System for Breast Tissue Recognition in Digital Mammograms

Breast cancer is the most common cancer in women worldwide. The conventional visual-inspection method for early breast-cancer detection is impractical non reproducible and may bestows ambiguous results. Early detection of breast-cancer greatly improves the chance of survival. Therefore a fully automated accurate and reliable computerized method it highly needed. This book therefore provides a new metric of success of CAD system for detecting abnormal regions on mammogram using image processing technique. Two methods have been used to achieve this objective and was the first method is full automatic system using shock filter where it has the ability to remove background noise and the pectoral muscle it also can increase contrast on abnormal region in mammogram. The second method is semi automatic system it consist of three phases: choose sub image then extract features and classify these features by Linear Discriminate Analysis (LDA) with accuracy 96.8%. the system is useful especially for doctors to detect abnormal areas in mammograms in real time or anyone else who may be interested in research development for CADs to diagnose breast cancer in early stages.