A review of computer-aided detection and diagnosis of breast cancer in digital mammography

Abstract

Mammography is the most valuable existing examination tool for the detection of early signs of breast cancer such as masses, calcifications, bilateral asymmetry and architectural distortion. Mammographic screening has been shown to be effective in reducing breast cancer mortality rates by 30-70%, as confirmed from available screening programs. However, mammograms are difficult to interpret, especially in the screening of physical aberrations. Studies have shown that the sensitivity of screening mammography is influenced by image quality and the radiologist’s level of proficiency. Over the years, computers have played a significant role in detecting early signs of cancer because of the limitations of human observation, hence a lot of research is presently being embarked on to develop Computer Aided Detection systems (CAD) of high accuracy. This paper presents a concise review of some of the advanced computer-aided detection and diagnosis methods currently being utilized to improve the intrinsic aspects of CAD, which include: contrast enhancement, detection and analysis of calcifications, masses and tumors, analysis of bilateral asymmetry and detection of architectural distortion.