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. This book 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
Breast cancer diagnosis by combination of fuzzy systems and an ant
colony optimization algorithm is proposed. 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.
© 2013 Society of Photo-Optical Instrumentation Engineers (SPIE)