Computer-Aided Diagnosis in Breast Imaging: Trends and Challenges

Computer-Aided Diagnosis in Breast Imaging: Trends and Challenges

Lena Costaridou (University of Patras, Greece), Spyros Skiadopoulos (University of Patras, Greece), Anna Karahaliou (University of Patras, Greece), Nikolaos Arikidis (University of Patras, Greece) and George Panayiotakis (University of Patras, Greece)
DOI: 10.4018/978-1-60566-314-2.ch010
OnDemand PDF Download:


Breast cancer is the most common cancer in women worldwide. Mammography is currently the most effective modality in detecting breast cancer, challenged by the presence of dense breast parenchyma with relatively low specificity in distinguishing malignant from benign lesions. Breast ultrasound and Magnetic Resonance Imaging (MRI) are significant adjuncts to mammography providing additional diagnostic information. Various Computer-Aided Diagnosis (CADx) schemes have been proposed across modalities, acting as clinical tools that provide a “second opinion” to assist radiologists in the diagnostic task of lesion characterization by means of quantitative image feature extraction and classification methods. The advent of multimodality imaging broadens the role of CADx, in terms of complementary tissue properties analyzed. In this chapter, major stages of CADx schemes in breast imaging are reviewed, while challenges and trends are discussed and highlighted by corresponding application examples of CADx methodologies for microcalcification clusters in mammography and masses in Dynamic Contrast-Enhanced MRI.
Chapter Preview


Breast cancer is the most common cancer in women worldwide and the second leading cause of cancer deaths after lung cancer. Lifetime risk of developing invasive breast cancer is approximately 1 in 8 women. Screen-Film Mammography (SFM), providing structural tissue properties by means of X-ray attenuation differences, is currently the most effective modality in detecting breast lesions such as masses, microcalcification (MC) clusters and architectural distortions.

SFM, although characterized by high spatial resolution (25 μm pixel size), is challenged by the relatively low image contrast, especially in case of dense breast parenchyma. Limitations of SFM are attributed to 3D information loss, due to projection geometry, and the sigmoid response curve (characteristic curve) of the screen-film, as image detector.

A natural extension of SFM is achieved by Full-Field Digital Mammography (FFDM) overcoming screen-film response limitation by the linear and broader characteristic curve of direct or indirect digital detectors (Williams et al., 2006). At present, the only technical limitation of FFDM is spatial resolution (40 μm pixel size). The higher detection accuracy of FFDM is demonstrated in screening of dense breasts (Pisano et al., 2005). Up to date, eight FFDM units have been approved by FDA1. Detection performance of FFDM is further enhanced by the capability to manipulate lesion-to-background contrast with image processing tools offered by viewing mammograms in softcopy display workstations. Recently, in an attempt to deal with 3D information loss, often resulting in misdetection of lesions obscured by overlapping dense parenchyma, Digital Breast Tomosynthesis has been introduced (Park et al., 2007). This is achieved by acquiring a small number of 2D projection images and adequately reconstructing tomographic images (slices) with respect to breast depth (z-axis).

When biological processes underlying disease are not captured by X-ray imaging, insight to additional structural and functional tissue properties as well as 3D imaging is exploited by modalities adjunct to mammography, such as Ultrasound (US) and Magnetic Resonance Imaging (MRI).

MRI acquires the nuclear magnetic resonance signal from hydrogen nuclei of tissue. By applying 3D encoded magnetic fields, time constants T1 and T2, characterizing the recovery of longitudinal and transverse magnetization respectively, provide unique biophysical properties used to differentiate contrast among tissues. In addition to 3D spatial information of anatomical structures, Dynamic Contrast-Enhanced MRI (DCE-MRI) offers a functional approach to imaging based on differentiation of malignant from benign tissue with respect to cellular composition, permeability and microvessel density. DCE-MRI data captures kinetics of contrast agents in targeted tissues (Wu & Markey, 2006).

Computer-Aided Detection and Diagnosis (CADe and CADx) schemes have been proposed across breast imaging modalities, acting as clinical tools that provide a “second opinion” to radiologists, with mammography being the most successful paradigm (Sampat et al., 2005).

CADe systems have been developed to improve radiologists’ performance in detecting breast lesions, by identifying suspicious regions of masses and MC clusters. CADe methodologies employed and performances achieved are provided in excellent reviews (Tourassi, 2005; Chan et al., 2005; Sampat et al., 2005). High performance mammographic CADe schemes have been incorporated in commercially available, FDA approved systems2. The impact of CADe systems, i.e. significant increase of breast cancers detected with an acceptable increase of recall rate, is reported in peer-reviewed retrospective and prospective studies, although with some criticism (Fenton et al., 2007).

CADx systems in breast imaging aim to assist radiologists in the diagnostic task of lesion characterization (malignancy vs. benignity), thus affecting patient management (follow-up vs. biopsy). The development of CADx systems is still ongoing in breast imaging (Suri et al., 2006). The advent of intra- and inter-modality computerized analysis broadens the role of CADe/CADx schemes both in terms of image feature fusion and/or image data fusion.

Key Terms in this Chapter

Mammography: The most effective imaging modality in detecting breast lesions such as masses, microcalcification clusters and architectural distortions, providing structural tissue properties by means of X-ray attenuation differences.

Feature Selection: Strategy to avoid supervised classification overtraining in case of a high feature dimensionality in small training datasets. Depending on feature selection method and criterion used, sets of the most discriminant features are obtained improving classification accuracy.

Feature Extraction: Quantification of image content by means of computer algorithms, aiming to capture tissue alterations, due to underlying biological processes reflected either as morphology or as texture variations, mimicking or complementing radiologist interpretation, used in subsequent pattern analysis.

Computer-Aided Diagnosis (CADx): CADx systems in breast imaging are fully automated computer vision algorithms developed to improve radiologists’ performance in characterizing breast lesion status (malignant vs. benign), by providing probability estimates of lesions’ malignancy.

Computer-Aided Detection (CADe): CADe systems in breast imaging are fully automated computer vision algorithms developed to improve radiologists’ performance in detecting breast lesions, by identifying suspicious regions in a breast image or series of images.

Lesion Segmentation: The process of delineating the boundary of a lesion from an image or image series either by use of interactive computer tools (manual) or by automated image segmentation algorithms.

Complete Chapter List

Search this Book:
Editorial Advisory Board
Table of Contents
Themis P. Exarchos, Athanasios Papadopoulos, Dimitrios I. Fotiadis
Chapter 1
Ioannis Dimou, Michalis Zervakis, David Lowe, Manolis Tsiknakis
The automation of diagnostic tools and the increasing availability of extensive medical datasets in the last decade have triggered the development... Sample PDF
Computational Methods and Tools for Decision Support in Biomedicine: An Overview of Algorithmic Challenges
Chapter 2
William Hsu, Alex A.T. Bui, Ricky K. Taira, Hooshang Kangarloo
Though an unparalleled amount and diversity of imaging and clinical data are now collected as part of routine care, this information is not... Sample PDF
Integrating Imaging and Clinical Data for Decision Support
Chapter 3
Spyretta Golemati, John Stoitsis, Konstantina S. Nikita
The estimation of motion of the myocardial and arterial wall is important for the quantification of tissue elasticity and contractility and has... Sample PDF
Analysis and Quantification of Motion within the Cardiovascular System: Implications for the Mechanical Strain of Cardiovascular Structures
Chapter 4
Christos V. Bourantas, Katerina Naka, Dimitrios Fotiadis, Lampros Michalis
Intracoronary Ultrasound (ICUS) imaging is an intravascular catheter-based technique which provides real-time, high resolution, cross-sectional... Sample PDF
New Developments in Intracoronary Ultrasound Processing
Chapter 5
Stavroula Mougiakakou, Ioannis Valavanis, Alexandra Nikita, Konstantina S. Nikita
Recent advances in computer science provide the intelligent computation tools needed to design and develop Diagnostic Support Systems (DSSs) that... Sample PDF
Diagnostic Support Systems and Computational Intelligence: Differential Diagnosis of Hepatic Lesions from Computed Tomography Images
Chapter 6
Marotesa Voultsidou, J. Michael Herrmann
Indicative features of an fMRI data set can be evaluated by methods provided by theory of random matrices (RMT). RMT considers ensembles of matrices... Sample PDF
Significance Estimation in fMRI from Random Matrices
Chapter 7
Dimitrios C. Karampinos, Robert Dawe, Konstantinos Arfanakis, John G. Georgiadis
Diffusion Magnetic Resonance Imaging (diffusion MRI) can provide important information about tissue microstructure by probing the diffusion of water... Sample PDF
Optimal Diffusion Encoding Strategies for Fiber Mapping in Diffusion MRI
Chapter 8
Dimitrios G. Tsalikakis, Petros S. Karvelis, Dimitrios I. Fotiadis
Segmentation plays a crucial role in cardiac magnetic resonance imaging (CMRI) applications, since it permits automated detection of regions of... Sample PDF
Segmentation of Cardiac Magnetic Resonance Images
Chapter 9
Katia Marina Passera, Luca Tommaso Mainardi
Image registration is the process of determining the correspondence of features between images collected at different times or using different... Sample PDF
Image Registration Algorithms for Applications in Oncology
Chapter 10
Lena Costaridou, Spyros Skiadopoulos, Anna Karahaliou, Nikolaos Arikidis, George Panayiotakis
Breast cancer is the most common cancer in women worldwide. Mammography is currently the most effective modality in detecting breast cancer... Sample PDF
Computer-Aided Diagnosis in Breast Imaging: Trends and Challenges
Chapter 11
E. Kyriacou, C.I. Christodoulou, C. Loizou, M.S. Pattichis, C.S. Pattichis, S. Kakkos
Stroke is the third leading cause of death in the Western world and a major cause of disability in adults. The objective of this work was to... Sample PDF
Assessment of Stroke by Analysing Cartoid Plaque Morphology
Chapter 12
Marios Neofytou, Constantinos Pattichis, Vasilios Tanos, Marios Pattichis, Eftyvoulos Kyriacou
The objective of this chapter is to propose a quantitative hysteroscopy imaging analysis system in gynaecological cancer and to provide the current... Sample PDF
Quantitative Analysis of Hysteroscopy Imaging in Gynecological Cancer
Chapter 13
Thomas V. Kilindris, Kiki Theodorou
Patient anatomy, biochemical response, as well functional evaluation at organ level, are key fields that produce a significant amount of multi modal... Sample PDF
Combining Geometry and Image in Biomedical Systems: The RT TPS Case
Chapter 14
Ioannis Tsougos, George Loudos, Panagiotis Georgoulias, Konstantina S. Nikita, Kiki Theodorou
Quantitative three-dimensional nuclear medical imaging plays a continuously increasing role in radionuclide dosimetry, allowing the development of... Sample PDF
Internal Radionuclide Dosimetry using Quantitative 3-D Nuclear Medical Imaging
Chapter 15
Evanthia E. Tripoliti, Dimitrios I. Fotiadis, Konstantia Veliou
Diffusion Tensor Imaging (DTI) is a magnetic resonance imaging (MRI) modality which can significantly improve our understanding of the brain... Sample PDF
Diffusion Tensor Imaging and Fiber Tractography
Chapter 16
Anastasios Koutlas, Dimitrios I. Fotiadis
The aim of this chapter is to analyze the recent advances in image processing and machine learning techniques with respect to facial expression... Sample PDF
Image Processing and Machine Learning Techniques for Facial Expression Recognition
Chapter 17
Arcangelo Merla
This chapter presents an overview on recent developments in the field of clinical applications of the functional infrared imaging. The functional... Sample PDF
Developments and Advances in Biomedical Functional Infrared Imaging
Chapter 18
Aristotelis Chatziioannou, Panagiotis Moulos
The completion of the Human Genome Project and the emergence of high-throughput technologies at the dawn of the new millennium, are rapidly changing... Sample PDF
DNA Microarrays: Analysis and Interpretation
Chapter 19
Nikolaos Giannakeas, Dimitrios I. Fotiadis
Microarray technology allows the comprehensive measurement of the expression level of many genes simultaneously on a common substrate. Typical... Sample PDF
Image Processing and Machine Learning Techniques for the Segmentation of cDNA
Chapter 20
Petros S. Karvelis, Dimitrios I. Fotiadis
Automated chromosome analysis is now becoming routine in most human cytogenetics laboratories. It involves both processing and analysis of digital... Sample PDF
Recent Advances in Automated Chromosome Image Analysis
Chapter 21
O. Lezoray, G. Lebrun, C. Meurie, C. Charrier, A. Elmotataz, M. Lecluse
The segmentation of microscopic images is a challenging application that can have numerous applications ranging from prognosis to diagnosis.... Sample PDF
Machine Learning in Morphological Segmentation
Chapter 22
Michael Haefner, Alfred Gangl, Michael Liedlgruber, A. Uhl, Andreas Vecsei, Friedrich Wrba
Wavelet-, Fourier-, and spatial domain-based texture classification methods have been used successfully for classifying zoom-endoscopic colon images... Sample PDF
Pit Pattern Classification Using Multichannel Features and Multiclassification
Chapter 23
C. Papaodysseus, P. Rousopoulos, D. Arabadjis, M. Panagopoulos, P. Loumou
In this chapter the state of the art is presented in the domain of automatic identification and classification of bodies on the basis of their... Sample PDF
Automatic Identification and Elastic Properties of Deformed Objects Using their Microscopic Images
Chapter 24
Alexia Giannoula, Richard S.C. Cobbold
“Elastography” or “elasticity imaging” can be defined as the science and methodology of estimating the mechanical properties of a medium (including... Sample PDF
Nonlinear Ultrasound Radiation-Force Elastography
Chapter 25
Valentina Russo, Roberto Setola
The aim of this chapter is to provide an overview about models and methodologies used for the Dynamic Contrast Enhancement (DCE) analysis. DCE is a... Sample PDF
Dynamic Contrast Enhancement: Analysis's Models and Methodologies
Chapter 26
George K. Matsopoulos
The accurate estimation of point correspondences is often required in a wide variety of medical image processing applications including image... Sample PDF
Automatic Correspondence Methods towards Point-Based Medical Image Registration: An Evaluation Study
Chapter 27
Alberto Taboada-Crispi, Hichem Sahli, Denis Hernandez-Pacheco, Alexander Falcon-Ruiz
Various approaches have been taken to detect anomalies, with certain particularities in the medical image scenario, linked to other terms... Sample PDF
Anomaly Detection in Medical Image Analysis
Chapter 28
C. Delgorge-Rosenberger, C. Rosenberger
The authors present in this chapter an overview on evaluation of medical image compression. The different methodologies used in the literature are... Sample PDF
Evaluation of Medical Image Compression
Chapter 29
Charalampos Doukas, Ilias Maglogiannis
Medical images are often characterized by high complexity and consist of high resolution image files, introducing thus several issues regarding... Sample PDF
Advanced ROI Coding Techniques for Medical Imaging
Chapter 30
Farhang Sahba
Ultrasound imaging now has widespread clinical use. It involves exposing a part of the body to highfrequency sound waves in order to generate images... Sample PDF
Segmentation Methods in Ultrasound Images
About the Editors
About the Contributors