based on Radar Target Signatures , 2010 .

[6]  Yifan Chen,et al.  Multiple-Input Multiple-Output Radar for Lesion Classification in Ultrawideband Breast Imaging , 2010, IEEE Journal of Selected Topics in Signal Processing.

[7]  Karri Muinonen,et al.  Introducing the Gaussian shape hypothesis for asteroids and comets , 1998 .

[8]  K. T. Mathew,et al.  ACTIVE MICROWAVE IMAGING FOR BREAST CANCER DETECTION , 2006 .

[9]  Elise C. Fear,et al.  Microwave system for breast tumor detection , 1999 .

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

[11]  M. O’Halloran,et al.  Evaluation of Features and Classifiers for Classification of Early-stage Breast Cancer , 2011 .

[12]  A. Taflove,et al.  Two-dimensional FDTD analysis of a pulsed microwave confocal system for breast cancer detection: fixed-focus and antenna-array sensors , 1998, IEEE Transactions on Biomedical Engineering.

[13]  Edward Jones,et al.  Contrast Enhanced Beamforming for Breast Cancer Detection , 2011 .

[14]  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.

[15]  M. Lindstrom,et al.  A large-scale study of the ultrawideband microwave dielectric properties of normal breast tissue obtained from reduction surgeries , 2007, Physics in medicine and biology.

[16]  Martin Glavin,et al.  TRANSMITTER-GROUPING ROBUST CAPON BEAM- FORMING FOR BREAST CANCER DETECTION , 2010 .

[17]  S.H. Zainud-Deen,et al.  Breast cancer detection using a hybrid Finite difference frequency domain and particle swarm optimization techniques , 2008, 2008 National Radio Science Conference.

[18]  J. Elmore,et al.  Ten-year risk of false positive screening mammograms and clinical breast examinations. , 1998, The New England journal of medicine.

[19]  Sabira Khatun,et al.  UWB imaging for breast cancer detection using neural network. , 2009 .

[20]  P. Huynh,et al.  The false-negative mammogram. , 1998, Radiographics : a review publication of the Radiological Society of North America, Inc.

[21]  Edward Jones,et al.  Investigation of Classifiers for Early-Stage Breast Cancer Based on Radar Target Signatures , 2010 .

[22]  M. O’Halloran,et al.  Spiking Neural Networks for Breast Cancer Classification Using Radar Target Signatures , 2010 .

[23]  Paul M. Meaney,et al.  A clinical prototype for active microwave imaging of the breast , 2000 .

[24]  Yifan Chen,et al.  Application of the MIMO radar technique for lesion classification in UWB breast cancer detection , 2009, 2009 17th European Signal Processing Conference.

[25]  Ian J Craddock,et al.  Numerical investigation of breast tumour detection using multi-static radar , 2003 .

[26]  Cheong Boon Soh,et al.  Breast Lesion Classification Using Ultrawideband Early Time Breast Lesion Response , 2010, IEEE Transactions on Antennas and Propagation.

[27]  Yifan Chen,et al.  Effect of Lesion Morphology on Microwave Signature in 2-D Ultra-Wideband Breast Imaging , 2008, IEEE Transactions on Biomedical Engineering.

[28]  Yifan Chen,et al.  Feasibility Study of Lesion Classification via Contrast-Agent-Aided UWB Breast Imaging , 2010, IEEE Transactions on Biomedical Engineering.

[29]  Martin Glavin,et al.  Data Independent Radar Beamforming Algorithms for Breast Cancer Detection , 2010 .

[30]  Karri Muinonen,et al.  Light Scattering by Stochastically Shaped Particles , 2000 .