This reference text explores cutting edge research into the detection of breast cancer using Microwave Imaging. Early breast cancer detection is vital for reducing mortality rates. Within this book Microwave scattering and microwave imaging based cancer detection are analysed as well as breast anatomy and breast cancer types. The book discusses 3-D level set based optimization as well as the Finite difference time domain (FDTD) technique. Advanced methods in image reconstruction techniques and Group Theory are explained with application to computation reduction. Machine learning-based advanced methods are also described for breast cancer detection.
This book is highly useful for the academic community working in biomedical imaging, electromagnetic and microwave imaging, breast cancer imaging, inverse scattering and optimization.
Key Features:
Breast cancer screening techniques are described and with advantages and disadvantages
Multiple frequency inverse scattering is discussed
Microwave imaging basics with detection analysis are explained in detail
Includes 3-D level set based optimization
Presents advanced methods on image-based reconstruction techniques
Author(s): Hardik N. Patel, Deepak K. Ghodgaonkkar, Jasjit S. Suri
Publisher: IOP Publishing
Year: 2022
Language: English
Pages: 262
City: Bristol
PRELIMS.pdf
Preface
Acknowledgements
Author biographies
Hardik N Patel
Deepak K Ghodgaonkar
Jasjit S Suri
CH001.pdf
Chapter 1 Introduction to breast cancer
1.1 Introduction to cancer
1.2 Worldwide cancer statistics
1.3 Breast cancer statistics
1.3.1 Breast cancer prediction
1.4 Breast anatomy and breast cancer
1.5 Summary
References
CH002.pdf
Chapter 2 Introduction to breast cancer detection techniques
2.1 Imaging modalities for breast cancer screening
2.2 Mammography
2.2.1 History of mammography
2.2.2 Basic understanding of mammography
2.2.3 Advantages and disadvantages of mammography
2.3 Ultrasound imaging
2.3.1 History of ultrasound
2.3.2 Physics of ultrasound
2.3.3 Current status of ultrasound imaging
2.3.4 Advantages and disadvantages of ultrasound
2.4 Magnetic resonanace imaging
2.4.1 Short history of MRI
2.4.2 Working principle of MRI
2.4.3 Advantages and disadvantages of MRI
2.5 Positron emission tomography
2.5.1 Short history of PET
2.5.2 Advantages and disadvantages of PET
2.6 Diffuse optical tomography
2.6.1 Short history of optical tomography
2.6.2 Advantages and disadvantages of diffuse optical tomography
2.7 Electrical impedance tomography
2.7.1 Advantages and disadvantages of EIT
2.8 Computed tomography (CT)
2.8.1 Short history of CT
2.8.2 Advantages and disadvantages of CT
2.9 Microwave imaging
2.9.1 Passive microwave imaging
2.9.2 Active microwave imaging
2.10 Comparison of mammography, MRI and ultrasound
2.11 Overview of image reconstruction methods
2.11.1 Algebraic reconstruction
2.11.2 Analytic reconstruction
2.11.3 Statistical reconstruction
2.11.4 Learned iterative reconstruction
2.12 Summary
References
CH003.pdf
Chapter 3 Introduction to microwave imaging
3.1 Introduction
3.2 Introduction to passive microwave imaging
3.2.1 Emission principles
3.2.2 Radiative transfer
3.2.3 Bio-heat transfer
3.2.4 Temperature resolution
3.3 Microwave radiometry for cancer detection
3.3.1 Multiprobe radiometric imaging
3.3.2 Multi-frequency microwave radiometry
3.4 Active microwave imaging
3.5 Summary
References
CH004.pdf
Chapter 4 Finite difference time domain method for microwave breast imaging
4.1 Overview of computational electromagnetic methods
4.1.1 Low frequency methods
4.1.2 High frequency methods
4.2 Motivation
4.3 Overview of FDTD
4.4 Derivation of basic FDTD update equations
4.5 Polarization current density equation derivation for numerical breast phantom region
4.6 Electric field update equation derivation for numerical breast phantom region
4.7 Derivation of electric field update equations for PML region
4.8 Magnetic field update equations
4.9 Steps for FDTD implementation
4.10 Simulation parameters
4.11 Results
4.12 Summary
References
CH005.pdf
Chapter 5 3D level set based optimization
5.1 Multiple frequency inverse scattering problem formulation
5.2 Introduction
5.3 Problem formulation
5.4 Review of previous work
5.5 Theoretical foundations
5.5.1 Evolution approach
5.5.2 Optimization approach
5.6 Single 3D level set function based optimization
5.7 Two 3D level set function based optimization
5.7.1 3D level set based regularized optimization
5.7.2 Steps for 3D level set based optimization implementation
5.8 Simulation parameters
5.9 Results
5.10 Summary
References
CH006.pdf
Chapter 6 Method of moments
6.1 Theoretical background
6.2 Problem formulation
6.3 Computation reduction using group theory
6.3.1 Human breast models
6.3.2 Symmetry exploitation using group theory
6.4 Inverse scattering problem formulation
6.5 Simulation parameters and noise consideration
6.6 Results
6.7 Summary
References
CH007.pdf
Chapter 7 Finite difference time domain for microwave imaging
7.1 Introduction to finite difference time domain
7.1.1 Grid size and stability
7.1.2 Input wave for Yee grid computations
7.1.3 Two-dimensional FDTD analysis of microwave breast imaging
7.1.4 Healthy breast tissue dielectric properties
7.1.5 Design of antenna array
7.2 Microwave image formation using confocal technique
7.3 Space–time beamforming
7.4 Removal of skin–breast artifact
7.5 FDTD based time reversal for microwave breast cancer detection
7.5.1 Matched filter FDTD based time reversal
7.6 Summary
References
CH008.pdf
Chapter 8 Review of machine learning based image reconstruction for different imaging modalities
8.1 Introduction
8.1.1 Image reconstruction (inverse) problem formulation
8.2 Traditional image reconstruction techniques
8.3 Machine learning techniques for image reconstruction
8.3.1 Machine learning based solution of inverse problems
8.3.2 Machine learning in computed tomography
8.3.3 Physics of low dose x-ray CT
8.4 Performance analysis of proposed approaches
8.5 Summary
References
CH009.pdf
Chapter 9 Review of machine learning based image reconstruction for microwave breast imaging
9.1 Motivation
9.2 Machine learning in microwave imaging
9.2.1 Current challenges in microwave breast diagnosis systems
9.2.2 Challenges in the development of robust machine learning classification models
9.3 Flow of the machine learning based microwave breast imaging for cancer diagnosis
9.3.1 Data collection through microwave scanning
9.3.2 Data processing
9.3.3 Diagnosis
9.4 Variational Bayesian inversion for microwave breast imaging
9.5 Deep neural networks for microwave breast imaging
9.6 Summary
References
CH010.pdf
Chapter 10 Microwave image reconstruction methods
10.1 Levenberg–Marquardt method
10.1.1 Forward problem
10.1.2 Inverse problem solution by using Levenberg–Marquardt
10.1.3 Choice of the regularization parameter
10.2 Gauss–Newton method
10.2.1 Forward problem formulation
10.2.2 The inverse problem formulation
10.2.3 Gauss–Newton optimization in general
10.2.4 Gauss–Newton method for the least squares
10.2.5 The BFGS quasi-Newton method
10.3 Born iterative method
10.4 Stochastic optimization methods for microwave imaging
10.4.1 Genetic algorithm
10.5 Summary
References
CH011.pdf
Chapter 11 The role of AI in diagnosis, treatment and monitoring of breast cancer during COVID-19 and ahead
11.1 Introduction
11.2 AI architectures
11.3 The role of artificial intelligence in diagnosis of breast cancer
11.4 The role of AI in treatment of breast cancer
11.5 The role of AI in monitoring of breast cancer
11.6 AI based integrated system for breast cancer management
11.7 Summary
References
APPA.pdf
Chapter
A.1 Numerical breast phantom
A.2 Antenna placement surrounding a numerical breast phantom
A.3 Immersion (surrounding) medium
References
APPB.pdf
Chapter
B.1 Debye model
B.2 Derivation of electric field update equations for numerical breast phantom region
B.3 Derivation of electric field update equations for PML region
B.4 Power calculations
References
