Share Email Print

Spie Press Book

Multimodality Breast Imaging: Diagnosis and Treatment
Editor(s): E. Y. K. Ng; U. Rajendra Acharya; Rangaraj M. Rangayyan; Jasjit S. Suri
Format Member Price Non-Member Price

Book Description

Breast cancer is an abnormal growth of cells in the breast, usually in the inner lining of the milk ducts or lobules. It is currently the most common type of cancer in women in developed and developing countries. The number of women affected by breast cancer is gradually increasing and remains as a significant health concern. Researchers are continuously working to develop novel techniques to detect early stages of breast cancer. This book covers breast cancer detection, diagnosis, and treatment using different imaging modalities such as mammography, magnetic resonance imaging, computed tomography, positron emission tomography, ultrasonography, infrared imaging, and other modalities. The information and methodologies presented will be useful to researchers, doctors, teachers, and students in biomedical sciences, medical imaging, and engineering.

Book Details

Date Published: 4 March 2013
Pages: 572
ISBN: 9780819492944
Volume: PM227

Table of Contents
SHOW Table of Contents | HIDE Table of Contents
List of Contributors
Acronyms and Abbreviations
1 Detection of Architectural Distortion in Prior Mammograms Using Statistical Measures of Angular Spread
Rangaraj M. Rangayyan, Shantanu Banik, and J. E. Leo Desautels
1.1 Introduction
1.2 Experimental Setup and Database
1.3 Methods
      1.3.1 Detection of potential sites of architectural distortion
      1.3.2 Analysis of angular spread
      1.3.3 Characterization of angular spread
      1.3.4 Measures of angular spread
      1.3.5 Feature selection and pattern classification
1.4 Results
      1.4.1 Analysis with various sets of features
      1.4.2 Statistical significance of differences in ROC analysis
      1.4.3 Reduction of FPs
      1.4.4 Statistical significance of the differences in FROC analysis
      1.4.5 Effects of the initial number of ROIs selected
1.5 Discussion
      1.5.1 Comparative analysis with related previous works
      1.5.2 Comparative analysis with other works
      1.5.3 Limitations
1.6 Conclusion

2 Texture-based Automated Detection of Breast Cancer Using Digitized Mammograms: A Comparative Study
U. Rajendra Acharya, E. Y. K. Ng, Jen-Hong Tan, S. Vinitha Sree, and Jasjit S. Suri
2.1 Introduction
2.2 Data Acquisition and Preprocessing
2.3 Feature extraction
      2.3.1 Gray level co-occurrence matrix
      2.3.2 Run length matrix
2.4 Classifiers
      2.4.1 Support vector machine
      2.4.2 Gaussian mixture model
      2.4.3 Fuzzy Sugeno classifier
      2.4.4 k-nearest neighbor
      2.4.5 Probabilistic neural network
      2.4.6 Decision tree
2.5 Results
      2.5.1 Performance measures
      2.5.2 Receiver operating characteristics
      2.5.3 Classification results
      2.5.4 Graphical user interface
2.6 Discussion
2.7 Conclusions

3 Case-based Clinical Decision Support for Breast Magnetic Resonance Imaging
Ye Xu and Hiroyuki Abe
3.1 Introduction
3.2 Methodologies
      3.2.1 Data preparation
      3.2.2 Block diagram of our case-based approach
      3.2.3 Features to calculate on breast MRI images
      3.2.4 Collections for ground truth of similarity from data
      3.2.5 Evaluation
3.3 Results and Discussion
3.4 Conclusion

4 Registration, Lesion Detection, and Discrimination for Breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging
Valentina Giannini, Anna Vignati, Massimo De Luca, Silvano Agliozzo, Alberto Bert, Lia Morra, Diego Persano, Filippo Molinari, and Daniele Regge
4.1 Introduction
4.2 Registration
      4.2.1 Method
      4.2.2 Results
4.3 Lesion Detection
      4.3.1 Method
      4.3.2 Results
4.4 Lesion Discrimination
      4.4.1 Method
      4.4.2 Results
4.5 Discussion and Conclusions

5 Advanced Modality Imaging of the Systemic Spread of Breast Cancer
Cher Heng Tan
5.1 Introduction
5.2 Nodal Disease
      5.2.1 Auxillary nodes
      5.2.2 Other draining nodes
5.3 Distant Metastases
      5.3.1 Pulmonary metastases
      5.3.2 Bone metastases
      5.3.3 Liver metastases
      5.3.4 Brain metastases
5.4 Treatment Response Evaluation: Response Evaluation Criteria in Solid Tumors (RECIST)
5.5 Surveillance: To Do or Not To Do?
5.6 Locoregional Recurrence
5.7 Summary

6 Nuclear Imaging with PET CT and PET Mammography
Andrew Eik Hock Tan and Wanying Xie
6.1 Introduction
6.2 Breast Cancer Molecular Pathology and PET
6.3 Diagnosis of Primary Breast Cancers
6.4 Staging of Breast Cancers
      6.4.1 Axillary nodal evaluation
      6.4.2 Mediastinal and internal mammary nodal evaluation
      6.4.3 Distant metastasis and overall staging impact of FDG PET
6.5 Response Assessment
6.6 Conclusion

7 3D Whole-Breast Ultrasonography
Ruey-Feng Chang and Yi-Wei Shen
7.1 Introduction
7.2 3D Whole-Breast Ultrasonography Machines
7.3 Related Studies of 3D Whole-Breast Ultrasonography
7.4 Conclusion

8 Diagnosis of Breast Cancer Using Ultrasound
Chui-Mei Tiu, Yi-Hong Chou, Chung-Ming Chen, and Jie-Zhi Cheng
8.1 Introduction
8.2 Instrument Requirements
      8.2.1 Equipment and transducer
      8.2.2 Image quality and equipment quality control
8.3 Examination Technique
      8.3.1 Patient positioning
      8.3.2 Scanning technique
      8.3.3 Doppler imaging and contrast-enhanced US
      8.3.4 Elastography
      8.3.5 Image labeling
8.4 Grayscale Ultrasonic Criteria of Breast Disease
      8.4.1 General criteria of interpretation
      8.4.2 Diagnosing cysts
      8.4.3 Differentiating solid lesions
      8.4.4 Diagnosing carcinoma
      8.4.5 Secondary signs of malignancy
      8.4.6 Evaluation of breast calcifications
8.5 Considerations in Interpreting US Examination Results
8.6 Ultrasonography of Malignant Tumors
      8.6.1 Invasive ductal carcinoma
      8.6.2 Mucinous carcinoma
      8.6.3 Medullary carcinoma
      8.6.4 Invasive lobular carcinoma
      8.6.5 Ductal carcinoma in situ
      8.6.6 Lobular carcinoma in situ
      8.6.7 Inflammatory carcinoma
      8.6.8 Lymphoma and metastases of the breast
8.7 Fibrocystic Changes and Breast Cysts
      8.7.1 Fibrocystic changes and benign
      8.7.2 Fibroadenomas
      8.7.3 Fibroadenoma variants
      8.7.4 Tubular adenomas and lactating adenomas
      8.7.5 Papilloma
      8.7.6 Intramammary lymph nodes
      8.7.7 Hamartomas
      8.7.8 Lipomas
      8.7.9 Pseudo-angiomatous stromal hyperplasia
      8.7.10 Hemangiomascarcinoma
      8.7.11 Invasive Phyllodes tumors
      8.7.12 Focal fibrosis
      8.7.13 Diabetic mastopathy
      8.7.14 Infections and abscesses of the breast
8.8 Clinical Usefulness of US-Guided Aspiration and Biopsy
      8.8.1 Ultrasound-guided breast aspiration
      8.8.2 Ultrasound-guided breast biopsy
      8.8.3 Vacuum-assisted biopsy
8.9 Conclusion

9 Abnormal Lesion Detection from Breast Thermal Images Using Chaos with Lyapunov Exponents
Mahnaz Etehadtavakol, E. Y. K. Ng, Caro Lucas, and Mohammed Ataei
9.1 Introduction
9.2 Time Series
9.3 Time-Delay Embedding
9.4 Lyapunov Exponents
9.5 Computation of the Lyapunov Exponents
      9.5.1 Polynomial model
9.6 Generating the Time Series
9.7 Experimental Results and Discussion
      9.7.1 Fractal images
      9.7.2 Real-world IR images
9.8 Conclusion

10 Intelligent Rule-based Classification of Image Features for Breast Thermogram Analysis
Gerald Schaefer
10.1 Introduction
10.2 Image Features
10.3 Fuzzy Rule-based Classification
      10.3.1 Classification algorithm
      10.3.2 Experimental results
10.4 Ant Colony Optimization Classification
      10.4.1 Classification algorithm
      10.4.2 Experimental results
10.5 Conclusions

11 Infrared Imaging for Breast Cancer Detection with Proper Selection of Properties: From Acquisition Protocol to Numerical Simulation
Luciete A. Bezerra, Marília M. Oliveira, Marcus C. Araújo, Mariana J. A. Viana, Ladjane C. Santos, Francisco G. S. Santos, Tiago L. Rolim, Paulo R. M. Lyra, Rita C. F. Lima, Tiago B. Borschartt, Roger Resmini, and Aura Conci
11.1 Introduction
11.2 Computer-Aided Diagnosis
      11.2.1 Standardization in acquiring IR breast images
      11.2.2 Data storage
      11.2.3 Breast segmentation
      11.2.4 Extracting features
      11.2.5 Classification results
11.3 Several Approaches for Improving the Numerical Simulation of Temperature Profiles
      11.3.1 Surrogate geometry of the breast
      11.3.2 A parametric analysis to investigate IR sensitivity
      11.3.3 Estimation of some breast and tumor properties
11.4 Conclusions

12 Diffuse Optical Imaging of the Breast: Recent Progress
Jun Hui Ho, Jing Dong, and Kijoon Lee
12.1 Introduction
12.2 Theory
      12.2.1 Photon propagation model
      12.2.2 Diffuse optical spectroscopy
      12.2.3 Diffuse correlation spectroscopy
      12.2.4 Diffuse optical tomography
12.3 Classifiers
      12.3.1 Diffuse optical spectroscopy
      12.3.2 Diffuse correlation spectroscopy
      12.3.3 Diffuse optical tomography
12.4 Clinical Applications
      12.4.1 Breast cancer detection/characterization
      12.4.2 Therapy monitoring
12.5 Future of DOI of the Breast
      12.5.1 Structural illumination
      12.5.2 Spectral derivative
      12.5.3 New parameters
12.6 Conclusion

13 Computer Vision Theoretic Approach for Breast Cancer Diagnosis: Commonly Perceived Diagnostic Significance of Cytological Features and Feature Usability Analysis of an Existing Breast Cancer Database
Hrushikesh Garud, Debdoot Sheet, Jyotirmoy Chatterjee, Manjunatha Mahadevappa, Ajoy Kumar Ray, and Arindam Ghosh
13.1 Introduction
13.2 Commonly Perceived Significance of Cytological Features in Breast FNAC
      13.2.1 Overview of the survey
      13.2.2 Opinion of the experts
13.3 Analysis of the Wisconsin Diagnostic Breast Cancer (WDBC) Database
      13.3.1 Ranking of features using feature usability index
      13.3.2 Feature selection
13.4 Conclusions

14 Radiofrequency Ablation of Breast Neoplasms
José Luis del Cura
14.1 Introduction
14.2 Radiofrequency
      14.2.1 Concept
      14.2.2 Technical issues
14.3 Radiofrequency Ablation in the Breast
14.4 Technique of Ablation
14.5 Outcomes
14.6 Complications
14.7 Conclusions and Future Trends

15 Minimally Invasive Thermal Ablation for Breast Cancer
Feng Wu
15.1 Introduction
15.2 Methods of Thermal Ablation Technique
      15.2.1 Radiofrequency ablation (RFA)
      15.2.2 Laser ablation (LA)
      15.2.3 Microwave ablation (MWA)
      15.2.4 Cryoablation
      15.2.5 High-intensity focused ultrasound (HIFU) ablation
15.3 Scientific Principles of Thermal Ablation
15.4 Mechanisms of Thermal Ablation
      15.4.1 Direct thermal and nonthermal effects on tumors
      15.4.2 Thermal effects on tumor vasculature
      15.4.3 Indirect effects on tumor
15.5 Clinical Studies on Thermal Ablation of Breast Cancer
      15.5.1 Radiofrequency ablation
      15.5.2 Laser ablation
      15.5.3 Microwave ablation
      15.5.4 Cryoablation
      15.5.5 High-intensity focused ultrasound ablation
15.6 Antitumor Immune Response after Thermal Ablation
      15.6.1 Antitumor immune response after RFA
      15.6.2 Antitumor immune response after LA
      15.6.3 Antitumor immune response after cryoablation
      15.6.4 Antitumor immune response after MWA
      15.6.5 Antitumor immune response after HIFU ablation
15.7 Summary

16 Correlated Microwave Acoustic Imaging for Breast Cancer Detection
Yuanjin Zheng, Fei Gao, and Zhiping Lin
16.1 Introduction
16.2 Emerging Microwave-based Imaging Modality
      16.2.1 Dielectric property of biological tissue
      16.2.2 Microwave imaging
      16.2.3 Microwave-induced thermo-acoustic imaging
16.3 Correlated Microwave Acoustic Imaging: Numerical Example
      16.3.1 Image reconstruction algorithm
      16.3.2 Numerical simulation results
16.4 Preliminary Prototyping
      16.4.1 Collecting microwaves and acoustic waves simultaneously
      16.4.2 UWB transmitter design
16.5 Conclusion

17 Diagnostic Sensing of Specific Proteins in Breast Cancer Cells Using Hollow-Core Photonic Crystal Fiber
Vadakke Matham Murukeshan, Vengalathunadakal Kuttinarayanan Shinoj, Saraswathi Padmanabhan, and Parasuraman Padmanabhan
17.1 Introduction
17.2 Photonic Crystal Fibers
      17.2.1 Refractive-index scaling law
      17.2.2 Selection of fibers
17.3 Sensing Mechanism Based on Evanescent Waves
      17.3.1 Conventional-fiber-based evanescent wave sensing
      17.3.2 Evanescent wave sensing using HC-PCF
17.4 Materials and Methods
      17.4.1 Cell culture and sample preparation
17.5 Results and Discussion
      17.5.1 HC-PCF-based fluorescence detection
17.6 Conclusion

18 Quality Assurance in Digital Mammography
Kwan-Hoong Ng, Tânia Aparecida Correia Furquim, and Noriah Jamal
18.1 Introduction
      18.1.1 Scope
18.2 Technical Quality Control
18.3 Testing by Medical Physicists and Equipment Performance
      18.3.1 Mammography unit assembly evaluation
      18.3.2 Compression force and thickness accuracy
      18.3.3 Site technique factors for SDNR (radiographer baseline)
      18.3.4 Automatic exposure control evaluation
      18.3.5 Baseline for detector performance
      18.3.6 Spatial linearity and geometric distortion of the detector
      18.3.7 Detector ghosting
      18.3.8 Detector uniformity and artifact evaluation
      18.3.9 Modulation transfer function
      18.3.10 Limiting spatial resolution
      18.3.11 Half-value layer
      18.3.12 Incident air kerma at the entrance surface of PMMA slabs
      18.3.13 Mean glandular dose
      18.3.14 Collimation system
      18.3.15 Image display quality
      18.3.16 Laser printer (where applicable)
      18.3.17 Phantom image quality
18.4 Technologist Testing
      18.4.1 Inspection, cleaning, and viewing conditions of monitors and view boxes
      18.4.2 Laser printer
      18.4.3 Phantom image quality
      18.4.4 Digital mammography equipment daily checklist
      18.4.5 Daily and monthly flat-field phantom image test
      18.4.6 Visual inspection for artifacts (CR systems only)
      18.4.7 Image plate erasure (CR systems only)
      18.4.8 Monitor QC
      18.4.9 Weekly QC test object and full-field artifacts
      18.4.10 Safety and function checks of examination room and equipment
      18.4.11 Repeat image analysis
      18.4.12 Spatial resolution test (CR and scanning systems only)
Appendix 18.1 ACR Summary of Medical Physicist's and Technologist's QC Tests: General Electric
Appendix 18.2 ACR Summary of Medical Physicist's and Technologist's QC Tests: Hologic
Appendix 18.3 IAEA Safety and Function Checklist of Examination Room and Equipment



Breast cancer is an abnormal growth of cells in the breast, usually in the inner lining of the milk ducts or lobules. It is currently the most common type of cancer in women in developed and developing countries. The number of women affected by breast cancer is gradually increasing and remains as a significant health concern. Hence, the early detection of breast cancer can improve the survival rate and quality of life. Therefore, today, newer modalities are available to more accurately detect breast cancer. Researchers are continuously working to develop novel techniques to detect early stages of breast cancer. This book covers breast cancer detection using different imaging modalities such as mammography, magnetic resonance imaging, computed tomography, positron emission tomography, ultrasonography, infrared imaging, and other modalities.

Architectural distortion is one of the major causes of false-negative findings in the detection of early stages of breast cancer. Chapter 1 presents methods for computer-aided detection of architectural distortion in mammograms acquired prior to the diagnosis of breast cancer in the interval between scheduled screening sessions. The results are promising and indicate that the proposed methods can detect architectural distortion in prior mammograms taken 15 months (on average) before clinical diagnosis of breast cancer, with a sensitivity of 0.8 at 5.2 false positives per patient.

A computer-aided system for the automated detection of normal, benign, and cancerous breasts using texture features extracted from digitized mammograms and data mining techniques is proposed in Chapter 2. The novelty of this work is to automatically classify the mammogram into normal, benign, and malignant classes using the texture features alone, with an efficiency of 93.3% and sensitivity of 92.3% using a fuzzy classifier.

Breast cancer diagnosis by combination of fuzzy systems and an ant colony optimization algorithm is proposed in Chapter 3. Results on the breast cancer diagnosis dataset from the University of California Irvine machine learning repository show that the proposed FUZZY-ACO would be capable of classifying cancer instances with a high accuracy rate and adequate interpretability of extracted rules.

Chapter 4 discusses a computer-aided diagnosis system tested on magnetic resonance datasets obtained from different scanners, with a variable temporal and spatial resolution and on both fat-sat and non–fat-sat images, and has shown promising results. This type of system could potentially be used for early diagnosis and staging of breast cancer to reduce reading time and to improve detection, especially of the smaller satellite nodules.

Imaging plays a pivotal role in the evaluation of metastatic spread of breast cancer disease. Chapter 5 gives an overview of the recent developments in breast cancer imaging, in terms of instrumentation and clinical applications. In addition, the theoretical framework behind advanced imaging modalities is highlighted to provide background knowledge to the reader, and potential future research directions are also presented.

The role of positron emission tomography is established in the practice of oncology. The advances in functional and molecular imaging techniques have increased the accuracy in the diagnostic evaluation of breast cancers and is discussed in detail in Chapter 6.

Chapter 7 discusses 3D whole-breast ultrasonography, which can provide the entire breast anatomy for later review. The 3D whole-breast ultrasound procedure and the training time are simpler and shorter than the traditional 2D US. It also provides interoperator consistency, and its reproducibility is better for follow-up studies.

Recent progress in medical ultrasound has paved the way for the evaluation of breast cancer. State-of-the-art high-resolution ultrasound can detect tiny breast lesions as small as 1–2 mm in size, and sometimes microcalcifications even less than 0.5 mm, or small carcinomas 3–6 mm in diameter. Chapter 8 presents an overview of the recent developments in ultrasound imaging of breast cancer, in terms of instrumentation and clinical applications.

Nonlinear features such as Lyapunov exponents are used to differentiate malignant and benign breast thermograms in Chapter 9. This work can be extended for classifying different stages of breast cancer. The authors are currently working toward these objectives.

A set of image features describing bilateral differences between left and right breast regions in thermograms is described in Chapter 10. These features are then used in a pattern classification stage to discriminate malignant cases from benign ones. Classification is performed by fuzzy if-then rules and applies a genetic algorithm to optimize the rule base, and secondly uses an ant colony optimization classification algorithm. Both approaches have shown good classification accuracy.

Infrared imaging has shown to be a promising technique for the early diagnosis of breast pathologies and as a screening technique. The concept of a combined diagnostic enables a high degree of specificity and sensibility in such diagnosis. Chapter 11 presents a concept of merging information from the images with other modalities of examination, such as mammograms and ultrasound, in order to improve the early detection of breast pathologies, including cancer.

Chapter 12 discusses diffuse optical imaging, which makes use of diffuse light to probe deep tissues by taking advantage of low tissue absorption within the near-infrared wavelength range (650–900 nm). The optical measurements obtained can be used to calculate optical properties, namely absorption and scattering within tissues. This, in turn, can provide information about physiological parameters within tissues, such as oxy- and deoxy-haemoglobin, and water and lipid, all of which can be utilized in the detection, characterization, and therapy monitoring of breast cancer.

Cytopathology is a branch of pathology that studies and diagnoses diseases on the cellular level, using samples of free cells or tissue fragments. Chapter 13 describes the results of a study of the features that are used by physicians and computers to diagnose cancer based on features in fineneedle aspiration cytology images. It discusses the significance of a cytological feature in representing its true ability to discriminate benign and malignant conditions of a breast lump in the Wisconsin Diagnostic Breast Cancer database.

Only a small number of studies have been reported on breast radiofrequency ablation, and most of them have included the posterior surgical excision of the treated breast. Chapter 14 presents the future trends in the development of more-specific radiofrequency algorithms for breast cancer treatment, to improve the results, determine the setting of the specific indications for the technique, and expand the study of long-term results and survival.

Breast conserving therapy is the gold-standard option for patients with early-stage breast cancer. The surgical excision removes the entire tumor with a negative surgical margin and helps to preserve the breast tissue as far as possible. Chapter 15 explains minimally invasive ablative techniques, which may offer complete tumor ablation, with less psychological morbidity, better cosmetic results, and shorter hospital stay.

A microwave-based imaging modality is an emerging noninvasive medical imaging approach exploring the dielectric property of biological tissue that shows great potential in breast cancer detection. Chapter 16 discusses a correlated microwave acoustic imaging modality and numerical simulation using finite-difference time-domain analysis. It is clearly shown that a combination of microwave-based imaging modalities is expected to provide an efficient diagnostic method for breast cancer detection in the future.

Fluorescence-based bioassays are novel diagnostic tools that are available to clinicians for deciding future treatment and to researchers for monitoring biological functions that may lead to novel investigations. The different aspects of photonic crystal fiber, its guiding mechanism, the refractive index law, etc. are analyzed and explained in Chapter 17. The proposed methodology is implemented in an array format of immuno recognition of specific proteins using a hollow-core photonic crystal fiber.

An overview of a quality-assurance program for digital mammography is discussed in Chapter 18. This overview includes the quality-control test procedures based on the American College of Radiology and the International Atomic Energy Agency. The role of medical physicists in the mammography quality-assurance programs, including acceptance, annual, and regular quality-control testing, is briefly presented.

In this book, we have made an honest effort to present information and methodologies for accurate diagnosis of breast cancer to help researchers, doctors, teachers, and students in biomedical science and engineering.

E. Y. K. Ng
U. Rajendra Acharya
Rangaraj M. Rangayyan
Jasjit S. Suri
February 2013

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?